Mobile agents show immense potential, yet current state-of-the-art (SoTA) agents exhibit inadequate success rates on real-world, long-horizon, cross-application tasks. We attribute this bottleneck to the agents' excessive reliance on static, internal knowledge within MLLMs, which leads to two critical failure points: 1) strategic hallucinations in high-level planning and 2) operational errors during low-level execution on user interfaces (UI). The core insight of this paper is that high-level planning and low-level UI operations require fundamentally distinct types of knowledge. Planning demands high-level, strategy-oriented experiences, whereas operations necessitate low-level, precise instructions closely tied to specific app UIs. Motivated by these insights, we propose Mobile-Agent-RAG, a novel hierarchical multi-agent framework that innovatively integrates dual-level retrieval augmentation. At the planning stage, we introduce Manager-RAG to reduce strategic hallucinations by retrieving human-validated comprehensive task plans that provide high-level guidance. At the execution stage, we develop Operator-RAG to improve execution accuracy by retrieving the most precise low-level guidance for accurate atomic actions, aligned with the current app and subtask. To accurately deliver these knowledge types, we construct two specialized retrieval-oriented knowledge bases. Furthermore, we introduce Mobile-Eval-RAG, a challenging benchmark for evaluating such agents on realistic multi-app, long-horizon tasks. Extensive experiments demonstrate that Mobile-Agent-RAG significantly outperforms SoTA baselines, improving task completion rate by 11.0% and step efficiency by 10.2%, establishing a robust paradigm for context-aware, reliable multi-agent mobile automation.

Image fusion seeks to seamlessly integrate foreground objects with background scenes, producing realistic and harmonious fused images. While existing methods often insert objects directly, adaptive and interactive fusion-requiring contextual adaptation and foreground-background interplay-remains a challenging yet critical task. To address this, we first propose a pipeline for generating high-quality fusion data. By combining iterative in-context learning with existing tools, we curate a diverse cross-scene dataset supporting three core tasks: object integration, replacement, and attribute-referenced editing. Leveraging this, we introduce DreamFuse, a unified diffusion-based approach that jointly optimizes these capabilities. DreamFuse exploits the Diffusion Transformer (DiT) architecture, using its attention mechanism to extract and align foreground-background features for coherent fusion. For flexible control, we incorporate a Positional Affine mechanism, enabling precise spatial and scale adjustments while supporting diverse text-driven fusion. Furthermore, we employ Localized Direct Preference Optimization (L-DPO), refining the model via human feedback to enhance harmony and consistency. Extensive experimental results demonstrate DreamFuse's superiority over state-of-the-art approaches across multiple metrics.

Semi-supervised object detection (SSOD) mitigates the annotation burden in object detection by leveraging unlabeled data, providing a scalable solution for modern perception systems. Concurrently, detection transformers (DETRs) have emerged as a popular end-to-end framework, offering advantages such as non-maximum suppression (NMS)-free inference. However, existing SSOD methods are predominantly designed for conventional detectors, leaving the exploration of DETR-based SSOD largely uncharted. This paper presents a systematic study to bridge this gap. We begin by identifying two principal obstacles in semi-supervised DETR training: (1) the inherent one-to-one assignment mechanism of DETRs is highly sensitive to noisy pseudo-labels, which impedes training efficiency; and (2) the query-based decoder architecture complicates the design of an effective consistency regularization scheme, limiting further performance gains. To address these challenges, we propose Semi-DETR++, a novel framework for efficient SSOD with DETRs. Our approach introduces a stage-wise hybrid matching strategy that enhances robustness to noisy pseudo-labels by synergistically combining one-to-many and one-to-one assignments while preserving NMS-free inference. Furthermore, based on our observation of the unique layer-wise decoding behavior in DETRs, we develop a simple yet effective re-decode query consistency training method to regularize the decoder. Extensive experiments demonstrate that Semi-DETR++ enables more efficient semi-supervised learning across various DETR architectures, outperforming existing methods by significant margins. The proposed components are also flexible and versatile, showing superior generalization by readily extending to semi-supervised segmentation tasks.

Continual image super-resolution (CISR) aims to efficiently adapt a pre-trained model to a variety of tasks while retaining knowledge from previously learned tasks, minimizing the need for intensive independent training. The primary challenges include catastrophic forgetting due to varying data distributions and degradation types, along with the necessity for high adaptability. While prompt-based continual learning has proven effective in image classification, its direct application to super-resolution (SR) often fails to meet the demands for detailed pixel-level restoration and domain discrimination in low-level characteristics. To address these challenges, we propose Learning Prompt Adapters (LPA), which dynamically generates pixel-wise prompts through a combination of multi-granularity prompt bases and identities. By adaptively integrating these prompts into the Transformer architecture, we effectively improve the model's performance on fine-grained details in super-resolution tasks, as well as enhancing the model's adaptability to new tasks and preserving knowledge from previous ones. Through organizing the low-rank prompt bases with specific identities, we set up an effective solution to managing cross-task differences and enhancing prompt richness. Extensive experiments on benchmarks comprising the NYU, RealSR, DIV2K, REDS, and MANGA109 datasets with diverse degradation types demonstrate that LPA significantly outperforms existing continual learning methods. Codes of this paper are available at: https://github.com/dummerchen/LPA.

Synthesizing human motion from textual descriptions is essential for immersive digital applications, yet existing methods face a persistent trade-off between semantic fidelity and physical realism. Large language model (LLM)-based approaches can interpret diverse open-vocabulary instructions and compose high-level action plans, but they often generate motions that violate physical constraints. Physics-aware models improve realism through simulation or control, but they struggle with semantic complexity, fine-grained instructions, and novel concepts. To address this gap, we propose In-Context Model Predictive Generation (ICMPG), a framework that integrates language-model planning with inference-time physical feedback. ICMPG reformulates motion synthesis as a Model Predictive Control (MPC)-like process with two modules. The Context-Aware Motion Generation (CAMG) module uses an LLM as a planner to decompose textual commands and generate candidate motion sequences from motion tokens. The Model Predictive Generation (MPG) module evaluates these candidates through physical simulation and semantic alignment, estimates a composite reward, and selects the best sequence to guide subsequent generation steps. Unlike open-loop generation, this closed-loop refinement enables ICMPG to adapt motions to both the input semantics and the simulated physical environment without task-specific policy retraining. Extensive experiments across standard and zero-shot open-vocabulary settings show that ICMPG generalizes robustly to diverse commands and produces motions that are more physically plausible and semantically faithful than representative baselines on the evaluated benchmarks. The framework bridges semantic interpretation and physical simulation while remaining flexible enough to incorporate different LLM backbones, enabling more versatile and controllable text-driven motion synthesis.

Self-supervised learning has shown potential in fine-grained visual recognition (FGVR). However, existing self-supervised learning methods are often susceptible to irrelevant patterns during training and lack the ability to capture the critical subtle differences in FGVR, leading to suboptimal performance. Moreover, existing approaches focus primarily on uni-modal visual concepts. Despite the emergence of powerful vision-language models (VLMs) in various high-level vision tasks, their potential in self-supervised FGVR remains largely unexplored. To this end, we propose a novel self-supervised learning (LearnMat) framework, that effectively filters out irrelevant feature interference and extracts more important and subtle discriminative features during training. Specifically, LearnMat consists of two key modules: the semantic awareness module (SAM) and the insight extraction module (IEM). In the SAM, we introduce a novel vision-language-grounded semantic distillation strategy using a corpus of generic, category-agnostic textual attributes, that injects explicit semantic constraints into self-supervised training and improves robustness to background interference. Complementarily, the IEM exploits gradient-based signals from the input image to highlight subtle differences and localize key discriminative regions, mitigating inter-class similarity and intra-class variation, and enhancing fine-grained discrimination. Extensive experiments across multiple popular FGVR datasets show that LearnMat significantly outperforms recent state-of-the-art methods, highlighting its marked effectiveness. Our code is avaliable at https://github.com/Heng-CHY/LearnMat.

Audio-driven talking face video generation has attracted increasing attention due to its huge industrial potential. Some previous methods focus on learning a direct mapping from audio to visual content. Despite progress, they often struggle with the ambiguity of the mapping process, leading to flawed results. An alternative strategy involves facial structural representations (e.g., facial landmarks) as intermediaries. This multi-stage approach better preserves the appearance details but suffers from error accumulation due to the independent optimization of different stages. Moreover, most previous methods rely on generative adversarial networks, prone to training instability and mode collapse. To address these challenges, our study proposes a novel landmark-based diffusion model for talking face generation, which leverages facial landmarks as intermediate representations while enabling end-to-end optimization. Specifically, we first establish the less ambiguous mapping from audio to landmark motion of lip and jaw. Then, we introduce an innovative conditioning module called TalkFormer to align the synthesized motion with the motion represented by landmarks via differentiable cross-attention, which enables end-to-end optimization for improved lip synchronization. Besides, TalkFormer employs implicit feature warping to align the reference image features with the target motion for preserving more appearance details. Extensive experiments demonstrate that our approach can synthesize high-fidelity and lip-synced talking face videos, preserving more subject appearance details from the reference image.

Histology image segmentation is a critical prerequisite to pathological diagnosis. Accurate segmentation of these images can significantly aid physicians by facilitating quicker and more precise diagnostic decisions. A notable challenge in this area arises from the fact that different objects within histology images require segmentation at varying magnifications. However, most existing models are typically limited to performing segmentation at one pre-determined magnification. In this paper, we propose a novel universal scale transformer model (UniScaleFormer), which employs a scale-aware approach and integrates textual input to uniformly segment objects in histology images across various magnifications. Our method adopts an end-to-end architecture and utilizes a candidate mask query mechanism, specifically designed to identify and distinguish objects at different image scales. Moreover, we develop a Scale-Aware Module that enhances our network's ability to recognize the magnification level of input histology images, by using a scale query with extracted visual features. Then the scale query is integrated with mask queries, facilitating the incorporation of scale information. Experimental results demonstrate that the proposed method effectively achieves competitive results on various segmentation benchmarks at different magnifications. The code will be released at https://github.com/lhaof/UniScale.

Realistic image super-resolution (SR) focuses on transforming real-world low-resolution (LR) images into high-resolution (HR) ones, handling more complex degradation patterns than synthetic SR tasks. This is critical for applications like surveillance, medical imaging, and consumer electronics. However, current methods struggle with limited real-world LR-HR data, impacting the learning of basic image features. Pre-trained SR models from large-scale synthetic datasets offer valuable prior knowledge, which can improve generalization, speed up training, and reduce the need for extensive real-world data in realistic SR tasks. In this paper, we introduce a novel approach,Dual-domain Adaptation Networks, which is able to efficiently adapt pre-trained image SR models from simulated to real-world datasets. To achieve this target, we first set up a spatial-domain adaptation strategy through selectively updating parameters of pre-trained models and employing the low-rank adaptation technique to adjust frozen parameters. Recognizing that image super-resolution involves recovering high-frequency components, we further integrate a frequency domain adaptation branch into the adapted model, which combines the spectral data of the input and the spatial-domain backbone's intermediate features to infer HR frequency maps, enhancing the SR result. Experimental evaluations on public realistic image SR benchmarks, including RealSR, D2CRealSR, and DRealSR, demonstrate the superiority of our proposed method over existing state-of-the-art models.

Visible watermark removal which involves watermark cleaning and background content restoration is pivotal to evaluate the resilience of watermarks. Existing deep neural network (DNN)-based models still struggle with large-area watermarks and are overly dependent on the quality of watermark mask prediction. To overcome these challenges, we introduce a novel feature adapting framework that leverages the representation modeling capacity of a pre-trained image inpainting model. Our approach bridges the knowledge gap between image inpainting and watermark removal by fusing information of the residual background content beneath watermarks into the inpainting backbone model. We establish a dual-branch system to capture and embed features from the residual background content, which are merged into intermediate features of the inpainting backbone model via gated feature fusion modules. Moreover, for relieving the dependence on high-quality watermark masks, we introduce a new training paradigm by utilizing coarse watermark masks to guide the inference process. This contributes to a visible image removal model which is insensitive to the quality of watermark mask during testing. Extensive experiments on both a large-scale synthesized dataset and a real-world dataset demonstrate that our approach significantly outperforms existing state-of-the-art methods. The source code is available in the supplementary materials.

Audio-driven talking head synthesis is a critical task in digital human modeling. While recent advances using diffusion models and Neural Radiance Fields (NeRF) have improved visual quality, they often require substantial computational resources, limiting practical deployment. We present a novel framework for audio-driven talking head synthesis, namely it Hierarchically Controlled Deformable 3D Gaussians (HiCoDe), which achieves state-of-the-art performance with significantly reduced computational costs. Our key contribution is a hierarchical control strategy that effectively bridges the gap between sparse audio features and dense 3D Gaussian point clouds. Specifically, this strategy comprises two control levels: i) coarse-level control based on a 3D Morphable Model (3DMM) and ii) fine-level control using facial landmarks. Extensive experiments on the HDTF dataset and additional test sets demonstrate that our method outperforms existing approaches in visual quality, facial landmark accuracy, and audio-visual synchronization while being more computationally efficient in both training and inference.

Virtual Try-On (VTON) is a transformative technology in e-commerce and fashion design, enabling realistic digital visualization of clothing on individuals. In this work, we propose VTON 360, a novel 3D VTON method that addresses the open challenge of achieving high-fidelity VTON that supports any-view rendering. Specifically, we leverage the equivalence between a 3D model and its rendered multi-view 2D images, and reformulate 3D VTON as an extension of 2D VTON that ensures 3D consistent results across multiple views. To achieve this, we extend 2D VTON models to include multi-view garments and clothing-agnostic human body images as input, and propose several novel techniques to enhance them, including: i) a pseudo-3D pose representation using normal maps derived from the SMPL-X 3D human model, ii) a multi-view spatial attention mechanism that models the correlations between features from different viewing angles, and iii) a multi-view CLIP embedding that enhances the garment CLIP features used in 2D VTON with camera information. Extensive experiments on large-scale real datasets and clothing images from e-commerce platforms demonstrate the effectiveness of our approach. Project page: https://scnuhealthy.github.io/VTON360.

Generating natural listener responses in conversational scenarios is crucial for creating engaging digital humans and avatars. Recent work has shown that large language models (LLMs) can be effectively leveraged for this task, demonstrating remarkable capabilities in generating contextually appropriate listener behaviors. However, current LLM-based methods face two critical limitations: they rely solely on speech content, overlooking other crucial communication signals, and they entangle listener identity with response generation, compromising output fidelity and generalization. In this work, we present a novel framework that addresses these limitations while maintaining the advantages of LLMs. Our approach introduces a Multimodal-LM architecture that jointly processes speech content, acoustics, and speaker emotion, capturing the full spectrum of communication cues. Additionally, we propose an identity disentanglement strategy using instance normalization and adaptive instance normalization in a VQ-VAE framework, enabling high-fidelity listening head synthesis with flexible identity control. Extensive experiments demonstrate that our method significantly outperforms existing approaches in terms of response naturalness and fidelity, while enabling effective identity control without retraining.

3D Question Answering (3D QA) requires the model to comprehensively understand its situated 3D scene described by the text, then reason about its surrounding environment and answer a question under that situation. However, existing methods usually rely on global scene perception from pure 3D point clouds and overlook the importance of rich local texture details from multi-view images. Moreover, due to the inherent noise in camera poses and complex occlusions, there exists significant feature degradation and reduced feature robustness problems when aligning 3D point cloud with multi-view images. In this paper, we propose a Dual-vision Scene Perception Network (DSPNet), to comprehensively integrate multi-view and point cloud features to improve robustness in 3D QA. Our Text-guided Multi-view Fusion (TGMF) module prioritizes image views that closely match the semantic content of the text. To adaptively fuse back-projected multi-view images with point cloud features, we design the Adaptive Dual-vision Perception (ADVP) module, enhancing 3D scene comprehension. Additionally, our Multimodal Context-guided Reasoning (MCGR) module facilitates robust reasoning by integrating contextual information across visual and linguistic modalities. Experimental results on SQA3D and ScanQA datasets demonstrate the superiority of our DSPNet. Codes will be available at https://github.com/LZ-CH/DSPNet.

Existing Vision-Language Navigation (VLN) methods primarily focus on single-stage navigation, limiting their effectiveness in multi-stage and long-horizon tasks within complex and dynamic environments. To address these limitations, we propose a novel VLN task, named Long-Horizon Vision-Language Navigation (LH-VLN), which emphasizes long-term planning and decision consistency across consecutive subtasks. Furthermore, to support LH-VLN, we develop an automated data generation platform NavGen, which constructs datasets with complex task structures and improves data utility through a bidirectional, multi-granularity generation approach. To accurately evaluate complex tasks, we construct the Long-Horizon Planning and Reasoning in VLN (LHPR-VLN) benchmark consisting of 3,260 tasks with an average of 150 task steps, serving as the first dataset specifically designed for the long-horizon vision-language navigation task. Furthermore, we propose Independent Success Rate (ISR), Conditional Success Rate (CSR), and CSR weight by Ground Truth (CGT) metrics, to provide fine-grained assessments of task completion. To improve model adaptability in complex tasks, we propose a novel Multi-Granularity Dynamic Memory (MGDM) module that integrates short-term memory blurring with long-term memory retrieval to enable flexible navigation in dynamic environments. Our platform, benchmark and method supply LH-VLN with a robust data generation pipeline, comprehensive model evaluation dataset, reasonable metrics, and a novel VLN model, establishing a foundational framework for advancing LH-VLN.

Driven by the great success of Large Language Models (LLMs) in the 2D image domain, their application in 3D scene understanding has emerged as a new trend. A key difference between 3D and 2D is that the situation of an egocentric observer in 3D scenes can change, resulting in different descriptions (e.g., "left" or "right"). However, current LLM-based methods overlook the egocentric perspective and use datasets from a global viewpoint. To address this issue, we propose a novel approach to automatically generate a situation-aware dataset by leveraging the scanning trajectory during data collection and utilizing Vision-Language Models (VLMs) to produce high-quality captions and question-answer pairs. Furthermore, we introduce a situation grounding module to explicitly predict the position and orientation of the observer’s viewpoint, thereby enabling LLMs to ground situation descriptions in 3D scenes. We evaluate our approach on several benchmarks, demonstrating that our method effectively enhances the 3D situational awareness of LLMs while significantly expanding existing datasets and reducing manual effort.

Class-Incremental/Continual image segmentation (CIS) aims to train an image segmenter in stages, where the set of available categories differs at each stage. To leverage the built-in objectness of query-based transformers, which mitigates catastrophic forgetting of mask proposals, current methods often decouple mask generation from the continual learning process. This study, however, identifies two key issues with decoupled frameworks: loss of plasticity and heavy reliance on input data order. To address these, we conduct an in-depth investigation of the built-in objectness and find that highly aggregated image features provide a shortcut for queries to generate masks through simple feature alignment. Based on this, we propose SimCIS, a simple yet powerful baseline for CIS. Its core idea is to directly select image features for query assignment, ensuring "perfect alignment" to preserve objectness, while simultaneously allowing queries to select new classes to promote plasticity. To further combat catastrophic forgetting of categories, we introduce cross-stage consistency in selection and an innovative "visual query"-based replay mechanism. Experiments demonstrate that SimCIS consistently outperforms state-of-the-art methods across various segmentation tasks, settings, splits, and input data orders. All models and codes will be made publicly available at https://github.com/SooLab/SimCIS.

Text-driven avatar generation has gained significant attention owing to its convenience. However, existing methods typically model the human body with all garments as a single 3D model, limiting its usability, such as clothing replacement, and reducing user control over the generation process. To overcome the limitations above, we propose DAGSM, a novel pipeline that generates disentangled human bodies and garments from the given text prompts. Specifically, we model each part (e.g., body, upper/lower clothes) of the clothed human as one GS-enhanced mesh (GSM), which is a traditional mesh attached with 2D Gaussians to better handle complicated textures (e.g., woolen, translucent clothes) and produce realistic cloth animations. During the generation, we first create the unclothed body, followed by a sequence of individual cloth generation based on the body, where we introduce a semantic-based algorithm to achieve better human-cloth and garment-garment separation. To improve texture quality, we propose a view-consistent texture refinement module, including a cross-view attention mechanism for texture style consistency and an incident-angle-weighted denoising (IAW-DE) strategy to update the appearance. Extensive experiments have demonstrated that DAGSM generates high-quality disentangled avatars, supports clothing replacement and realistic animation, and outperforms the baselines in visual quality.

Image fusion seeks to seamlessly integrate foreground objects with background scenes, producing realistic and harmonious fused images. Unlike existing methods that directly insert objects into the background, adaptive and interactive fusion remains a challenging yet appealing task. It requires the foreground to adjust or interact with the background context, enabling more coherent integration. To address this, we propose an iterative human-in-the-loop data generation pipeline, which leverages limited initial data with diverse textual prompts to generate fusion datasets across various scenarios and interactions, including placement, holding, wearing, and style transfer. Building on this, we introduce DreamFuse, a novel approach based on the Diffusion Transformer (DiT) model, to generate consistent and harmonious fused images with both foreground and background information. DreamFuse employs a Positional Affine mechanism to inject the size and position of the foreground into the background, enabling effective foreground-background interaction through shared attention. Furthermore, we apply Localized Direct Preference Optimization guided by human feedback to refine DreamFuse, enhancing background consistency and foreground harmony. DreamFuse achieves harmonious fusion while generalizing to text-driven attribute editing of the fused results. Experimental results demonstrate that our method outperforms state-of-the-art approaches across multiple metrics.

Embodied Question Answering (EQA) is a challenging task in embodied intelligence that requires agents to dynamically explore 3D environments, actively gather visual information, and perform multi-step reasoning to answer questions. However, current EQA approaches suffer from critical limitations in exploration efficiency, dataset design, and evaluation metrics. Moreover, existing datasets often introduce biases or prior knowledge, leading to disembodied reasoning, while frontier-based exploration strategies struggle in cluttered environments and fail to ensure fine-grained exploration of task-relevant areas. To address these challenges, we construct the EXPloration-awaRe Embodied queStion anSwering Benchmark (EXPRESS-Bench), the largest dataset designed specifically to evaluate both exploration and reasoning capabilities. EXPRESS-Bench consists of 777 exploration trajectories and 2,044 question-trajectory pairs. To improve exploration efficiency, we propose Fine-EQA, a hybrid exploration model that integrates frontier-based and goal-oriented navigation to guide agents toward task-relevant regions more effectively. Additionally, we introduce a novel evaluation metric, Exploration-Answer Consistency (EAC), which ensures faithful assessment by measuring the alignment between answer grounding and exploration reliability. Extensive experimental comparisons with state-of-the-art EQA models demonstrate the effectiveness of our EXPRESS-Bench in advancing embodied exploration and question reasoning.

In this paper, we propose FakeRadar, a novel deepfake video detection framework designed to address the challenges of cross-domain generalization in real-world scenarios. Existing detection methods typically rely on manipulation-specific cues, performing well on known forgery types but exhibiting severe limitations against emerging manipulation techniques. This poor generalization stems from their inability to adapt effectively to unseen forgery patterns. To overcome this, we leverage large-scale pretrained models (e.g. CLIP) to proactively probe the feature space, explicitly highlighting distributional gaps between real videos, known forgeries, and unseen manipulations. Specifically, FakeRadar introduces Forgery Outlier Probing, which employs dynamic subcluster modeling and cluster-conditional outlier generation to synthesize outlier samples near boundaries of estimated subclusters, simulating novel forgery artifacts beyond known manipulation types. Additionally, we design Outlier-Guided Tri-Training, which optimizes the detector to distinguish real, fake, and outlier samples using proposed outlier-driven contrastive learning and outlier-conditioned cross-entropy losses. Experiments show that FakeRadar outperforms existing methods across various benchmark datasets for deepfake video detection, particularly in cross-domain evaluations, by handling the variety of emerging manipulation techniques.

Temporal sentence grounding aims to identify exact moments in a video that correspond to a given textual query, typically addressed with detection transformer (DETR) solutions. However, we find that typical strategies designed to enhance DETR do not improve, and may even degrade, its performance in this task. We systematically analyze and identify the root causes of this abnormal behavior: (1) conflicts between queries from similar target moments and (2) internal query conflicts due to the tension between global semantics and local localization. Building on these insights, we propose a simple yet powerful baseline, Sim-DETR, which extends the standard DETR with two minor modifications in the decoder layers: (1) constraining self-attention between queries based on their semantic and positional overlap and (2) adding query-to-frame alignment to bridge the global and local contexts. Experiments demonstrate that Sim-DETR unlocks the full potential of DETR for temporal sentence grounding, offering a strong baseline for future research.

Video Multimodal Large Language Models~(Video-MLLM) have achieved remarkable advancements in video understanding tasks. However, constrained by the context length limitation in the underlying LLMs, existing Video-MLLMs typically exhibit suboptimal performance on long video scenarios. To understand extended input frames, common solutions span token compression and streaming inference techniques, which sacrifice feature granularity or inference efficiency. Differently, to efficiently achieve comprehensive understanding of longer frame inputs, we draw ideas from MoE and propose a training-free approach \textbf{Free-MoRef}, which instantly multiplexes the context perception capabilities of Video-MLLMs within one inference pass. Specifically, Free-MoRef reconstructs the vision tokens into several short sequences as multi-references. Subsequently, we introduce MoRef-attention, which gathers clues from the multi-reference chunks in parallel to summarize unified query activations. After the shadow layers in LLMs, a reference fusion step is derived to compose a final mixed reasoning sequence with key tokens from parallel chunks, which compensates the cross-reference vision interactions that are neglected in MoRef-attention. By splitting and fusing the long vision token sequences, Free-MoRef achieves improved performance under much lower computing costs in reasoning multiplexed context length, demonstrating strong efficiency and effectiveness. Experiments on VideoMME, MLVU, LongVideoBench show that Free-MoRef achieves full perception of 2$\times$ to 8$\times$ longer input frames without compression on a single A100 GPU while keeping instant responses, thereby bringing significant performance gains, even surpassing dedicatedly trained long-video-MLLMs. Codes are available at https://github.com/wkfdb/Free-MoRef

Centerline graphs, crucial for path planning in autonomous driving, are traditionally learned using deterministic methods. However, these methods often lack spatial reasoning and struggle with occluded or invisible centerlines. Generative approaches, despite their potential, remain underexplored in this domain. We introduce LaneDiffusion, a novel generative paradigm for centerline graph learning. LaneDiffusion innovatively employs diffusion models to generate lane centerline priors at the Bird's Eye View (BEV) feature level, instead of directly predicting vectorized centerlines. Our method integrates a Lane Prior Injection Module (LPIM) and a Lane Prior Diffusion Module (LPDM) to effectively construct diffusion targets and manage the diffusion process. Furthermore, vectorized centerlines and topologies are then decoded from these prior-injected BEV features. Extensive evaluations on the nuScenes and Argoverse2 datasets demonstrate that LaneDiffusion significantly outperforms existing methods, achieving improvements of 4.2%, 4.6%, 4.7%, 6.4% and 1.8% on fine-grained point-level metrics (GEO F1, TOPO F1, JTOPO F1, APLS and SDA) and 2.3%, 6.4%, 6.8% and 2.1% on segment-level metrics (IoU, mAP_cf, DET_l and TOP_ll). These results establish state-of-the-art performance in centerline graph learning, offering new insights into generative models for this task.

Recent 3D Gaussian Splatting (3DGS) representations have demonstrated remarkable performance in novel view synthesis; further, material-lighting disentanglement on 3DGS warrants relighting capabilities and its adaptability to broader applications. While the general approach to the latter operation lies in integrating differentiable physically-based rendering (PBR) techniques to jointly recover BRDF materials and environment lighting, achieving a precise disentanglement remains an inherently difficult task due to the challenge of accurately modeling light transport. Existing approaches typically approximate Gaussian points' normals, which constitute an implicit geometric constraint. However, they usually suffer from inaccuracies in normal estimation that subsequently degrade light transport, resulting in noisy material decomposition and flawed relighting results. To address this, we propose GeoSplatting, a novel approach that augments 3DGS with explicit geometry guidance for precise light transport modeling. By differentiably constructing a surface-grounded 3DGS from an optimizable mesh, our approach leverages well-defined mesh normals and the opaque mesh surface, and additionally facilitates the use of mesh-based ray tracing techniques for efficient, occlusion-aware light transport calculations. This enhancement ensures precise material decomposition while preserving the efficiency and high-quality rendering capabilities of 3DGS. Comprehensive evaluations across diverse datasets demonstrate the effectiveness of GeoSplatting, highlighting its superior efficiency and state-of-the-art inverse rendering performance. The project page can be found at https://pku-vcl-geometry.github.io/GeoSplatting/.

Effectively integrating Large Language Models (LLMs) into autonomous driving requires a balance between leveraging high-level reasoning and maintaining real-time efficiency. Existing approaches either activate LLMs too frequently, causing excessive computational overhead, or use fixed schedules, failing to adapt to dynamic driving conditions. To address these challenges, we propose AdaDrive, an adaptively collaborative slow-fast framework that optimally determines when and how LLMs contribute to decision-making. (1) When to activate the LLM: AdaDrive employs a novel adaptive activation loss that dynamically determines LLM invocation based on a comparative learning mechanism, ensuring activation only in complex or critical scenarios. (2) How to integrate LLM assistance: Instead of rigid binary activation, AdaDrive introduces an adaptive fusion strategy that modulates a continuous, scaled LLM influence based on scene complexity and prediction confidence, ensuring seamless collaboration with conventional planners. Through these strategies, AdaDrive provides a flexible, context-aware framework that maximizes decision accuracy without compromising real-time performance. Extensive experiments on language-grounded autonomous driving benchmarks demonstrate that AdaDrive state-of-the-art performance in terms of both driving accuracy and computational efficiency. Code is available at https://github.com/ReaFly/AdaDrive.

Most existing face swapping methods involve decomposing the identity component of a source image into a latent vector and integrating it with a target image at the feature level. However, such methods often encounter challenges in accurately transferring identity while preserving facial structure. In this work, we propose a NeRF-based generative model for face swapping (NeRFSwap). Our core idea is to acquire the 3D representation of an intermediate face whose identity is from the source image and the remaining attributes are from the target image. Subsequently, we employ a novel dual adaptive blending module to generate results conditioned on this 3D representation and the target image at the feature level, which effectively transfers the facial structure from the 3D representation to the target image. Extensive experiments demonstrate the effectiveness of our method and show that NeRFSwap surpasses other state-of-the-art methods in generating high-fidelity images with superior identity transfer.

We introduce Referring 3D Gaussian Splatting Segmentation (R3DGS), a new task that aims to segment target objects in a 3D Gaussian scene based on natural language descriptions, which often contain spatial relationships or object attributes. This task requires the model to identify newly described objects that may be occluded or not directly visible in a novel view, posing a significant challenge for 3D multi-modal understanding. Developing this capability is crucial for advancing embodied AI. To support research in this area, we construct the first R3DGS dataset, Ref-LERF. Our analysis reveals that 3D multi-modal understanding and spatial relationship modeling are key challenges for R3DGS. To address these challenges, we propose ReferSplat, a framework that explicitly models 3D Gaussian points with natural language expressions in a spatially aware paradigm. ReferSplat achieves state-of-the-art performance on both the newly proposed R3DGS task and 3D open-vocabulary segmentation benchmarks. Dataset and code are available at https://github.com/heshuting555/ReferSplat.

In Partial Multi-Label Learning (PML), each instance is associated with a candidate label set containing multiple relevant labels along with other false positive labels. Currently, most PML methods directly extract instance correlation from instance features while ignoring the candidate labels, which may contain more discriminative instance-related information. This paper argues that, with a well-designed model, more accurate instance correlation can be mined from the candidate labels to facilitate label disambiguation. To this end, we propose a novel PML method based on pseudo-label reconstruction (PML-PLR). Specifically, we first propose a novel orthogonal candidate label reconstruction method, which jointly optimizes with instance features to extract more consistent instance correlation. Then, we use instance correlation as reconstruction coefficient to reconstruct pseudo-labels. Subsequently, through local manifold learning, the reconstructed pseudo-labels are leveraged to propagate the consistency relationship between labels and instances, thereby improving the accuracy of pseudo-labels. Extensive experiments and analyses demonstrate that the proposed PML-PLR outperforms state-of-the-art methods.

Pre-trained vision-language models have shown remarkable potential for downstream tasks. However, their fine-tuning under noisy labels remains an open problem due to challenges like self-confirmation bias and the limitations of conventional small-loss criteria. In this paper, we propose a unified framework to address these issues, consisting of three key steps: Screening, Rectifying, and Re-Screening. First, a dual-level semantic matching mechanism is introduced to categorize samples into clean, ambiguous, and noisy samples by leveraging both macro-level and micro-level textual prompts. Second, we design tailored pseudo-labeling strategies to rectify noisy and ambiguous labels, enabling their effective incorporation into the training process. Finally, a re-screening step, utilizing cross-validation with an auxiliary vision-language model, mitigates self-confirmation bias and enhances the robustness of the framework. Extensive experiments across ten datasets demonstrate that the proposed method significantly outperforms existing approaches for tuning vision-language pre-trained models with noisy labels.

Visible watermark removal is crucial for evaluating watermark robustness and advancing more resilient protection techniques. Current methods face challenges in real-world scenarios due to architectural constraints in multi-task frameworks and limited dataset diversity. To address these challenges, we first propose a novel two-stage framework, PatchWiper, consisting of an independent watermark segmentation network and a highly dynamic patch-wise restoration network. This framework decouples watermark localization from background restoration, allowing each network to focus on its designated task. Our restoration network dynamically generates unique parameters for each image patch, enabling fine-grained adaptation to different watermark distortions. Second, we construct the Pixabay Real-world Watermark Dataset (PRWD ), which incorporates diverse background images and over 1,000 distinct watermark types, providing a more comprehensive benchmark for evaluating watermark removal methods. Extensive experiments on PRWD, ILAW, and real-world testing images demonstrate our method's superior performance over existing approaches, particularly in handling complex real-world cases.

3D affordance reasoning plays a critical role in associating human instructions with the functional regions of 3D objects, facilitating precise, task-oriented manipulations in embodied AI. However, current methods, which predominantly depend on sparse 3D point clouds, exhibit limited generalizability and robustness due to their sensitivity to coordinate variations and the inherent sparsity of the data. By contrast, 3D Gaussian Splatting (3DGS) delivers high-fidelity, real-time rendering with minimal computational overhead by representing scenes as dense, continuous distributions. This positions 3DGS as a highly effective approach for capturing fine-grained affordance details and improving recognition accuracy. Nevertheless, its full potential remains largely untapped due to the absence of large-scale, 3DGS-specific affordance datasets. To overcome these limitations, we present 3DAffordSplat, the first large-scale, multi-modal dataset tailored for 3DGS-based affordance reasoning. This dataset includes 23,672 Gaussian instances, 8,231 point cloud instances, and 6,631 manually annotated affordance labels, encompassing 21 object categories and 18 affordance types. Building upon this dataset, we introduce AffordSplatNet, a novel model specifically designed for affordance reasoning using 3DGS representations. AffordSplatNet features an innovative cross-modal structure alignment module that exploits structural consistency priors to align 3D point cloud and 3DGS representations, resulting in enhanced affordance recognition accuracy. Extensive experiments demonstrate that the 3DAffordSplat dataset significantly advances affordance learning within the 3DGS domain, while AffordSplatNet consistently outperforms existing methods across both seen and unseen settings, highlighting its robust generalization capabilities. Code, model, and video are available at https://hcplab-sysu.github.io/3DAffordSplat.

Fine-grained open-vocabulary object detection (FG-OVD) aims to detect novel object categories described by attribute-rich texts. While existing open-vocabulary detectors show promise at the base-category level, they underperform in fine-grained settings due to the semantic entanglement of subjects and attributes in pretrained vision-language model (VLM) embeddings -- leading to over-representation of attributes, mislocalization, and semantic drift in embedding space. We propose GUIDED, a decomposition framework specifically designed to address the semantic entanglement between subjects and attributes in fine-grained prompts. By separating object localization and fine-grained recognition into distinct pathways, GUIDED aligns each subtask with the module best suited for its respective roles. Specifically, given a fine-grained class name, we first use a language model to extract a coarse-grained subject and its descriptive attributes. Then the detector is guided solely by the subject embedding, ensuring stable localization unaffected by irrelevant or overrepresented attributes. To selectively retain helpful attributes, we introduce an attribute embedding fusion module that incorporates attribute information into detection queries in an attention-based manner. This mitigates over-representation while preserving discriminative power. Finally, a region-level attribute discrimination module compares each detected region against full fine-grained class names using a refined vision-language model with a projection head for improved alignment. Extensive experiments on FG-OVD and 3F-OVD benchmarks show that GUIDED achieves new state-of-the-art results, demonstrating the benefits of disentangled modeling and modular optimization.

Offset-based representation has emerged as a promising approach for modeling semantic relations between pixels and object motion, demonstrating efficacy across various computer vision tasks. In this paper, we introduce a novel one-stage multi-tasking network tailored to extend the offset-based approach to MOTS. Our proposed framework, named OffsetNet, is designed to concurrently address amodal bounding box detection, instance segmentation, and tracking. It achieves this by formulating these three tasks within a unified pixel-offset-based representation, thereby achieving excellent efficiency and encouraging mutual collaborations. OffsetNet achieves several remarkable properties: first, the encoder is empowered by a novel Memory Enhanced Linear Self-Attention (MELSA) block to efficiently aggregate spatial-temporal features; second, all tasks are decoupled fairly using three lightweight decoders that operate in a one-shot manner; third, a novel cross-frame offsets prediction module is proposed to enhance the robustness of tracking against occlusions. With these merits, OffsetNet achieves 76.83% HOTA on KITTI MOTS benchmark, which is the best result without relying on 3D detection. Furthermore, OffsetNet achieves 74.83% HOTA at 50 FPS on the KITTI MOT benchmark, which is nearly 3.3 times faster than CenterTrack with better performance. We hope our approach will serve as a solid baseline and encourage future research in this field.

This work studies the problem of finding optimal distributed resource allocation policies on wireless networks in the existence of an unknown malicious adding-edge attacker, depicted as the games of games (GoG) model. Specifically, two subnetwork policymakers constitute a Nash game, while a Stackelberg game captures the confrontation between each subnetwork policymaker and the malicious attacker. We first demonstrate that by utilizing the Foschini-Miljanic algorithm, the communication resource allocation of cellular networks can be converted into a geometric program (GP) that can be efficiently solved by convex optimization. Then, the upper limit of attack magnitude that the network can withstand is calculated. It is shown that the proposed GP framework is solvable within the attack bound and a Gestalt Nash equilibrium (GNE) exists for the GoG. Moreover, a heuristic algorithm that iteratively employs GP is developed to obtain the optimal policy profiles of subnetworks, which can converge asymptotically. Correspondingly, a greedy heuristic adding-edge strategy is proposed to identify the set of the most vulnerable edges for the attacker. Finally, simulation examples show that the obtained algorithm is resilient to malicious attacks and can attain the GNE. Despite the presence of malicious attacks, all channels’ transmission and interference gains can be well-adjusted within a limited budget.

This paper aims to restore original background images in watermarked videos, overcoming challenges posed by traditional approaches that fail to handle the temporal dynamics and diverse watermark characteristics effectively. Our method introduces a unique framework that first "decouples" the extraction of prior knowledge-such as common-sense knowledge and residual background details-from the temporal modeling process, allowing for independent handling of background restoration and temporal consistency. Subsequently, it "couples" these extracted features by integrating them into the temporal modeling backbone of a video inpainting (VI) framework. This integration is facilitated by a specialized module, which includes an intrinsic background image prediction sub-module and a dual-branch frame embedding module, designed to reduce watermark interference and enhance the application of prior knowledge. Moreover, a frame-adaptive feature selection module dynamically adjusts the extraction of prior features based on the corruption level of each frame, ensuring their effective incorporation into the temporal processing. Extensive experiments on YouTube-VOS and DAVIS datasets validate our method's efficiency in watermark removal and background restoration, showing significant improvement over state-of-the-art techniques in visible image watermark removal, video restoration, and video inpainting.

Radiology Report Generation (RRG) is essential for computer-aided diagnosis and medication guidance, which can relieve the heavy burden of radiologists by automatically generating the corresponding radiology reports according to the given radiology image. However, generating accurate lesion descriptions remains challenging due to spurious correlations from visual-linguistic biases and inherent limitations of radiological imaging, such as low resolution and noise interference. To address these issues, we propose a two-stage framework named Cross-Modal Causal Representation Learning (CMCRL), consisting of the Radiological Cross-modal Alignment and Reconstruction Enhanced (RadCARE) pre-training and the Visual-Linguistic Causal Intervention (VLCI) fine-tuning. In the pre-training stage, RadCARE introduces a degradation-aware masked image restoration strategy tailored for radiological images, which reconstructs high-resolution patches from low-resolution inputs to mitigate noise and detail loss. Combined with a multiway architecture and four adaptive training strategies (e.g., text postfix generation with degraded images and text prefixes), RadCARE establishes robust cross-modal correlations even with incomplete data. In the VLCI phase, we deploy causal front-door intervention through two modules: the Visual Deconfounding Module (VDM) disentangles local-global features without fine-grained annotations, while the Linguistic Deconfounding Module (LDM) eliminates context bias without external terminology databases. Experiments on IU-Xray and MIMIC-CXR show that our CMCRL pipeline significantly outperforms state-of-the-art methods, with ablation studies confirming the necessity of both stages. Code and models are available at https://github.com/WissingChen/CMCRL.

Automated polyp segmentation from colonoscopy images is crucial for colorectal cancer diagnosis. The accuracy of such segmentation, however, is challenged by two main factors. First, the variability in polyps' size, shape, and color, coupled with the scarcity of well-annotated data due to the need for specialized manual annotation, hampers the efficacy of existing deep learning methods. Second, concealed polyps often blend with adjacent intestinal tissues, leading to poor contrast that challenges segmentation models. Recently, diffusion models have been explored and adapted for polyp segmentation tasks. However, the significant domain gap between RGB-colonoscopy images and grayscale segmentation masks, along with the low efficiency of the diffusion generation process, hinders the practical implementation of these models. To mitigate these challenges, we introduce the Highlighted Diffusion Model Plus (HDM+), a two-stage polyp segmentation framework. This framework incorporates the Highlighted Diffusion Model (HDM) to provide explicit semantic guidance, thereby enhancing segmentation accuracy. In the initial stage, the HDM is trained using highlighted ground-truth data, which emphasizes polyp regions while suppressing the background in the images. This approach reduces the domain gap by focusing on the image itself rather than on the segmentation mask. In the subsequent second stage, we employ the highlighted features from the trained HDM's U-Net model as plug-in priors for polyp segmentation, rather than generating highlighted images, thereby increasing efficiency. Extensive experiments conducted on six polyp segmentation benchmarks demonstrate the effectiveness of our approach.

Metro Origin-Destination (OD) prediction is a crucial yet challenging spatial-temporal prediction task in urban computing, which aims to accurately forecast cross-station ridership for optimizing metro scheduling and enhancing overall transport efficiency. Analyzing fine-grained and comprehensive relations among stations effectively is imperative for metro OD prediction. However, existing metro OD models either mix information from multiple OD pairs from the station's perspective or exclusively focus on a subset of OD pairs. These approaches may overlook fine-grained relations among OD pairs, leading to difficulties in predicting potential anomalous conditions. To address these challenges, we learn traffic evolution from the perspective of all OD pairs and propose a fine-grained spatialtemporal MLP architecture for metro OD prediction, namely ODMixer. Specifically, our ODMixer has double-branch structure and involves the Channel Mixer, the Multi-view Mixer, and the Bidirectional Trend Learner. The Channel Mixer aims to capture short-term temporal relations among OD pairs, the Multi-view Mixer concentrates on capturing spatial relations from both origin and destination perspectives. To model long-term temporal relations, we introduce the Bidirectional Trend Learner. Extensive experiments on two large-scale metro OD prediction datasets HZMOD and SHMO demonstrate the advantages of our ODMixer. Our code is available at https://github.com/KLatitude/ODMixer

CT-based bronchial tree analysis is a key step for the diagnosis of lung and airway diseases. However, the topology of bronchial trees varies across individuals, which presents a challenge to the automatic bronchus classification. To solve this issue, we propose the Bronchus Classification Network (BCNet), a structure-guided framework that exploits the segment-level topological information using point clouds to learn the voxel-level features. BCNet has two branches, a Point-Voxel Graph Neural Network (PV-GNN) for segment classification, and a Convolutional Neural Network (CNN) for voxel labeling. The two branches are simultaneously trained to learn topology-aware features for their shared backbone while it is feasible to run only the CNN branch for the inference. Therefore, BCNet maintains the same inference efficiency as its CNN baseline. Experimental results show that BCNet significantly exceeds the state-of-the-art methods by over 8.0% both on F1-score for classifying bronchus. Furthermore, we contribute BronAtlas: an open-access benchmark of bronchus imaging analysis with high-quality voxel-wise annotations of both anatomical and abnormal bronchial segments. The benchmark is available at https://osf.io/pskr9/?viewonly=94fa3d87274b4095ac9a4b88cc9a1341.

Nuclei segmentation is critical for computational pathology analysis. Most previous methods employ pixel-wise classification or regression for automatic nuclei segmentation, without describing nucleus instances as individual entities at the feature level. To address the above limitation, we propose an instance-aware multi-task learning framework that strengthens a pixel-wise prediction branch with an instance-wise prediction branch. The instance-wise prediction branch leverages learnable cell-level queries, enabling the model to capture positional information and visual representations for individual nuclei. Concretely, we introduce an instance-disentangling feature learning module that effectively aligns the embeddings of the object-level queries with pixel-wise decoder features from the first branch. Further, we design a dual-branch unified post-processing algorithm that aggregates the complementary outputs of both branches for computing the instance segmentation results. Experimental results demonstrate that our framework achieves competitive performance on a wide range of nuclei segmentation benchmarks. The code and model weights are released in https://github.com/lhaof/IML.

Point cloud sampling aims to derive a sparse point cloud from a relatively dense point cloud, which is essential for efficient data transmission and storage. While existing deep sampling methods prioritize preserving the perception of sampled point clouds for downstream networks, few studies have critically examined the rationale behind this goal. Specifically, we observe that sampling can lead to a perceptual degradation phenomenon in many influential downstream networks, impairing their ability to effectively process sampled point clouds. We theoretically reveal the nature of the phenomenon and attempt to construct a novel sampling target by uniting upsampling and perceptual reconstruction. Accordingly, we propose a Maximum A Posteriori (MAP) sampling framework named Sample for Reconstruct (S4R), which impels the sampling stage to infer upsampling-guided perception. In S4R, we design very simple but effective sampling and upsampling networks using residual-based graph convolutions and incorporate a pseudo-residual connection to introduce prior knowledge. This architecture takes advantage of reconstruction properties and allows the sampling network to be trained in an unsupervised manner. Extensive experiments on classical networks demonstrates the excellent performance of S4R compared with the previous sampling schemes and reveals its advantages on different point cloud downstream tasks, i.e., classification, reconstruction and segmentation.

Federated learning (FL) makes it possible for multiple clients to collaboratively train a machine-learning model through communicating models instead of data, reducing privacy risk. Thus, FL is more suitable for processing data security and privacy for intelligent systems and applications. Unfortunately, there are several challenges in FL, such as the low training accuracy for nonindependent and identically distributed (non-IID) data and the high cost of computation and communication. Considering these, we propose a novel FL framework named dynamic sparse federated contrastive learning (DSFedCon). DSFedCon combines FL with dynamic sparse (DSR) training of network pruning and contrastive learning to improve model performance and reduce computation costs and communication costs. We analyze DSFedCon from the perspective of accuracy, communication, and security, demonstrating it is communication-efficient and safe. To give a practical evaluation for non-IID data training, we perform experiments and comparisons on the MNIST, CIFAR-10, and CIFAR-100 datasets with different parameters of Dirichlet distribution. Results indicate that DSFedCon can get higher accuracy and better communication cost than other state-of-the-art methods in these two datasets. More precisely, we show that DSFedCon has a 4.67-time speedup of communication rounds in MNIST, a 7.5-time speedup of communication rounds in CIFAR-10, and an 18.33-time speedup of communication rounds in CIFAR-100 dataset while achieving the same training accuracy.

Accurate inference of fine-grained traffic flow from coarse-grained one is an emerging yet crucial problem, which can help greatly reduce the number of the required traffic monitoring sensors for cost savings. In this work, we note that traffic flow has a high correlation with road network, which was either completely ignored or simply treated as an external factor in previous works. To facilitate this problem, we propose a novel road-aware traffic flow magnifier (RATFM) that explicitly exploits the prior knowledge of road networks to fully learn the road-aware spatial distribution of fine-grained traffic flow. Specifically, a multidirectional 1-D convolutional layer is first introduced to extract the semantic feature of the road network. Subsequently, we incorporate the road network feature and coarse-grained flow feature to regularize the short-range spatial distribution modeling of road-relative traffic flow. Furthermore, we take the road network feature as a query to capture the long-range spatial distribution of traffic flow with a transformer architecture. Benefiting from the road-aware inference mechanism, our method can generate high-quality fine-grained traffic flow maps. Extensive experiments on three real-world datasets show that the proposed RATFM outperforms state-of-the-art models under various scenarios. Our code and datasets are released at https://github.com/luimoli/RATFM.

Although existing speech-driven talking face generation methods achieve significant progress, they are far from real-world application due to the avatar-specific training demand and unstable lip movements. To address the above issues, we propose the GSmoothFace, a novel two-stage generalized talking face generation model guided by a fine-grained 3D face model, which can synthesize smooth lip dynamics while preserving the speaker's identity. Our proposed GSmoothFace model mainly consists of the Audio to Expression Prediction (A2EP) module and the Target Adaptive Face Translation (TAFT) module. Specifically, we first develop the A2EP module to predict expression parameters synchronized with the driven speech. It uses a transformer to capture the long-term audio context and learns the parameters from the fine-grained 3D facial vertices, resulting in accurate and smooth lip-synchronization performance. Afterward, the well-designed TAFT module, empowered by Morphology Augmented Face Blending (MAFB), takes the predicted expression parameters and target video as inputs to modify the facial region of the target video without distorting the background content. The TAFT effectively exploits the identity appearance and background context in the target video, which makes it possible to generalize to different speakers without retraining. Both quantitative and qualitative experiments confirm the superiority of our method in terms of realism, lip-synchronization, and visual quality.

Point-based interactive image segmentation can ease the burden of mask annotation in applications such as semantic segmentation and image editing. However, fully extracting the target mask with limited user inputs remains challenging. We introduce a novel method, Variance-Insensitive and Target-Preserving Mask Refinement to enhance segmentation quality with fewer user inputs. Regarding the last segmentation result as the initial mask, an iterative refinement process is commonly employed to continually enhance the initial mask. Nevertheless, conventional techniques suffer from sensitivity to the variance in the initial mask. To circumvent this problem, our proposed method incorporates a mask matching algorithm for ensuring consistent inferences from different types of initial masks. We also introduce a target-aware zooming algorithm to preserve object information during downsampling, balancing efficiency and accuracy. Experiments on GrabCut, Berkeley, SBD, and DAVIS datasets demonstrate our method's state-of-the-art performance in interactive image segmentation.

The recognition of multi-class cell nuclei can significantly facilitate the process of histopathological diagnosis. Numerous pathological datasets are currently available, but their annotations are inconsistent. Most existing methods require individual training on each dataset to deduce the relevant labels and lack the use of common knowledge across datasets, consequently restricting the quality of recognition. In this paper, we propose a universal cell nucleus classification framework (UniCell), which employs a novel prompt learning mechanism to uniformly predict the corresponding categories of pathological images from different dataset domains. In particular, our framework adopts an end-to-end architecture for nuclei detection and classification, and utilizes flexible prediction heads for adapting various datasets. Moreover, we develop a Dynamic Prompt Module (DPM) that exploits the properties of multiple datasets to enhance features. The DPM first integrates the embeddings of datasets and semantic categories, and then employs the integrated prompts to refine image representations, efficiently harvesting the shared knowledge among the related cell types and data sources. Experimental results demonstrate that the proposed method effectively achieves the state-of-the-art results on four nucleus detection and classification benchmarks. Code and models are available at https://github.com/lhaof/UniCell

Visible watermarks, while instrumental in protecting image copyrights, frequently distort the underlying content, complicating tasks like scene interpretation and image editing. Visible watermark removal aims to eliminate the interference of watermarks and restore the background content. However, existing methods often implement watermark component removal and background restoration tasks within a singular branch, leading to residual watermarks in the predictions and ignoring cases where watermarks heavily obscure the background. To address these limitations, this study introduces the Removing Interference and Recovering Content Imaginatively (RIRCI) framework. RIRCI embodies a two-stage approach: the initial phase centers on discerning and segregating the watermark component, while the subsequent phase focuses on background content restoration. To achieve meticulous background restoration, our proposed model employs a dual-path network capable of fully exploring the intrinsic background information beneath semi-transparent watermarks and peripheral contextual information from unaffected regions. Moreover, a Global and Local Context Interaction module is built upon multi-layer perceptrons and bidirectional feature transformation for comprehensive representation modeling in the background restoration phase. The efficacy of our approach is empirically validated across two large-scale datasets, and our findings reveal a marked enhancement over existing watermark removal techniques.

Federated Learning with Noisy Labels (F-LNL) aims at seeking an optimal server model via collaborative distributed learning by aggregating multiple client models trained with local noisy or clean samples. On the basis of a federated learning framework, recent advances primarily adopt label noise filtering to separate clean samples from noisy ones on each client, thereby mitigating the negative impact of label noise. However, these prior methods do not learn noise filters by exploiting knowledge across all clients, leading to sub-optimal and inferior noise filtering performance and thus damaging training stability. In this paper, we present FedDiv to tackle the challenges of F-LNL. Specifically, we propose a global noise filter called Federated Noise Filter for effectively identifying samples with noisy labels on every client, thereby raising stability during local training sessions. Without sacrificing data privacy, this is achieved by modeling the global distribution of label noise across all clients. Then, in an effort to make the global model achieve higher performance, we introduce a Predictive Consistency based Sampler to identify more credible local data for local model training, thus preventing noise memorization and further boosting the training stability. Extensive experiments on CIFAR-10, CIFAR-100, and Clothing1M demonstrate that FedDiv achieves superior performance over state-of-the-art F-LNL methods under different label noise settings for both IID and non-IID data partitions. Source code is publicly available at https://github.com/lijichang/FLNL-FedDiv.

Nuclei classification is a critical step in computer-aided diagnosis with histopathology images. In the past, various methods have employed graph neural networks (GNN) to analyze cell graphs that model inter-cell relationships by considering nuclei as vertices. However, they are limited by the GNN mechanism that only passes messages among local nodes via fixed edges. To address the issue, we develop a cell graph transformer (CGT) that treats nodes and edges as input tokens to enable learnable adjacency and information exchange among all nodes. Nevertheless, training the transformer with a cell graph presents another challenge. Poorly initialized features can lead to noisy self-attention scores and inferior convergence, particularly when processing the cell graphs with numerous connections. Thus, we further propose a novel topology-aware pretraining method that leverages a graph convolutional network (GCN) to learn a feature extractor. The pre-trained features may suppress unreasonable correlations and hence ease the finetuning of CGT. Experimental results suggest that the proposed cell graph transformer with topology-aware pretraining significantly improves the nuclei classification results, and achieves the state-of-the-art performance. Code and models are available at https://github.com/lhaof/CGT

AI-assisted lesion detection models play a crucial role in the early screening of cancer. However, previous image-based models ignore the inter-frame contextual information present in videos. On the other hand, video-based models capture the inter-frame context but are computationally expensive. To mitigate this contradiction, we delve into Video-to-Image knowledge distillation leveraging DEtection TRansformer (V2I-DETR) for the task of medical video lesion detection. V2I-DETR adopts a teacher-student network paradigm. The teacher network aims at extracting temporal contexts from multiple frames and transferring them to the student network, and the student network is an image-based model dedicated to fast prediction in inference. By distilling multi-frame contexts into a single frame, the proposed V2I-DETR combines the advantages of utilizing temporal contexts from video-based models and the inference speed of image-based models. Through extensive experiments, V2I-DETR outperforms previous state-of-the-art methods by a large margin while achieving the real-time inference speed (30 FPS) as the image-based model.

Factor models, originating in finance for asset pricing, are fundamental tools in quantitative investment. Recently, there has been a trend towards adopting more flexible machine learning approaches instead of previous linear models. However, traditional factor models and recent deep learning approaches either overlook the relationships among stocks or rely on static, predefined ones, which hampers their representational power and hinders their ability to dynamically adapt to market changes. To overcome this limitation, we introduce a novel dynamic factor model named GraphVAE. This model leverages temporal adaptive dynamic stock relationship graphs, facilitating improved information transfer among stocks within the dynamic probabilistic factor model. Experimental results on three real stock market datasets demonstrate that our method outperforms various state-of-the-art approaches.

Given the long textual product information and the product image, Multi-modal Product Summarization (MPS) aims to increase customers’ desire to purchase by highlighting product characteristics with a short textual summary. Existing MPS methods can produce promising results. Nevertheless, they still 1) lack end-to-end product summarization, 2) lack multi-grained multi-modal modeling, and 3) lack multi-modal attribute modeling. To improve MPS, we propose an end-to-end multi-grained multi-modal attribute-aware product summarization method (MMAPS) for generating high-quality product summaries in e-commerce. MMAPS jointly models product attributes and generates product summaries. We design several multi-grained multi-modal tasks to better guide the multi-modal learning of MMAPS. Furthermore, we model product attributes based on both text and image modalities so that multi-modal product characteristics can be manifested in the generated summaries. Extensive experiments on a real large-scale Chinese e-commence dataset demonstrate that our model outperforms state-of-the-art product summarization methods w.r.t. several summarization metrics. Our code is publicly available at: https://github.com/KDEGroup/MMAPS.

Neural Radiance Field (NeRF) has been widely recognized for its excellence in novel view synthesis and 3D scene reconstruction. However, their effectiveness is in-herently tied to the assumption of static scenes, rendering them susceptible to undesirable artifacts when confronted with transient distractors such as moving objects or shad-ows. In this work, we propose a novel paradigm, namely “Heuristics-Guided Segmentation” (HuGS), which signifi-cantly enhances the separation of static scenes from tran-sient distractors by harmoniously combining the strengths of hand-crafted heuristics and state-of-the-art segmentation models, thus significantly transcending the limitations of previous solutions. Furthermore, we delve into the metic-ulous design of heuristics, introducing a seamless fusion of Structure-from-Motion (SfM)-based heuristics and color residual heuristics, catering to a diverse range of texture profiles. Extensive experiments demonstrate the superiority and robustness of our method in mitigating transient dis-tractors for NeRFs trained in non-static scenes. Project page: https://cnhaox.github.io/NeRF-HuGS/

In this paper, we target the adaptive source driven 3D scene editing task by proposing a CustomNeRF model that unifies a text description or a reference image as the editing prompt. However, obtaining desired editing results conformed with the editing prompt is nontrivial since there exist two significant challenges, including accurate editing of only foreground regions and multi-view consistency given a single-view reference image. To tackle the first challenge, we propose a Local-Global Iterative Editing (LGIE) training scheme that alternates between foreground region editing and full-image editing, aimed at foreground-only manipulation while preserving the background. For the second challenge, we also design a class-guided regularization that exploits class priors within the generation model to alleviate the inconsistency problem among different views in image-driven editing. Extensive experiments show that our CustomNeRF produces precise editing results under various real scenes for both text- and image-driven settings. The code is available at: https://github.com/hrz2000/CustomNeRF.

Powered by massive curated training data, Segment Any-thing Model (SAM) has demonstrated its impressive generalization capabilities in open-world scenarios with the guidance of prompts. However, the vanilla SAM is class-agnostic and heavily relies on user-provided prompts to segment objects of interest. Adapting this method to diverse tasks is crucial for accurate target identification and to avoid suboptimal segmentation results. In this paper, we propose a novel framework, termed AlignSAM, designed for automatic prompting for aligning SAM to an open context through reinforcement learning. Anchored by an agent, AlignSAM enables the generality of the SAM model across diverse downstream tasks while keeping its parameters frozen. Specifically, AlignSAM initiates a prompting agent to iteratively refine segmentation predictions by interacting with the foundational model. It integrates a reinforcement learning policy network to provide informative prompts to the foundational models. Additionally, a semantic recal-ibration module is introduced to provide fine-grained labels of prompts, enhancing the model's proficiency in handling tasks encompassing explicit and implicit semantics. Experiments conducted on various challenging segmentation tasks among existing foundation models demonstrate the superiority of the proposed AlignSAM over state-of-the-art approaches. Project page: https://github.com/Duojun-Huang/AIignSAM-CVPR2024.

Open vocabulary object detection (OVD) aims at seeking an optimal object detector capable of recognizing objects from both base and novel categories. Recent advances leverage knowledge distillation to transfer insightful knowledge from pre-trained large-scale vision-language models to the task of object detection, significantly generalizing the powerful capabilities of the detector to identify more unknown object categories. However, these methods face significant challenges in background interpretation and model overfitting and thus often result in the loss of crucial back-ground knowledge, giving rise to sub-optimal inference performance of the detector. To mitigate these issues, we present a novel OVD framework termed LBP to propose learning background prompts to harness explored implicit background knowledge, thus enhancing the detection performance w.r.t. base and novel categories. Specifically, we devise three modules: Background Category-specific Prompt, Background Object Discovery, and Inference Probability Rectification, to empower the detector to discover, represent, and leverage implicit object knowledge explored from background proposals. Evaluation on two benchmark datasets, OV-COCO and OV-LVIS, demonstrates the superiority of our proposed method over existing state-of-the-art approaches in handling the OVD tasks.

This paper studies open-vocabulary segmentation (OVS) through calibrating in-vocabulary and domain-biased embedding space with generalized contextual prior of CLIP. As the core of open-vocabulary understanding, alignment of visual content with the semantics of unbounded text has become the bottleneck of this field. To address this challenge, recent works propose to utilize CLIP as an additional classifier and aggregate model predictions with CLIP classification results. Despite their remarkable progress, performance of OVS methods in relevant scenarios is still unsatisfactory compared with supervised counterparts. We attribute this to the in-vocabulary embedding and domain-biased CLIP prediction. To this end, we present a Semantic-assisted CAlibration Network (SCAN). In SCAN, we incor-porate generalized semantic prior of CLIP into proposal embedding to avoid collapsing on known categories. Besides, a contextual shift strategy is applied to mitigate the lack of global context and unnatural background noise. With above designs, SCAN achieves state-of-the-art performance on all popular open-vocabulary segmentation benchmarks. Furthermore, we also focus on the problem of existing evaluation system that ignores semantic duplication across categories, and propose a new metric called Semantic-Guided IoU (SG-IoU). Code is available here.

We delve into pseudo-labeling for semi-supervised monocular 3D object detection (SSM30D) and discover two primary issues: a misalignment between the prediction quality of 3D and 2D attributes and the tendency of depth supervision derived from pseudo-labels to be noisy, leading to significant optimization conflicts with other re-liable forms of supervision. To tackle these issues, we introduce a novel decoupled pseudo-labeling (DPL) approach for SSM30D. Our approach features a Decoupled Pseudo-label Generation (DPG) module, designed to efficiently generate pseudo-labels by separately processing 2D and 3D attributes. This module incorporates a unique homography-based method for identifying dependable pseudo-labels in Bird's Eye View (BEV) space, specifically for 3D attributes. Additionally, we present a Depth Gradient Projection (DGP) module to mitigate optimization conflicts caused by noisy depth supervision of pseudo-labels, effectively decoupling the depth gradient and re-moving conflicting gradients. This dual decoupling strat-egy-at both the pseudo-label generation and gradient lev-els-significantly improves the utilization of pseudo-labels in SSM30D. Our comprehensive experiments on the KITTI benchmark demonstrate the superiority of our method over existing approaches.

Recent advances in Iterative Vision-and-Language Navigation (IVLN) introduce a more meaningful and practical paradigm of VLN by maintaining the agent's memory across tours of scenes. Although the long-term memory aligns better with the persistent nature of the VLN task, it poses more challenges on how to utilize the highly unstructured navigation memory with extremely sparse supervision. Towards this end, we propose OVER-NAV, which aims to go over and beyond the current arts of IVLN techniques. In particular, we propose to incorporate LLMs and open-vocabulary detectors to distill key information and establish correspondence between multi-modal signals. Such a mechanism introduces reliable cross-modal supervision and enables on-the-fly generalization to unseen scenes without the need of extra annotation and re-training. To fully exploit the interpreted navigation data, we further introduce a structured representation, coded Omnigraph, to effectively integrate multi-modal information along the tour. Accompanied with a novel omnigraph fusion mechanism, OVER-NAV is able to extract the most relevant knowledge from omnigraph for a more accurate navigating action. In addition, OVER-NAV seamlessly supports both discrete and continuous environments under a unified framework. We demonstrate the superiority of OVER-NAV in extensive experiments.

Semi-Supervised Object Detection (SSOD) has achieved resounding success by leveraging unlabeled data to improve detection performance. However, in Open Scene Semi-Supervised Object Detection (O-SSOD), unlabeled data may contains unknown objects not observed in the labeled data, which will increase uncertainty in the model’s predictions for known objects. It is detrimental to the current methods that mainly rely on self-training, as more uncertainty leads to the lower localization and classification precision of pseudo labels. To this end, we propose Credible Teacher, an end-to-end framework. Credible Teacher adopts an interactive teaching mechanism using flexible labels to prevent uncertain pseudo labels from misleading the model and gradually reduces its uncertainty through the guidance of other credible pseudo labels. Empirical results have demonstrated our method effectively restrains the adverse effect caused by O-SSOD and significantly outperforms existing counterparts.

Creating stable, controllable videos is a complex task due to the need for significant variation in temporal dynamics and cross-frame temporal consistency. To address this, we enhance the spatial-temporal capability and introduce a versatile video generation model, VersVideo, which leverages textual, visual, and stylistic conditions. Current video diffusion models typically extend image diffusion architectures by supplementing 2D operations (such as convolutions and attentions) with temporal operations. While this approach is efficient, it often restricts spatial-temporal performance due to the oversimplification of standard 3D operations. To counter this, we incorporate two key elements: (1) multi-excitation paths for spatial-temporal convolutions with dimension pooling across different axes, and (2) multi-expert spatial-temporal attention blocks. These enhancements boost the model's spatial-temporal performance without significantly escalating training and inference costs. We also tackle the issue of information loss that arises when a variational autoencoder is used to transform pixel space into latent features and then back into pixel frames. To mitigate this, we incorporate temporal modules into the decoder to maintain inter-frame consistency. Lastly, by utilizing the innovative denoising UNet and decoder, we develop a unified ControlNet model suitable for various conditions, including image, Canny, HED, depth, and style. Examples of the videos generated by our model can be found at https://jinxixiang.github.io/versvideo/.

Automatic segmentation of the bronchial tree from CT imaging is important, as it provides structural information for disease diagnosis. Despite the merits of previous automatic bronchus segmentation methods, they have paied less attention to the issue we term as Intensity Confusion, wherein the intensity values of certain background voxels approach those of the foreground voxels within bronchi. Conversely, the intensity values of some foreground voxels are nearly identical to those of background voxels. This proximity in intensity values introduces significant challenges to neural network methodologies. To address the issue, we introduce a novel Intensity-Distance Guided loss function, which assigns adaptive weights to different image voxels for mining hard samples that cause the intensity confusion. The proposed loss estimates the voxel-level hardness of samples, on the basis of the following intensity and distance priors. We regard a voxel as a hard sample if it is in: (1) the background and has an intensity value close to the bronchus region; (2) the bronchus region and is of higher intensity than most voxels inside the bronchus; (3) the background region and at a short distance from the bronchus. Extensive experiments not only show the superiority of our method compared with the state-of-the-art methods, but also verify that tackling the intensity confusion issue helps to significantly improve bronchus segmentation. Project page: https://github.com/lhaof/ICM.

Whole-slide image (WSI) classification methods play a crucial role in tumor diagnosis. Most of them use hematoxylin and eosin (H&E) stained images, while Immunohistochemistry (IHC) staining provides molecular markers and protein expression information that highlights cancer regions. However, obtaining IHC-stained images requires higher costs in practice. In this work, we propose a multi-modal denoising diffusion pre-training framework that harnesses the advantages of IHC staining to learn visual representations. The framework is trained with the H&E-to-IHC re-staining task and IHC-stained image reconstruction task, which helps capture the structural similarity and staining difference between two image modalities. The trained model can then provide IHC-guided features, by taking only H&E-stained images as inputs. Besides, we build a new class-constraint constrastive loss to achieve the semantic consistency between dual-modal features from our pre-training framework. To integrate with WSI classifiers based on multi-instance learning, we further propose a bag feature augmentation strategy to extend bags with the features extracted by our pre-trained model. Experimental results on three datasets show that our pre-training framework effectively improves WSI classification and surpasses the state-of-the-art pre-training approaches. Code and model are released via https://github.com/lhaof/MDDP

Recently, there has been significant progress in leveraging human feedback to enhance diffusion-based image generation, garnering considerable interest and attention. However, existing methods fail to achieve a fine-grained performance boost for the following challenges: i) insufficient amount of fine-grained feedback data; ii) lack of effective fine-grained feedback learning framework; To tackle these challenges, we present TreeReward to facilitate the fine-grained feedback optimization for diffusion models. Specifically, to address the limitation of the fine-grained feedback data, we first design a novel "AI + Expert" feedback data construction pipeline, yielding about 2.2M high-quality feedback dataset encompassing six fine-grained dimensions at a relatively low cost. Built upon this dataset, we introduce a tree-structure reward model to exploit the fine-grained feedback data efficiently and provide tailored optimization during feedback learning. We validate the feedback learning performance of our method across different fine-grained dimensions and various downstream tasks. Extensive experiments on both Stable Diffusion v1.5 (SD1.5) and Stable Diffusion XL (SDXL) demonstrate the effectiveness of our method in enhancing the general and fine-grained generation and downstream tasks generalization.

Recently, large language models (LLMs) have achieved superior performance, empowering the development of large multimodal agents (LMAs). An LMA is anticipated to execute practical tasks requires various capabilities including multimodal perception, interaction, reasoning, and decision making. However, existing benchmarks are limited in assessing compositional skills and actions demanded by practical scenarios, where they primarily focused on single tasks and static scenarios. To bridge this gap, we introduce WhodunitBench, a benchmark rooted from murder mystery games, where players are required to utilize the aforementioned skills to achieve their objective (i.e., identifying the `murderer' or hiding themselves), providing a simulated dynamic environment for evaluating LMAs. Specifically, WhodunitBench includes two evaluation modes. The first mode, the arena-style evaluation, is constructed from 50 meticulously curated scripts featuring clear reasoning clues and distinct murderers; The second mode, the chain of evaluation, consists of over 3000 curated multiple-choice questions and open-ended questions, aiming to assess every facet of the murder mystery games for LMAs. Experiments show that although current LMAs show acceptable performance in basic perceptual tasks, they are insufficiently equipped for complex multi-agent collaboration and multi-step reasoning tasks. Furthermore, the full application of the theory of mind to complete games in a manner akin to human behavior remains a significant challenge. We hope this work can illuminate the path forward, providing a solid foundation for the future development of LMAs. Our WhodunitBench is open-source and accessible at: https://github.com/jun0wanan/WhodunitBench-MurderMysteryGames

Latent diffusion models (LDM) have revolutionized text-to-image generation, leading to the proliferation of various advanced models and diverse downstream applications. However, despite these significant advancements, current diffusion models still suffer from several limitations, including inferior visual quality, inadequate aesthetic appeal, and inefficient inference, without a comprehensive solution in sight. To address these challenges, we present **UniFL**, a unified framework that leverages feedback learning to enhance diffusion models comprehensively. UniFL stands out as a universal, effective, and generalizable solution applicable to various diffusion models, such as SD1.5 and SDXL. Notably, UniFL consists of three key components: perceptual feedback learning, which enhances visual quality; decoupled feedback learning, which improves aesthetic appeal; and adversarial feedback learning, which accelerates inference. In-depth experiments and extensive user studies validate the superior performance of our method in enhancing generation quality and inference acceleration. For instance, UniFL surpasses ImageReward by 17\% user preference in terms of generation quality and outperforms LCM and SDXL Turbo by 57\% and 20\% general preference with 4-step inference.

In this paper, we introduce a realistic and challenging domain adaptation problem called Universal Semi-supervised Model Adaptation (USMA), which i) requires only a pre-trained source model, ii) allows the source and target domain to have different label sets, i.e., they share a common label set and hold their own private label set, and iii) requires only a few labeled samples in each class of the target domain. To address USMA, we propose a collaborative consistency training framework that regularizes the prediction consistency between two models, i.e., a pre-trained source model and its variant pre-trained with target data only, and combines their complementary strengths to learn a more powerful model. The rationale of our framework stems from the observation that the source model performs better on common categories than the target-only model, while on target-private categories, the target-only model performs better. We also propose a two-perspective, i.e., sample-wise and class-wise, consistency regularization to improve the training. Experimental results demonstrate the effectiveness of our method on several benchmark datasets.

Due to the advancement of deep learning, the performance of salient object detection (SOD) has been significantly improved. However, deep learning-based techniques require a sizable amount of pixel-wise annotations. To relieve the burden of data annotation, a variety of deep weakly-supervised and unsupervised SOD methods have been proposed, yet the performance gap between them and fully supervised methods remains significant. In this paper, we propose a novel, cost-efficient salient object detection framework, which can adapt models from synthetic data to real-world data with the help of a limited number of actively selected annotations. Specifically, we first construct a synthetic SOD dataset by copying and pasting foreground objects into pure background images. With the masks of foreground objects taken as the ground-truth saliency maps, this dataset can be used for training the SOD model initially. However, due to the large domain gap between synthetic images and real-world images, the performance of the initially trained model on the real-world images is deficient. To transfer the model from the synthetic dataset to the real-world datasets, we further design an uncertainty-aware active domain adaptive algorithm to generate labels for the real-world target images. The prediction variances against data augmentations are utilized to calculate the superpixel-level uncertainty values. For those superpixels with relatively low uncertainty, we directly generate pseudo labels according to the network predictions. Meanwhile, we select a few superpixels with high uncertainty scores and assign labels to them manually. This labeling strategy is capable of generating high-quality labels without incurring too much annotation cost. Experimental results on six benchmark SOD datasets demonstrate that our method outperforms the existing state-of-the-art weakly-supervised and unsupervised SOD methods and is even comparable to the fully supervised ones. Code will be released at: https://github.com/czh-3/UADA.

Self-supervised depth estimation methods can achieve competitive performance using only unlabeled monocular videos, but they suffer from the uncertainty of jointly learning depth and pose without any ground truths of both tasks. Supervised framework provides robust and superior performance but is limited by the scope of the labeled data. In this paper, we introduce SENSE, a novel learning paradigm for self-supervised monocular depth estimation that progressively evolves the prediction result using supervised learning, but without requiring labeled data. The key contribution of our approach stems from the novel use of the pseudo labels - the noisy depth estimation from the self-supervised methods. We surprisingly find that a fully supervised depth estimation network trained using the pseudo labels can produce even better results than its "ground truth". To push the envelope further, we then evolve the self-supervised backbone by replacing its depth estimation branch with that fully supervised network. Based on this idea, we devise a comprehensive training pipeline that alternatively enhances the two key branches (depth and pose estimation) of the self-supervised backbone network. Our proposed approach can effectively ease the difficulty of multi-task training in self-supervised depth estimation. Experimental results have shown that our proposed approach achieves state-of-the-art results on the KITTI dataset.

In this paper, we address a complex but practical scenario in Active Learning (AL) known as open-set AL, where the unlabeled data consists of both in-distribution (ID) and out-of-distribution (OOD) samples. Standard AL methods will fail in this scenario as OOD samples are highly likely to be regarded as uncertain samples, leading to their selection and wasting of the budget. Existing methods focus on selecting the highly likely ID samples, which tend to be easy and less informative. To this end, we introduce two criteria, namely contrastive confidence and historical divergence, which measure the possibility of being ID and the hardness of a sample, respectively. By balancing the two proposed criteria, highly informative ID samples can be selected as much as possible. Furthermore, unlike previous methods that require additional neural networks to detect the OOD samples, we propose a contrastive clustering framework that endows the classifier with the ability to identify the OOD samples and further enhances the network's representation learning. The experimental results demonstrate that the proposed method achieves state-of-the-art performance on several benchmark datasets.

Accurate polyp detection is critical for early colorectal cancer diagnosis. Although remarkable progress has been achieved in recent years, the complex colon environment and concealed polyps with unclear boundaries still pose severe challenges in this area. Existing methods either involve computationally expensive context aggregation or lack prior modeling of polyps, resulting in poor performance in challenging cases. In this paper, we propose the Enhanced CenterNet with Contrastive Learning (ECC-PolypDet), a two-stage training & end-to-end inference framework that leverages images and bounding box annotations to train a general model and fine-tune it based on the inference score to obtain a final robust model. Specifically, we conduct Box-assisted Contrastive Learning (BCL) during training to minimize the intra-class difference and maximize the inter-class difference between foreground polyps and backgrounds, enabling our model to capture concealed polyps. Moreover, to enhance the recognition of small polyps, we design the Semantic Flow-guided Feature Pyramid Network (SFFPN) to aggregate multi-scale features and the Heatmap Propagation (HP) module to boost the model's attention on polyp targets. In the fine-tuning stage, we introduce the IoU-guided Sample Re-weighting (ISR) mechanism to prioritize hard samples by adaptively adjusting the loss weight for each sample during fine-tuning. Extensive experiments on six large-scale colonoscopy datasets demonstrate the superiority of our model compared with previous state-of-the-art detectors.

Nuclei classification provides valuable information for histopathology image analysis. However, the large variations in the appearance of different nuclei types cause difficulties in identifying nuclei. Most neural network based methods are affected by the local receptive field of convolutions, and pay less attention to the spatial distribution of nuclei or the irregular contour shape of a nucleus. In this paper, we first propose a novel polygon-structure feature learning mechanism that transforms a nucleus contour into a sequence of points sampled in order, and employ a recurrent neural network that aggregates the sequential change in distance between key points to obtain learnable shape features. Next, we convert a histopathology image into a graph structure with nuclei as nodes, and build a graph neural network to embed the spatial distribution of nuclei into their representations. To capture the correlations between the categories of nuclei and their surrounding tissue patterns, we further introduce edge features that are defined as the background textures between adjacent nuclei. Lastly, we integrate both polygon and graph structure learning mechanisms into a whole framework that can extract intra and inter-nucleus structural characteristics for nuclei classification. Experimental results show that the proposed framework achieves significant improvements compared to the previous methods. Code and data are made available via https://github.com/lhaof/SENC.

Most existing methods that cope with noisy labels usually assume that the classwise data distributions are well balanced. They are difficult to deal with the practical scenarios where training samples have imbalanced distributions, since they are not able to differentiate noisy samples from tail classes' clean samples. This article makes an early effort to tackle the image classification task in which the provided labels are noisy and have a long-tailed distribution. To deal with this problem, we propose a new learning paradigm which can screen out noisy samples by matching between inferences on weak and strong data augmentations. A leave-noise-out regularization (LNOR) is further introduced to eliminate the effect of the recognized noisy samples. Besides, we propose a prediction penalty based on the online classwise confidence levels to avoid the bias toward easy classes which are dominated by head classes. Extensive experiments on five datasets including CIFAR-10, CIFAR-100, MNIST, FashionMNIST, and Clothing1M demonstrate that the proposed method outperforms the existing algorithms for learning with long-tailed distribution and label noise.

Text-driven 3D scene editing has gained significant attention owing to its convenience and user-friendliness. However, existing methods still lack accurate control of the specified appearance and location of the editing result due to the inherent limitations of the text description. To this end, we propose a 3D scene editing framework, TIP-Editor, that accepts both text and image prompts and a 3D bounding box to specify the editing region. With the image prompt, users can conveniently specify the detailed appearance/style of the target content in complement to the text description, enabling accurate control of the appearance. Specifically, TIP-Editor employs a stepwise 2D personalization strategy to better learn the representation of the existing scene and the reference image, in which a localization loss is proposed to encourage correct object placement as specified by the bounding box. Additionally, TIP-Editor utilizes explicit and flexible 3D Gaussian splatting (GS) as the 3D representation to facilitate local editing while keeping the background unchanged. Extensive experiments have demonstrated that TIP-Editor conducts accurate editing following the text and image prompts in the specified bounding box region, consistently outperforming the baselines in editing quality, and the alignment to the prompts, qualitatively and quantitatively.

Semi-supervised object detection (SSOD) attracts extensive research interest due to its great significance in reducing the data annotation effort. Collecting high-quality and category-balanced pseudo labels for unlabeled images is critical to addressing the SSOD problem. However, most of the existing pseudo-labeling-based methods depend on a large and fixed threshold to select high-quality pseudo labels from the predictions of a teacher model. Considering different object classes usually have different detection difficulty levels due to scale variance and data distribution imbalance, conventional pseudo-labeling-based methods are arduous to explore the value of unlabeled data sufficiently. To address these issues, we propose an adaptive pseudo labeling strategy, which can assign thresholds to classes with respect to their “hardness”. This is beneficial for ensuring the high quality of easier classes and increasing the quantity of harder classes simultaneously. Besides, label refinement modules are set up based on box jittering for guaranteeing the localization quality of pseudo labels. To further improve the algorithm’s robustness against scale variance and make the most of pseudo labels, we devise a joint feature-level and prediction-level consistency learning pipeline for transferring the information of the teacher model to the student model. Extensive experiments on COCO and VOC datasets indicate that our method achieves state-of-the-art performance. Especially, it brings mean average precision gains of 2.08 and 1.28 on MS-COCO dataset with 5% and 10% labeled images, respectively.

Most of the recent research in semi-supervised object detection follows the pseudo-labeling paradigm evolved from the semi-supervised image classification task. However, the training paradigm of the two-stage object detector inevitably makes the pseudo-label learning process for unlabeled images full of bias. Specifically, the IoU matching scheme used for selecting and labeling candidate boxes is based on the assumption that the matching source~(ground truth) is accurate enough in terms of the number of objects, object position and object category. Obviously, pseudo-labels generated for unlabeled images cannot satisfy such a strong assumption, which makes the produced training proposals extremely unreliable and thus severely spoil the follow-up training. To de-bias the training proposals generated by the pseudo-label-based IoU matching, we propose a general framework -- De-biased Teacher, which abandons both the IoU matching and pseudo labeling processes by directly generating favorable training proposals for consistency regularization between the weak/strong augmented image pairs. Moreover, a distribution-based refinement scheme is designed to eliminate the scattered class predictions of significantly low values for higher efficiency. Extensive experiments demonstrate that the proposed De-biased Teacher consistently outperforms other state-of-the-art methods on the MS-COCO and PASCAL VOC benchmarks. Source codes are available at https://github.com/wkfdb/De-biased-Teracher.

Visual grounding (VG) aims to establish fine-grained alignment between vision and language. Ideally, it can be a testbed for vision-and-language models to evaluate their understanding of the images and texts and their reasoning abilities over their joint space. However, most existing VG datasets are constructed using simple description texts, which do not require sufficient reasoning over the images and texts. This has been demonstrated in a recent study [27], where a simple LSTM-based text encoder without pretraining can achieve state-of-the-art performance on mainstream VG datasets. Therefore, in this paper, we propose a novel benchmark of Scene Knowledge-guided Visual Grounding (SK-VG), where the image content and referring expressions are not sufficient to ground the target objects, forcing the models to have a reasoning ability on the long-form scene knowledge. To perform this task, we propose two approaches to accept the triple-type input, where the former embeds knowledge into the image features before the image-query interaction; the latter leverages linguistic structure to assist in computing the image-text matching. We conduct extensive experiments to analyze the above methods and show that the proposed approaches achieve promising results but still leave room for improvement, including performance and interpretability. The dataset and code are available at https://github.com/zhjohnchan/SK-VG.

Active domain adaptation (ADA) aims to improve the model adaptation performance by incorporating active learning (AL) techniques to label a maximally-informative subset of target samples. Conventional AL methods do not consider the existence of domain shift, and hence, fail to identify the truly valuable samples in the context of domain adaptation. To accommodate active learning and domain adaption, the two naturally different tasks, in a collaborative framework, we advocate that a customized learning strategy for the target data is the key to the success of ADA solutions. We present Divide-and-Adapt (DiaNA), a new ADA framework that partitions the target instances into four categories with stratified transferable properties. With a novel data subdivision protocol based on uncertainty and domainness, DiaNA can accurately recognize the most gainful samples. While sending the informative instances for annotation, DiaNA employs tailored learning strategies for the remaining categories. Furthermore, we propose an informativeness score that unifies the data partitioning criteria. This enables the use of a Gaussian mixture model (GMM) to automatically sample unlabeled data into the proposed four categories. Thanks to the “divide-and-adapt” spirit, DiaNA can handle data with large variations of domain gap. In addition, we show that DiaNA can generalize to different domain adaptation settings, such as unsupervised domain adaptation (UDA), semi-supervised domain adaptation (SSDA), source-free domain adaptation (SFDA), etc.

Audio-driven facial reenactment is a crucial technique that has a range of applications in film-making, virtual avatars and video conferences. Existing works either employ explicit intermediate face representations (e.g., 2D facial landmarks or 3D face models) or implicit ones (e.g., Neural Radiance Fields), thus suffering from the trade-offs between interpretability and expressive power, hence between controllability and quality of the results. In this work, we break these trade-offs with our novel parametric implicit face representation and propose a novel audio-driven facial reenactment framework that is both controllable and can generate high-quality talking heads. Specifically, our parametric implicit representation parameterizes the implicit representation with interpretable parameters of 3D face models, thereby taking the best of both explicit and implicit methods. In addition, we propose several new techniques to improve the three components of our framework, including i) incorporating contextual information into the audio-to-expression parameters encoding; ii) using conditional image synthesis to parameterize the implicit representation and implementing it with an innovative tri-plane structure for efficient learning; iii) formulating facial reenactment as a conditional image inpainting problem and proposing a novel data augmentation technique to improve model generalizability. Extensive experiments demonstrate that our method can generate more realistic results than previous methods with greater fidelity to the identities and talking styles of speakers.

Text-to-motion generation is an emerging and challenging problem, which aims to synthesize motion with the same semantics as the input text. However, due to the lack of diverse labeled training data, most approaches either limit to specific types of text annotations or require online optimizations to cater to the texts during inference at the cost of efficiency and stability. In this paper, we investigate offline open-vocabulary text-to-motion generation in a zero-shot learning manner that neither requires paired training data nor extra online optimization to adapt for unseen texts. Inspired by the prompt learning in NLP, we pretrain a motion generator that learns to reconstruct the full motion from the masked motion. During inference, instead of changing the motion generator, our method reformulates the input text into a masked motion as the prompt for the motion generator to “reconstruct” the motion. In constructing the prompt, the unmasked poses of the prompt are synthesized by a text-to-pose generator. To supervise the optimization of the text-to-pose generator, we propose the first text-pose alignment model for measuring the alignment between texts and 3D poses. And to prevent the pose generator from over-fitting to limited training texts, we further propose a novel wordless training mechanism that optimizes the text-to-pose generator without any training texts. The comprehensive experimental results show that our method obtains a significant improvement against the baseline methods. The code is available at https://github.com/junfanlin/oohmg.

3D shape completion from point clouds is a challenging task, especially from scans of real-world objects. Considering the paucity of 3D shape ground truths for real scans, existing works mainly focus on benchmarking this task on synthetic data, e.g. 3D computer-aided design models. However, the domain gap between synthetic and real data limits the generalizability of these methods. Thus, we propose a new task, SCoDA, for the domain adaptation of real scan shape completion from synthetic data. A new dataset, ScanSalon, is contributed with a bunch of elaborate 3D models created by skillful artists according to scans. To address this new task, we propose a novel cross-domain feature fusion method for knowledge transfer and a novel volume-consistent self-training framework for robust learning from real data. Extensive experiments prove our method is effective to bring an improvement of 6%~7% mIoU.

We analyze the DETR-based framework on semi-supervised object detection (SSOD) and observe that (1) the one-to-one assignment strategy generates incorrect matching when the pseudo ground-truth bounding box is inaccurate, leading to training inefficiency; (2) DETR-based detectors lack deterministic correspondence between the input query and its prediction output, which hinders the applicability of the consistency-based regularization widely used in current SSOD methods. We present Semi-DETR, the first transformer-based end-to-end semi-supervised object detector, to tackle these problems. Specifically, we propose a Stage-wise Hybrid Matching strategy that combines the one-to-many assignment and one-to-one assignment strategies to improve the training efficiency of the first stage and thus provide high-quality pseudo labels for the training of the second stage. Besides, we introduce a Cross-view Query Consistency method to learn the semantic feature invariance of object queries from different views while avoiding the need to find deterministic query correspondence. Furthermore, we propose a Cost-based Pseudo Label Mining module to dynamically mine more pseudo boxes based on the matching cost of pseudo ground truth bounding boxes for consistency training. Extensive experiments on all SSOD settings of both COCO and Pascal VOC benchmark datasets show that our Semi-DETR method outperforms all state-of-the-art methods by clear margins.

Dataset Condensation aims to condense a large dataset into a smaller one while maintaining its ability to train a well-performing model, thus reducing the storage cost and training effort in deep learning applications. However, conventional dataset condensation methods are optimization-oriented and condense the dataset by performing gradient or parameter matching during model optimization, which is computationally intensive even on small datasets and models. In this paper, we propose a novel dataset condensation method based on distribution matching, which is more efficient and promising. Specifically, we identify two important shortcomings of naive distribution matching (i.e., imbalanced feature numbers and unvalidated embeddings for distance computation) and address them with three novel techniques (i.e., partitioning and expansion augmentation, efficient and enriched model sampling, and class-aware distribution regularization). Our simple yet effective method outperforms most previous optimization-oriented methods with much fewer computational resources, thereby scaling data condensation to larger datasets and models. Extensive experiments demonstrate the effectiveness of our method. Codes are available at https://github.com/uitrbn/IDM

Generating talking face videos from audio attracts lots of research interest. A few person-specific methods can generate vivid videos but require the target speaker's videos for training or fine-tuning. Existing person-generic methods have difficulty in generating realistic and lip-synced videos while preserving identity information. To tackle this problem, we propose a two-stage framework consisting of audio-to-landmark generation and landmark-to-video rendering procedures. First, we devise a novel Transformer-based landmark generator to infer lip and jaw landmarks from the audio. Prior landmark characteristics of the speaker's face are employed to make the generated landmarks coincide with the facial outline of the speaker. Then, a video rendering model is built to translate the generated landmarks into face images. During this stage, prior appearance information is extracted from the lower-half occluded target face and static reference images, which helps generate realistic and identity-preserving visual content. For effectively exploring the prior information of static reference images, we align static reference images with the target face's pose and expression based on motion fields. Moreover, auditory features are reused to guarantee that the generated face images are well synchronized with the audio. Extensive experiments demonstrate that our method can produce more realistic, lip-synced, and identity-preserving videos than existing person-generic talking face generation methods.

Medical vision-and-language pre-training (Med-VLP) has shown promising improvements on many downstream medical tasks owing to its applicability to extracting generic representations from medical images and texts. Practically, there exist two typical types, i.e., the fusion-encoder type and the dual-encoder type, depending on whether a heavy fusion module is used. The former is superior at multi-modal tasks owing to the sufficient interaction between modalities; the latter is good at uni-modal and cross-modal tasks due to the single-modality encoding ability. To take advantage of these two types, we propose an effective yet straightforward scheme named PTUnifier to unify the two types. We first unify the input format by introducing visual and textual prompts, which serve as DETR-like queries that assist in extracting features when one of the modalities is missing. By doing so, a single model could serve as a foundation model that processes various tasks adopting different input formats (i.e., image-only, text-only, and image-text-pair). Furthermore, we construct a prompt pool (instead of static ones) to improve diversity and scalability, enabling queries conditioned on different input instances. Experimental results show that our approach achieves competitive results on a broad range of tasks, spanning uni-modal tasks (i.e., image/text classification and text summarization), cross-modal tasks (i.e., image-to-text generation and image-text/text-image retrieval), and multi-modal tasks (i.e., visual question answering), demonstrating the effectiveness of our approach. Note that the adoption of prompts is orthogonal to most existing Med-VLP approaches and could be a beneficial and complementary extension to these approaches.1

Multi-class cell nuclei detection is a fundamental prerequisite in the diagnosis of histopathology. It is critical to efficiently locate and identify cells with diverse morphology and distributions in digital pathological images. Most existing methods take complex intermediate representations as learning targets and rely on inflexible post-refinements while paying less attention to various cell density and fields of view. In this paper, we propose a novel Affine-Consistent Transformer (AC-Former), which directly yields a sequence of nucleus positions and is trained collaboratively through two sub-networks, a global and a local network. The local branch learns to infer distorted input images of smaller scales while the global network outputs the large-scale predictions as extra supervision signals. We further introduce an Adaptive Affine Transformer (AAT) module, which can automatically learn the key spatial transformations to warp original images for local network training. The AAT module works by learning to capture the transformed image regions that are more valuable for training the model. Experimental results demonstrate that the proposed method significantly outperforms existing state-of-the-art algorithms on various benchmarks.

Current semi-supervised object detection (SSOD) algorithms typically assume class balanced datasets (PASCAL VOC etc.) or slightly class imbalanced datasets (MS-COCO, etc). This assumption can be easily violated since real world datasets can be extremely class imbalanced in nature, thus making the performance of semi-supervised object detectors far from satisfactory. Besides, the research for this problem in SSOD is severely under-explored. To bridge this research gap, we comprehensively study the class imbalance problem for SSOD under more challenging scenarios, thus forming the first experimental setting for class imbalanced SSOD (CI-SSOD). Moreover, we propose a simple yet effective gradient-based sampling framework that tackles the class imbalance problem from the perspective of two types of confirmation biases. To tackle confirmation bias towards majority classes, the gradient-based reweighting and gradient-based thresholding modules leverage the gradients from each class to fully balance the influence of the majority and minority classes. To tackle the confirmation bias from incorrect pseudo labels of minority classes, the class-rebalancing sampling module resamples unlabeled data following the guidance of the gradient-based reweighting module. Experiments on three proposed sub-tasks, namely MS-COCO, MS-COCO → Object365 and LVIS, suggest that our method outperforms current class imbalanced object detectors by clear margins, serving as a baseline for future research in CI-SSOD. Code will be available at https://github.com/nightkeepers/CI-SSOD.

As a mainstream framework in the field of semi-supervised learning (SSL), self-training via pseudo labeling and its variants have witnessed impressive progress in semi-supervised semantic segmentation with the recent advance of deep neural networks. However, modern self-training based SSL algorithms use a pre-defined constant threshold to select unlabeled pixel samples that contribute to the training, thus failing to be compatible with different learning difficulties of variant categories and different learning status of the model. To address these issues, we propose Enhanced Soft Label (ESL), a curriculum learning approach to fully leverage the high-value supervisory signals implicit in the untrustworthy pseudo label. ESL believes that pixels with unconfident predictions can be pretty sure about their belonging to a subset of dominant classes though being arduous to determine the exact one. It thus contains a Dynamic Soft Label (DSL) module to dynamically maintain the high probability classes, keeping the label "soft" so as to make full use of the high entropy prediction. However, the DSL itself will inevitably introduce ambiguity between dominant classes, thus blurring the classification boundary. Therefore, we further propose a pixel-to-part contrastive learning method cooperated with an unsupervised object part grouping mechanism to improve its ability to distinguish between different classes. Extensive experimental results on Pascal VOC 2012 and Cityscapes show that our approach achieves remarkable improvements over existing state-of-the-art approaches.

Despite substantial advances, single-image super-resolution (SISR) is always in a dilemma to reconstruct high-quality images with limited information from one input image, especially in realistic scenarios. In this paper, we establish a large-scale real-world burst super-resolution dataset, i.e., RealBSR, to explore the faithful reconstruction of image details from multiple frames. Furthermore, we introduce a Federated Burst Affinity network (FBAnet) to investigate non-trivial pixel-wise displacements among images under real-world image degradation. Specifically, rather than using pixel-wise alignment, our FBAnet employs a simple homography alignment from a structural geometry aspect and a Federated Affinity Fusion (FAF) strategy to aggregate the complementary information among frames. Those fused informative representations are fed to a Transformer-based module of burst representation decoding. Besides, we have conducted extensive experiments on two versions of our datasets, i.e., RealBSR-RAW and RealBSR-RGB. Experimental results demonstrate that our FBAnet outperforms existing state-of-the-art burst SR methods and also achieves visually-pleasant SR image predictions with model details. Our dataset, codes, and models are publicly available at https://github.com/yjsunnn/FBANet.

Parameter Efficient Tuning (PET) has gained attention for reducing the number of parameters while maintaining performance and providing better hardware resource savings, but few studies investigate dense prediction tasks and interaction between modalities. In this paper, we do an investigation of efficient tuning problems on referring image segmentation. We propose a novel adapter called Bridger to facilitate cross-modal information exchange and inject task-specific information into the pre-trained model. We also design a lightweight decoder for image segmentation. Our approach achieves comparable or superior performance with only 1.61% to 3.38% backbone parameter updates, evaluated on challenging benchmarks. The code is available at https://github.com/kkakkkka/ETRIS.

Skeleton sequence representation learning has shown great advantages for action recognition due to its promising ability to model human joints and topology. However, the current methods usually require sufficient labeled data for training computationally expensive models. Moreover, these methods ignore how to utilize the fine-grained dependencies among different skeleton joints to pre-train an efficient skeleton sequence learning model that can generalize well across different datasets. In this paper, we propose an efficient skeleton sequence learning framework, named Skeleton Sequence Learning (SSL). To comprehensively capture the human pose and obtain discriminative skeleton sequence representation, we build an asymmetric graph-based encoder-decoder pre-training architecture named SkeletonMAE, which embeds skeleton joint sequence into graph convolutional network and reconstructs the masked skeleton joints and edges based on the prior human topology knowledge. Then, the pre-trained SkeletonMAE encoder is integrated with the Spatial-Temporal Representation Learning (STRL) module to build the SSL framework. Extensive experimental results show that our SSL generalizes well across different datasets and outperforms the state-of-the-art self-supervised skeleton-based methods on FineGym, Diving48, NTU 60 and NTU 120 datasets. Moreover, we obtain comparable performance to some fully supervised methods. The code is avaliable at https://github.com/HongYan1123/SkeletonMAE.

Learning with noisy labels (LNL) is one of the most important and challenging problems in weakly-supervised learning. Recent advances adopt the sample selection strategy to mitigate the interference of noisy labels and use small-loss criteria to select clean samples. However, the one-dimensional loss is an over-simplified metric that fails to accommodate the complex feature landscape of various samples, and, hence, is prone to introduce classification errors during sample selection. In this paper, we propose RankMatch, a novel LNL framework that investigates additional dimensions of confidence and consistency in order to combat noisy labels. Confidence-wise, we propose a novel sample selection strategy based on confidence representation voting instead of the widely-used small-loss criterion. This new strategy is capable of increasing sample selection quantity without sacrificing labeling accuracy. Consistency-wise, instead of the widely adopted feature distance metric for measuring the consistency of inner-class samples, we advocate that the rank of principal features is a much more robust indicator. Based on this metric, we propose rank contrastive loss, which strengthens the consistency of similar samples regardless of their labels and facilitates feature representation learning. Experimental results on noisy versions of CIFAR-10, CIFAR-100, Clothing1M and WebVision have validated the superiority of our approach over existing state-of-the-art methods.

Traffic Signal Control (TSC) aims to reduce the average travel time of vehicles in a road network, which in turn enhances fuel utilization efficiency, air quality, and road safety, benefiting society as a whole. Due to the complexity of long-horizon control and coordination, most prior TSC methods leverage deep reinforcement learning (RL) to search for a control policy and have witnessed great success. However, TSC still faces two significant challenges. 1) The travel time of a vehicle is delayed feedback on the effectiveness of TSC policy at each traffic intersection since it is obtained after the vehicle has left the road network. Although several heuristic reward functions have been proposed as substitutes for travel time, they are usually biased and not leading the policy to improve in the correct direction. 2) The traffic condition of each intersection is influenced by the non-local intersections since vehicles traverse multiple intersections over time. Therefore, the TSC agent is required to leverage both the local observation and the non-local traffic conditions to predict the long-horizontal traffic conditions of each intersection comprehensively. To address these challenges, we propose DenseLight, a novel RL-based TSC method that employs an unbiased reward function to provide dense feedback on policy effectiveness and a non-local enhanced TSC agent to better predict future traffic conditions for more precise traffic control. Extensive experiments and ablation studies demonstrate that DenseLight can consistently outperform advanced baselines on various road networks with diverse traffic flows. The code is available at https://github.com/junfanlin/DenseLight.

Wind power is attracting increasing attention around the world due to its renewable, pollution-free, and other advantages. However, safely and stably integrating the high permeability intermittent power energy into electric power systems remains challenging. Accurate wind power forecasting (WPF) can effectively reduce power fluctuations in power system operations. Existing methods are mainly designed for short-term predictions and lack effective spatial-temporal feature augmentation. In this work, we propose a novel end-to-end wind power forecasting model named Hierarchical Spatial-Temporal Transformer Network (HSTTN) to address the long-term WPF problems. Specifically, we construct an hourglass-shaped encoder-decoder framework with skip-connections to jointly model representations aggregated in hierarchical temporal scales, which benefits long-term forecasting. Based on this framework, we capture the inter-scale long-range temporal dependencies and global spatial correlations with two parallel Transformer skeletons and strengthen the intra-scale connections with downsampling and upsampling operations. Moreover, the complementary information from spatial and temporal features is fused and propagated in each other via Contextual Fusion Blocks (CFBs) to promote the prediction further. Extensive experimental results on two large-scale real-world datasets demonstrate the superior performance of our HSTTN over existing solutions.

Existing methods for video question answering (VideoQA) often suffer from spurious correlations between different modalities, leading to a failure in identifying the dominant visual evidence and the intended question. Moreover, these methods function as black boxes, making it difficult to interpret the visual scene during the QA process. In this paper, to discover critical video segments and frames that serve as the visual causal scene for generating reliable answers, we present a causal analysis of VideoQA and propose a framework for cross-modal causal relational reasoning, named Visual Causal Scene Refinement (VCSR). Particularly, a set of causal front-door intervention operations is introduced to explicitly find the visual causal scenes at both segment and frame levels. Our VCSR involves two essential modules: i) the Question-Guided Refiner (QGR) module, which refines consecutive video frames guided by the question semantics to obtain more representative segment features for causal front-door intervention; ii) the Causal Scene Separator (CSS) module, which discovers a collection of visual causal and non-causal scenes based on the visual-linguistic causal relevance and estimates the causal effect of the scene-separating intervention in a contrastive learning manner. Extensive experiments on the NExT-QA, Causal-VidQA, and MSRVTT-QA datasets demonstrate the superiority of our VCSR in discovering visual causal scene and achieving robust video question answering.

Neural fields have achieved impressive advancements in view synthesis and scene reconstruction. However, editing these neural fields remains challenging due to the implicit encoding of geometry and texture information. In this paper, we propose DreamEditor, a novel framework that enables users to perform controlled editing of neural fields using text prompts. By representing scenes as mesh-based neural fields, DreamEditor allows localized editing within specific regions. DreamEditor utilizes the text encoder of a pretrained text-to-Image diffusion model to automatically identify the regions to be edited based on the semantics of the text prompts. Subsequently, DreamEditor optimizes the editing region and aligns its geometry and texture with the text prompts through score distillation sampling [Poole et al. 2022]. Extensive experiments have demonstrated that DreamEditor can accurately edit neural fields of real-world scenes according to the given text prompts while ensuring consistency in irrelevant areas. DreamEditor generates highly realistic textures and geometry, significantly surpassing previous works in both quantitative and qualitative evaluations.

MOTIVATION: Proteins play crucial roles in biological processes, with their functions being closely tied to thermodynamic stability. However, measuring stability changes upon point mutations of amino acid residues using physical methods can be time-consuming. In recent years, several computational methods for protein thermodynamic stability prediction (PTSP) based on deep learning have emerged. Nevertheless, these approaches either overlook the natural topology of protein structures or neglect the inherent noisy samples resulting from theoretical calculation or experimental errors. RESULTS: We propose a novel Global-Local Graph Neural Network powered by Unbiased Curriculum Learning for the PTSP task. Our method first builds a Siamese graph neural network to extract protein features before and after mutation. Since the graph's topological changes stem from local node mutations, we design a local feature transformation module to make the model focus on the mutated site. To address model bias caused by noisy samples, which represent unavoidable errors from physical experiments, we introduce an unbiased curriculum learning method. This approach effectively identifies and re-weights noisy samples during the training process. Extensive experiments demonstrate that our proposed method outperforms advanced protein stability prediction methods, and surpasses state-of-the-art learning methods for regression prediction tasks. AVAILABILITY AND IMPLEMENTATION: All code and data is available at https://github.com/haifangong/UCL-GLGNN.

Semantic segmentation of point cloud usually relies on dense annotation that is exhausting and costly, so it attracts wide attention to investigate solutions for the weakly supervised scheme with only sparse points annotated. Existing works start from the given labels and propagate them to highly-related but unlabeled points, with the guidance of data, e.g. intra-point relation. However, it suffers from (i) the inefficient exploitation of data information, and (ii) the strong reliance on labels thus is easily suppressed when given much fewer annotations. Therefore, we propose a novel framework, PointMatch, that stands on both data and label, by applying consistency regularization to sufficiently probe information from data itself and leveraging weak labels as assistance at the same time. By doing so, meaningful information can be learned from both data and label for better representation learning , which also enables the model more robust to the extent of label sparsity . Simple yet effective, the proposed PointMatch achieves the state-of-the-art performance under various weakly-supervised schemes on both ScanNet-v2 and S3DIS datasets, especially on the settings with extremely sparse labels, e.g. surpassing SQN by 21.2% and 17.2% on the 0.01% and 0.1% setting of ScanNet-v2, respectively.

Matching clothing images from customers and online shopping stores has rich applications in e-commerce. Existing algorithms mostly encode an image as a global feature vector and perform retrieval via global representation matching. However, distinctive local information on clothing is immersed in this global representation, resulting in sub-optimized performance. To address this issue, we propose a novel graph reasoning network (GRNet) on a similarity pyramid, which learns similarities between a query and a gallery cloth by using both initial pairwise multi-scale feature representations and matching propagation for unaligned representations. The query local representations at each scale are aligned with those of the gallery via an adaptive window pooling module. The similarity pyramid is represented by a similarity graph, where nodes represent similarities between clothing components at different scales, and the final matching score is obtained by message propagation along edges. In GRNet, graph reasoning is solved by training a graph convolutional network, enabling the alignment of salient clothing components to improve clothing retrieval. To facilitate future research, we introduce a new benchmark, i.e. FindFashion, containing rich annotations of bounding boxes, views, occlusions, and cropping. Extensive experiments show that GRNet obtains new state-of-the-art results on three challenging benchmarks, e.g. pushing the accuracy of top-1, top-20, and top-50 on DeepFashion to 27, 66, and 75 percent (i.e. 6, 12, and 10 percent absolute improvements), outperforming competitors with large margins. On FindFashion, GRNet achieves considerable improvements on all empirical settings.

Given a natural language referring expression, the goal of referring video segmentation task is to predict the segmentation mask of the referred object in the video. Previous methods only adopt 3D CNNs upon the video clip as a single encoder to extract a mixed spatio-temporal feature for the target frame. Though 3D convolutions are able to recognize which object is performing the described actions, they still introduce misaligned spatial information from adjacent frames, which inevitably confuses features of the target frame and leads to inaccurate segmentation. To tackle this issue, we propose a language-aware spatial-temporal collaboration framework that contains a 3D temporal encoder upon the video clip to recognize the described actions, and a 2D spatial encoder upon the target frame to provide undisturbed spatial features of the referred object. For multimodal features extraction, we propose a Cross-Modal Adaptive Modulation (CMAM) module and its improved version CMAM+ to conduct adaptive cross-modal interaction in the encoders with spatial- or temporal-relevant language features which are also updated progressively to enrich linguistic global context. In addition, we also propose a Language-Aware Semantic Propagation (LASP) module in the decoder to propagate semantic information from deep stages to the shallow stages with language-aware sampling and assignment, which is able to highlight language-compatible foreground visual features and suppress language-incompatible background visual features for better facilitating the spatial-temporal collaboration. Extensive experiments on four popular referring video segmentation benchmarks demonstrate the superiority of our method over the previous state-of-the-art methods.

Existing visual question answering methods often suffer from cross-modal spurious correlations and oversimplified event-level reasoning processes that fail to capture event temporality, causality, and dynamics spanning over the video. In this work, to address the task of event-level visual question answering, we propose a framework for cross-modal causal relational reasoning. In particular, a set of causal intervention operations is introduced to discover the underlying causal structures across visual and linguistic modalities. Our framework, named Cross-Modal Causal RelatIonal Reasoning (CMCIR), involves three modules: i) Causality-aware Visual-Linguistic Reasoning (CVLR) module for collaboratively disentangling the visual and linguistic spurious correlations via front-door and back-door causal interventions; ii) Spatial-Temporal Transformer (STT) module for capturing the fine-grained interactions between visual and linguistic semantics; iii) Visual-Linguistic Feature Fusion (VLFF) module for learning the global semantic-aware visual-linguistic representations adaptively. Extensive experiments on four event-level datasets demonstrate the superiority of our CMCIR in discovering visual-linguistic causal structures and achieving robust event-level visual question answering.

Metro origin-destination prediction is a crucial yet challenging time-series analysis task in intelligent transportation systems, which aims to accurately forecast two specific types of cross-station ridership, i.e., Origin-Destination (OD) one and Destination-Origin (DO) one. However, complete OD matrices of previous time intervals can not be obtained immediately in online metro systems, and conventional methods only used limited information to forecast the future OD and DO ridership separately. In this work, we proposed a novel neural network module termed Heterogeneous Information Aggregation Machine (HIAM), which fully exploits heterogeneous information of historical data (e.g., incomplete OD matrices, unfinished order vectors, and DO matrices) to jointly learn the evolutionary patterns of OD and DO ridership. Specifically, an OD modeling branch estimates the potential destinations of unfinished orders explicitly to complement the information of incomplete OD matrices, while a DO modeling branch takes DO matrices as input to capture the spatial-temporal distribution of DO ridership. Moreover, a Dual Information Transformer is introduced to propagate the mutual information among OD features and DO features for modeling the OD-DO causality and correlation. Based on the proposed HIAM, we develop a unified Seq2Seq network to forecast the future OD and DO ridership simultaneously. Extensive experiments conducted on two large-scale benchmarks demonstrate the effectiveness of our method for online metro origin-destination prediction. Our code is resealed at https://github.com/HCPLab-SYSU/HIAM.

Electricity theft is the primary cause of electrical losses in power systems, which severely harms the economic benefits of electricity providers and threatens the safety of the power supply. However, due to the inherent complex correlation and periodicity of electricity consumption and the low efficiency of large-scale data processing, detecting anomalies in electricity consumption data accurately and efficiently remains challenging. Existing methods usually focus on first-order information and ignore the second-order representation learning that can efficiently model global temporal dependency and facilitate discriminative representation learning of electricity consumption data. In this article, we propose a novel electricity theft detection framework named hybrid-order representation learning network (HORLN). Specifically, the sequential electricity consumption data is transformed into the matrix format containing weekly consumption records. Then, an inter-and-intra week convolution block is designed to capture multiscale features in a local-to-global manner. Meanwhile, a self-dependency modeling module is proposed to learn the second-order representations from self-correlation matrices, which are finally combined with the first-order representations to predict the anomaly scores of electricity consumers. Extensive experiments on a real-world benchmark demonstrate the advantages of our HORLN over state-of-the-art methods.

Compared to unsupervised domain adaptation, semi-supervised domain adaptation (SSDA) aims to significantly improve the classification performance and generalization capability of the model by leveraging the presence of a small amount of labeled data from the target domain. Several SSDA approaches have been developed to enable semantic-aligned feature confusion between labeled (or pseudo labeled) samples across domains; nevertheless, owing to the scarcity of semantic label information of the target domain, they were arduous to fully realize their potential. In this study, we propose a novel SSDA approach named Graph-based Adaptive Betweenness Clustering (G-ABC) for achieving categorical domain alignment, which enables cross-domain semantic alignment by mandating semantic transfer from labeled data of both the source and target domains to unlabeled target samples. In particular, a heterogeneous graph is initially constructed to reflect the pairwise relationships between labeled samples from both domains and unlabeled ones of the target domain. Then, to degrade the noisy connectivity in the graph, connectivity refinement is conducted by introducing two strategies, namely Confidence Uncertainty based Node Removal and Prediction Dissimilarity based Edge Pruning. Once the graph has been refined, Adaptive Betweenness Clustering is introduced to facilitate semantic transfer by using across-domain betweenness clustering and within-domain betweenness clustering, thereby propagating semantic label information from labeled samples across domains to unlabeled target data. Extensive experiments on three standard benchmark datasets, namely DomainNet, Office-Home, and Office-31, indicated that our method outperforms previous state-of-the-art SSDA approaches, demonstrating the superiority of the proposed G-ABC algorithm.

Due to the difficulty of collecting paired Low-Resolution (LR) and High-Resolution (HR) images, the recent research on single image Super-Resolution (SR) has often been criticized for the data bottleneck of the synthetic image degradation between LRs and HRs. Recently, the emergence of real-world SR datasets, e.g., RealSR and DRealSR, promotes the exploration of Real-World image Super-Resolution (RWSR). RWSR exposes a more practical image degradation, which greatly challenges the learning capacity of deep neural networks to reconstruct high-quality images from low-quality images collected in realistic scenarios. In this paper, we explore Taylor series approximation in prevalent deep neural networks for image reconstruction, and propose a very general Taylor architecture to derive Taylor Neural Networks (TNNs) in a principled manner. Our TNN builds Taylor Modules with Taylor Skip Connections (TSCs) to approximate the feature projection functions, following the spirit of Taylor Series. TSCs introduce the input connected directly with each layer at different layers, to sequentially produces different high-order Taylor maps to attend more image details, and then aggregate the different high-order information from different layers. Only via simple skip connections, TNN is compatible with various existing neural networks to effectively learn high-order components of the input image with little increase of parameters. Furthermore, we have conducted extensive experiments to evaluate our TNNs in different backbones on two RWSR benchmarks, which achieve a superior performance in comparison with existing baseline methods.

Locating and stratifying the submucosal tumor of the digestive tract from endoscopy ultrasound (EUS) images are of vital significance to the preliminary diagnosis of tumors. However, the above problems are challenging, due to the poor appearance contrast between different layers of the digestive tract wall (DTW) and the narrowness of each layer. Few of existing deep-learning based diagnosis algorithms are devised to tackle this issue. In this article, we build a multi-task framework for simultaneously locating and stratifying the submucosal tumor. And considering the awareness of the DTW is critical to the localization and stratification of the tumor, we integrate the DTW segmentation task into the proposed multi-task framework. Except for sharing a common backbone model, the three tasks are explicitly directed with a hierarchical guidance module, in which the probability map of DTW itself is used to locally enhance the feature representation for tumor localization, and the probability maps of DTW and tumor are jointly employed to locally enhance the feature representation for tumor stratification. Moreover, by means of the dynamic class activation map, probability maps of DTW and tumor are reused to enforce the stratification inference process to pay more attention to DTW and tumor regions, contributing to a reliable and interpretable submucosal tumor stratification model. Additionally, considering the relation with respect to other structures is beneficial for stratifying tumors, we devise a graph reasoning module to replenish non-local relation knowledge for the stratification branch. Experiments on a Stomach-Esophagus and an Intestinal EUS dataset prove that our method achieves very appealing performance on both tumor localization and stratification, significantly outperforming state-of-the-art object detection approaches.

Recently deep neural networks, which require a large amount of annotated samples, have been widely applied in nuclei instance segmentation of H&E stained pathology images. However, it is inefficient and unnecessary to label all pixels for a dataset of nuclei images which usually contain similar and redundant patterns. Although unsupervised and semi-supervised learning methods have been studied for nuclei segmentation, very few works have delved into the selective labeling of samples to reduce the workload of annotation. Thus, in this paper, we propose a novel full nuclei segmentation framework that chooses only a few image patches to be annotated, augments the training set from the selected samples, and achieves nuclei segmentation in a semi-supervised manner. In the proposed framework, we first develop a novel consistency-based patch selection method to determine which image patches are the most beneficial to the training. Then we introduce a conditional single-image GAN with a component-wise discriminator, to synthesize more training samples. Lastly, our proposed framework trains an existing segmentation model with the above augmented samples. The experimental results show that our proposed method could obtain the same-level performance as a fully-supervised baseline by annotating less than 5% pixels on some benchmarks.

Land remote-sensing analysis is a crucial research in earth science. In this work, we focus on a challenging task of land analysis, i.e., automatic extraction of traffic roads from remote-sensing data, which has widespread applications in urban development and expansion estimation. Nevertheless, conventional methods either only utilized the limited information of aerial images, or simply fused multimodal information (e.g., vehicle trajectories), thus cannot well recognize unconstrained roads. To facilitate this problem, we introduce a novel neural network framework termed cross-modal message propagation network (CMMPNet), which fully benefits the complementary different modal data (i.e., aerial images and crowdsourced trajectories). Specifically, CMMPNet is composed of two deep autoencoders for modality-specific representation learning and a tailor-designed dual enhancement module for cross-modal representation refinement. In particular, the complementary information of each modality is comprehensively extracted and dynamically propagated to enhance the representation of another modality. Extensive experiments on three real-world benchmarks demonstrate the effectiveness of our CMMPNet for robust road extraction benefiting from blending different modal data, either using image and trajectory data or image and light detection and ranging (LiDAR) data. From the experimental results, we observe that the proposed approach outperforms current state-of-the-art methods by large margins. Our source code is resealed on the project page http://lingboliu.com/multimodal_road_extraction.html.

Unsupervised video anomaly detection, a task that requires no labeled normal/abnormal training data in any form, is challenging yet of great importance to both industrial applications and academic research. Existing methods typically follow an iterative pseudo label generation process. However, they lack a principled analysis of the impact of such pseudo label generation on training. Furthermore, the long-range temporal dependencies also has been overlooked, which is unreasonable since the definition of an abnormal event depends on the long-range temporal context. To this end, first, we propose a causal graph to analyze the confounding effect of the pseudo label generation process. Then, we introduce a simple yet effective causal inference based framework to disentangle the noisy pseudo label's impact. Finally, we perform counterfactual based model ensemble that blends long-range temporal context with local image context in inference to make final anomaly detection. Extensive experiments on six standard benchmark datasets show that our proposed method significantly outperforms previous state-of-the-art methods, demonstrating our framework's effectiveness.

Unsupervised Salient Object Detection (USOD) is a promising yet challenging task that aims to learn a salient object detection model without any ground-truth labels. Self-supervised learning based methods have achieved remarkable success recently and have become the dominant approach in USOD. However, we observed that two distribution biases of salient objects limit further performance improvement of the USOD methods, namely, contrast distribution bias and spatial distribution bias. Concretely, contrast distribution bias is essentially a confounder that makes images with similar high-level semantic contrast and/or low-level visual appearance contrast spuriously dependent, thus forming data-rich contrast clusters and leading the training process biased towards the data-rich contrast clusters in the data. Spatial distribution bias means that the position distribution of all salient objects in a dataset is concentrated on the center of the image plane, which could be harmful to off-center objects prediction. This paper proposes a causal based debiasing framework to disentangle the model from the impact of such biases. Specifically, we use causal intervention to perform de-confounded model training to minimize the contrast distribution bias and propose an image-level weighting strategy that softly weights each image's importance according to the spatial distribution bias map. Extensive experiments on 6 benchmark datasets show that our method significantly outperforms previous unsupervised state-of-the-art methods and even surpasses some of the supervised methods, demonstrating our debiasing framework's effectiveness.

Recent advances in deep learning significantly boost the performance of salient object detection (SOD) at the expense of labeling larger-scale per-pixel annotations. To relieve the burden of labor-intensive labeling, deep unsupervised SOD methods have been proposed to exploit noisy labels generated by handcrafted saliency methods. However, it is still difficult to learn accurate saliency details from rough noisy labels. In this paper, we propose to learn saliency from synthetic but clean labels, which naturally has higher pixel-labeling quality without the effort of manual annotations. Specifically, we first construct a novel synthetic SOD dataset by a simple copy-paste strategy. Considering the large appearance differences between the synthetic and real-world scenarios, directly training with synthetic data will lead to performance degradation on real-world scenarios. To mitigate this problem, we propose a novel unsupervised domain adaptive SOD method to adapt between these two domains by uncertainty-aware self-training. Experimental results show that our proposed method outperforms the existing state-of-the-art deep unsupervised SOD methods on several benchmark datasets, and is even comparable to fully-supervised ones.

Due to the sophisticated imaging process, an identical scene captured by different cameras could exhibit distinct imaging patterns, introducing distinct proficiency among the super-resolution (SR) models trained on images from different devices. In this paper, we investigate a novel and practical task coded cross-device SR, which strives to adapt a real-world SR model trained on the paired images captured by one camera to low-resolution (LR) images captured by arbitrary target devices. The proposed task is highly challenging due to the absence of paired data from various imaging devices. To address this issue, we propose an unsupervised domain adaptation mechanism for real-world SR, named Dual ADversarial Adaptation (DADA), which only requires LR images in the target domain with available real paired data from a source camera. DADA employs the Domain-Invariant Attention (DIA) module to establish the basis of target model training even without HR supervision. Furthermore, the dual framework of DADA facilitates an Inter-domain Adversarial Adaptation (InterAA) in one branch for two LR input images from two domains, and an Intra-domain Adversarial Adaptation (IntraAA) in two branches for an LR input image. InterAA and IntraAA together improve the model transferability from the source domain to the target. We empirically conduct experiments under six$\text{Real} \rightarrow \text{Real}$adaptation settings among three different cameras, and achieve superior performance compared with existing state-of-the-art approaches. We also evaluate the proposed DADA to address the adaptation to the video camera, which presents a promising re-search topic to promote the wide applications of real-world super-resolution. Our source code is publicly available at https://github.com/lonelyhopeIDADA.

3D dense captioning aims to describe individual objects in 3D scenes by natural language, where 3D scenes are usually represented as RGB-D scans or point clouds. However, only exploiting single modal information, e.g., point cloud, previous approaches fail to produce faithful descriptions. Though aggregating 2D features into point clouds may be beneficial, it introduces an extra computational burden, especially in the inference phase. In this study, we investigate a cross-modal knowledge transfer using Transformer for 3D dense captioning, namely X-Trans2Cap. Our proposed X-Trans2Cap effectively boost the performance of single-modal 3D captioning through the knowledge distillation enabled by a teacher-student framework. In practice, during the training phase, the teacher network exploits auxiliary 2D modality and guides the student network that only takes point clouds as input through the feature consistency constraints. Owing to the well-designed cross-modal feature fusion module and the feature alignment in the training phase, X-Trans2Cap acquires rich appearance information embedded in 2D images with ease. Thus, a more faithful caption can be generated only using point clouds during the inference. Qualitative and quantitative results confirm that X-Trans2Cap outperforms previous state-of-the-art by a large margin, i.e., about +21 and +16 CIDEr points on ScanRefer and Nr3D datasets, respectively.

Crowd counting is a fundamental yet challenging task that aims to automatically estimate the number of people in crowded scenes. Nowadays, with the rapid development of thermal and depth sensors, thermal images and depth maps become more accessible, which are proven to be beneficial information in boosting the performance of crowd counting. Consequently, we propose a Mutual Attention Transformer (MAT) module to fully leverage the complementary information of different modalities. Specifically, our MAT employs a cross-modal mutual attention mechanism to utilize the features of one modality to enhance the features of the other. Moreover, to improve performance by learning better visual representation and further exploiting modality-wise comple-mentarity, we design a self-supervised pre-training method based on cross-modal image reconstruction. Extensive experiments on two standard benchmarks (i.e., RGBT-CC and ShanghaiTechRGBD) show that the proposed method is effective and universal for multimodal crowd counting, outper-forming previous state-of-the-art methods.

Hair color transfer aims to transfer the hair color from a reference image to an original image while maintaining the hair structure of the original image. However, due to the complex hair structure and the misalignment of hair regions between the original image and the reference image, existing methods cannot complete this task well. To address these issues, we propose a hair color transfer GAN (HairGAN). It first utilizes off-the-shelf network to extract the hair region from the original image and transfer it into intermediary hair color. Then, Spatial-Aware Palette Alignment (SAPA) module is introduced to align the hair regions in the original image and the reference image. Furthermore, HairGAN employs cycle consistency reconstruction module to ensure the global consistency between original image and transferred image. We collect a dataset containing 2850 images and a few paired samples for hair color transfer. Extensive experiments show that HairGAN could generate high-quality transferred results.

In Open Set Domain Adaptation (OSDA), large amounts of target samples are drawn from the implicit categories that never appear in the source domain. Due to the lack of their specific belonging, existing methods indiscriminately regard them as a single class “unknown”. We challenge this broadly-adopted practice that may arouse unexpected detrimental ef-fects because the decision boundaries between the implicit categories have been fully ignored. Instead, we propose Self-supervised Class-Discovering Adapter (SCDA) that attempts to achieve OSDA by gradually discovering those implicit classes, then incorporating them to restructure the classifier and update the domain-adaptive features iteratively. SCDA performs two alternate steps to achieve implicit class discov-ery and self-supervised OSDA, respectively. By jointly op-timizing for two tasks, SCDA achieves the state-of-the-art in OSDA and shows a competitive performance to unearth the implicit target classes.

In the semi-supervised object detection task, due to the scarcity of labeled data and the diversity and complexity of objects to be detected, the quality of pseudo-labels generated by existing methods for unlabeled data is relatively low, which severely restricts the performance of semi-supervised object detection. In this paper, we revisit the pseudo-labeling based Teacher-Student mutual learning framework for semi-supervised object detection and identify that the inconsistency of the location and feature of the candidate object proposals between the Teacher and the Student branches are the fatal cause of the low quality of the pseudo labels. To address this issue, we propose a simple yet effective technique within the mainstream teacher-student framework, called Double Check Soft Teacher, to overcome the harm caused by insufficient quality of pseudo labels. Specifically, our proposed method leverages teacher model to generate pseudo labels for the student model. Especially, the candidate boxes generated by the student model based on the pseudo label will be sent to the teacher model for "double check", and then the teacher model will output probabilistic soft label with background class for those candidate boxes, which will be used to train the student model. Together with a pseudo labeling mechanism based on the sum of the TOP-K prediction score, which improves the recall rate of pseudo labels, Double Check Soft Teacher consistently surpasses state-of-the-art methods by significant margins on the MS-COCO benchmark, pushing the new state-of-the-art. Source codes are available at https://github.com/wkfdb/DCST.

Semi-supervised domain adaptation (SSDA) aims to apply knowledge learned from a fully labeled source domain to a scarcely labeled target domain. In this paper, we propose a Multi-level Consistency Learning (MCL) framework for SSDA. Specifically, our MCL regularizes the consistency of different views of target domain samples at three levels: (i) at inter-domain level, we robustly and accurately align the source and target domains using a prototype-based optimal transport method that utilizes the pros and cons of different views of target samples; (ii) at intra-domain level, we facilitate the learning of both discriminative and compact target feature representations by proposing a novel class-wise contrastive clustering loss; (iii) at sample level, we follow standard practice and improve the prediction accuracy by conducting a consistency-based self-training. Empirically, we verified the effectiveness of our MCL framework on three popular SSDA benchmarks, i.e., VisDA2017, DomainNet, and Office-Home datasets, and the experimental results demonstrate that our MCL framework achieves the state-of-the-art performance.

Medical vision-and-language pre-training (Med-VLP) has received considerable attention owing to its applicability to extracting generic vision-and-language representations from medical images and texts. Most existing methods mainly contain three elements: uni-modal encoders (i.e., a vision encoder and a language encoder), a multi-modal fusion module, and pretext tasks, with few studies considering the importance of medical domain expert knowledge and explicitly exploiting such knowledge to facilitate Med-VLP. Although there exist knowledge-enhanced vision-and-language pre-training (VLP) methods in the general domain, most require off-the-shelf toolkits (e.g., object detectors and scene graph parsers), which are unavailable in the medical domain. In this paper, we propose a systematic and effective approach to enhance Med-VLP by structured medical knowledge from three perspectives. First, considering knowledge can be regarded as the intermediate medium between vision and language, we align the representations of the vision encoder and the language encoder through knowledge. Second, we inject knowledge into the multi-modal fusion model to enable the model to perform reasoning using knowledge as the supplementation of the input image and text. Third, we guide the model to put emphasis on the most critical information in images and texts by designing knowledge-induced pretext tasks. To perform a comprehensive evaluation and facilitate further research, we construct a medical vision-and-language benchmark including three tasks. Experimental results illustrate the effectiveness of our approach, where state-of-the-art performance is achieved on all downstream tasks. Further analyses explore the effects of different components of our approach and various settings of pre-training.

Significant progress has been made in learning image classification neural networks under long-tail data distribution using robust training algorithms such as data re-sampling, re-weighting, and margin adjustment. Those methods, however, ignore the impact of data imbalance on feature normalization. The dominance of majority classes (head classes) in estimating statistics and affine parameters causes internal covariate shifts within less-frequent categories to be overlooked. To alleviate this challenge, we propose a compound batch normalization method based on a Gaussian mixture. It can model the feature space more comprehensively and reduce the dominance of head classes. In addition, a moving average-based expectation maximization (EM) algorithm is employed to estimate the statistical parameters of multiple Gaussian distributions. However, the EM algorithm is sensitive to initialization and can easily become stuck in local minima where the multiple Gaussian components continue to focus on majority classes. To tackle this issue, we developed a dual-path learning framework that employs class-aware split feature normalization to diversify the estimated Gaussian distributions, allowing the Gaussian components to fit with training samples of less-frequent classes more comprehensively. Extensive experiments on commonly used datasets demonstrated that the proposed method outperforms existing methods on long-tailed image classification.

In the task of talking head generation, it is hard to learn the mapping relationship between generated head image and input audio signal. To tackle this challenge, we propose to learn the mapping relationship between input audio signal and the parameters of three-dimensional morphable face model (3DMM) first, which is easier to learn. Then the parameters of 3DMM are used to guide the generation of high-quality talking head images. Prior works mostly encode audio features from short audio windows, which may influence the accuracy of lip movements sometimes because of the limited context. In this paper, we propose a transformer-based audio encoder to take full use of the long-term context from audio and then predict a sequence of 3DMM parameters accurately. Unlike prior works that only use the 3DMM parameters of expression, rotation and translation, we propose to include the parameters of identity. Since the location of 3D facial mesh point is decided by the expression and identity parameters, it is helpful to supply more subtle control of lip movement by considering the identity parameters. The experimental results reveal that our method ranks first in 4 of the total 11 evaluation metrics, which ranks first in the talking head generation track.

We investigate a practical domain adaptation task, called source-free domain adaptation (SFUDA), where the source pretrained model is adapted to the target domain without access to the source data. Existing techniques mainly leverage self-supervised pseudo-labeling to achieve class-wise global alignment [1] or rely on local structure extraction that encourages the feature consistency among neighborhoods [2]. While impressive progress has been made, both lines of methods have their own drawbacks – the “global” approach is sensitive to noisy labels while the “local” counterpart suffers from the source bias. In this paper, we present Divide and Contrast (DaC), a new paradigm for SFUDA that strives to connect the good ends of both worlds while bypassing their limitations. Based on the prediction confidence of the source model, DaC divides the target data into source-like and target-specific samples, where either group of samples is treated with tailored goals under an adaptive contrastive learning framework. Specifically, the source-like samples are utilized for learning global class clustering thanks to their relatively clean labels. The more noisy target-specific data are harnessed at the instance level for learning the intrinsic local structures. We further align the source-like domain with the target-specific samples using a memory bank-based Maximum Mean Discrepancy (MMD) loss to reduce the distribution mismatch. Extensive experiments on VisDA, Office-Home, and the more challenging DomainNet have verified the superior performance of DaC over current state-of-the-art approaches. The code is available at https://github.com/ZyeZhang/DaC.git.

Given a natural language expression and an image/video, the goal of referring segmentation is to produce the pixel-level masks of the entities described by the subject of the expression. Previous approaches tackle this problem by implicit feature interaction and fusion between visual and linguistic modalities in a one-stage manner. However, human tends to solve the referring problem in a progressive manner based on informative words in the expression, i.e., first roughly locating candidate entities and then distinguishing the target one. In this paper, we propose a cross-modal progressive comprehension (CMPC) scheme to effectively mimic human behaviors and implement it as a CMPC-I (Image) module and a CMPC-V (Video) module to improve referring image and video segmentation models. For image data, our CMPC-I module first employs entity and attribute words to perceive all the related entities that might be considered by the expression. Then, the relational words are adopted to highlight the target entity as well as suppress other irrelevant ones by spatial graph reasoning. For video data, our CMPC-V module further exploits action words based on CMPC-I to highlight the correct entity matched with the action cues by temporal graph reasoning. In addition to the CMPC, we also introduce a simple yet effective Text-Guided Feature Exchange (TGFE) module to integrate the reasoned multimodal features corresponding to different levels in the visual backbone under the guidance of textual information. In this way, multi-level features can communicate with each other and be mutually refined based on the textual context. Combining CMPC-I or CMPC-V with TGFE can form our image or video version referring segmentation frameworks and our frameworks achieve new state-of-the-art performances on four referring image segmentation benchmarks and three referring video segmentation benchmarks respectively. Our code is available at https://github.com/spyflying/CMPC-Refseg.

Although deep convolutional neural networks (CNNs) have demonstrated remarkable performance on multiple computer vision tasks, researches on adversarial learning have shown that deep models are vulnerable to adversarial examples, which are crafted by adding visually imperceptible perturbations to the input images. Most of the existing adversarial attack methods only create a single adversarial example for the input, which just gives a glimpse of the underlying data manifold of adversarial examples. An attractive solution is to explore the solution space of the adversarial examples and generate a diverse bunch of them, which could potentially improve the robustness of real-world systems and help prevent severe security threats and vulnerabilities. In this paper, we present an effective method, called Hamiltonian Monte Carlo with Accumulated Momentum (HMCAM), aiming to generate a sequence of adversarial examples. To improve the efficiency of HMC, we propose a new regime to automatically control the length of trajectories, which allows the algorithm to move with adaptive step sizes along the search direction at different positions. Moreover, we revisit the reason for high computational cost of adversarial training under the view of MCMC and design a new generative method called Contrastive Adversarial Training (CAT), which approaches equilibrium distribution of adversarial examples with only few iterations by building from small modifications of the standard Contrastive Divergence (CD) and achieve a trade-off between efficiency and accuracy. Both quantitative and qualitative analysis on several natural image datasets and practical systems have confirmed the superiority of the proposed algorithm.

In this work, we introduce a novel task – Human-centric Spatio-Temporal Video Grounding (HC-STVG). Unlike the existing referring expression tasks in images or videos, by focusing on humans, HC-STVG aims to localize a spatio-temporal tube of the target person from an untrimmed video based on a given textural description. This task is useful, especially for healthcare and security related applications, where the surveillance videos can be extremely long but only a specific person during a specific period is concerned. HC-STVG is a video grounding task that requires both spatial (where) and temporal (when) localization. Unfortunately, the existing grounding methods cannot handle this task well. We tackle this task by proposing an effective baseline method named Spatio-Temporal Grounding with Visual Transformers (STGVT), which utilizes Visual Transformers to extract cross-modal representations for video-sentence matching and temporal localization. To facilitate this task, we also contribute an HC-STVG datasetThe new dataset is available athttps://github.com/tzhhhh123/HC-STVG. consisting of 5,660 video-sentence pairs on complex multi-person scenes. Specifically, each video lasts for 20 seconds, pairing with a natural query sentence with an average of 17.25 words. Extensive experiments are conducted on this dataset, demonstrating that the newly-proposed method outperforms the existing baseline methods.

Due to the widespread applications in real-world scenarios, metro ridership prediction is a crucial but challenging task in intelligent transportation systems. However, conventional methods either ignore the topological information of metro systems or directly learn on physical topology, and cannot fully explore the patterns of ridership evolution. To address this problem, we model a metro system as graphs with various topologies and propose a unified Physical-Virtual Collaboration Graph Network (PVCGN), which can effectively learn the complex ridership patterns from the tailor-designed graphs. Specifically, a physical graph is directly built based on the realistic topology of the studied metro system, while a similarity graph and a correlation graph are built with virtual topologies under the guidance of the inter-station passenger flow similarity and correlation. These complementary graphs are incorporated into a Graph Convolution Gated Recurrent Unit (GC-GRU) for spatial-temporal representation learning. Further, a Fully-Connected Gated Recurrent Unit (FC-GRU) is also applied to capture the global evolution tendency. Finally, we develop a Seq2Seq model with GC-GRU and FC-GRU to forecast the future metro ridership sequentially. Extensive experiments on two large-scale benchmarks (e.g., Shanghai Metro and Hangzhou Metro) well demonstrate the superiority of our PVCGN for station-level metro ridership prediction. Moreover, we apply the proposed PVCGN to address the online origin-destination (OD) ridership prediction and the experiment results show the universality of our method. Our code and benchmarks are available athttps://github.com/HCPLab-SYSU/PVCGN.

Medical visual question answering (VQA) aims to correctly answer a clinical question related to a given medical image. Nevertheless, owing to the expensive manual annotations of medical data, the lack of labeled data limits the development of medical VQA. In this paper, we propose a simple yet effective data augmentation method, VQAMix, to mitigate the data limitation problem. Specifically, VQAMix generates more labeled training samples by linearly combining a pair of VQA samples, which can be easily embedded into any visual-language model to boost performance. However, mixing two VQA samples would construct new connections between images and questions from different samples, which will cause the answers for those new fabricated image-question pairs to be missing or meaningless. To solve the missing answer problem, we first develop the Learning with Missing Labels (LML) strategy, which roughly excludes the missing answers. To alleviate the meaningless answer issue, we design the Learning with Conditional-mixed Labels (LCL) strategy, which further utilizes language-type prior to forcing the mixed pairs to have reasonable answers that belong to the same category. Experimental results on the VQA-RAD and PathVQA benchmarks show that our proposed method significantly improves the performance of the baseline by about 7% and 5% on the averaging result of two backbones, respectively. More importantly, VQAMix could improve confidence calibration and model interpretability, which is significant for medical VQA models in practical applications. All code and models are available at https://github.com/haifangong/VQAMix.

Referring image segmentation aims at segmenting out the object or stuff referred to by a natural language expression. The challenge of this task lies in the requirement of understanding both vision and language. The linguistic structure of a referring expression can provide an intuitive and explainable layout for reasoning over visual and linguistic concepts. In this paper, we propose a structured attention network (SANet) to explore the multimodal reasoning over the dependency tree parsed from the referring expression. Specifically, SANet implements the multimodal reasoning using an attentional multimodal tree-structure recurrent module (AMTreeGRU) in a bottom-up manner. In addition, for spatial detail improvement, SANet further incorporates the semantics-guided low-level features into high-level ones using the proposed attentional skip connection module. Extensive experiments on four public benchmark datasets demonstrate the superiority of our proposed SANet with more explainable visualization examples.

The postprocessing method of ensemble forecasts is usually used to find a more precise estimate of future precipitation, because dynamic meteorology models have limitations in fitting fine-grained atmospheric processes and precipitation is driven more often by smaller-scale processes, while ensemble forecasts can hit this precipitation at times. However, the pattern of these hits cannot be easily summarized. The existing objective postprocessing methods tend to extend the rain area or false alarm the precipitation intensity categories. In this work, we introduce a multi-layer structure to simultaneously reduce the bias in forecast ensembles output by meteorology models and merge them to a quality deterministic (single-valued) forecast using cross-grid information, which differs quite dramatically from the previous statistical postprocessing method. The multi-layer network is designed to model the spatial distribution of future precipitation of different intensity categories(IC-MLNet). We provide a comparison of IC-MLNet to simple average as well as another two state-of-the-art ensemble quantitative precipitation forecasts (QPFs) postprocessing approaches over both single-model and multi-model ensemble forecasts datasets from TIGGE. The experimental results indicate that our model achieves superior performance over the compared baselines in precipitation amount prediction as well as precipitation intensities categories prediction.

Language-queried video actor segmentation aims to predict the pixel-level mask of the actor which performs the actions described by a natural language query in the target frames. Existing methods adopt 3D CNNs over the video clip as a general encoder to extract a mixed spatio-temporal feature for the target frame. Though 3D convolutions are amenable to recognizing which actor is performing the queried actions, it also inevitably introduces misaligned spatial information from adjacent frames, which confuses features of the target frame and yields inaccurate segmentation. Therefore, we propose a collaborative spatial-temporal encoder-decoder framework which contains a 3D temporal encoder over the video clip to recognize the queried actions, and a 2D spatial encoder over the target frame to accurately segment the queried actors. In the decoder, a Language-Guided Feature Selection (LGFS) module is proposed to flexibly integrate spatial and temporal features from the two encoders. We also propose a Cross-Modal Adaptive Modulation (CMAM) module to dynamically recombine spatial- and temporal-relevant linguistic features for multimodal feature interaction in each stage of the two encoders. Our method achieves new state-of-the-art performance on two popular benchmarks with less computational overhead than previous approaches.

In semi-supervised domain adaptation, a few labeled samples per class in the target domain guide features of the remaining target samples to aggregate around them. However, the trained model cannot produce a highly discriminative feature representation for the target domain because the training data is dominated by labeled samples from the source domain. This could lead to disconnection between the labeled and unlabeled target samples as well as misalignment between unlabeled target samples and the source domain. In this paper, we propose a novel approach called Cross-domain Adaptive Clustering to address this problem. To achieve both inter-domain and intra-domain adaptation, we first introduce an adversarial adaptive clustering loss to group features of unlabeled target data into clusters and perform cluster-wise feature alignment across the source and target domains. We further apply pseudo labeling to unlabeled samples in the target domain and retain pseudo-labels with high confidence. Pseudo labeling expands the number of "labeled" samples in each class in the target domain, and thus produces a more robust and powerful cluster core for each class to facilitate adversarial learning. Extensive experiments on benchmark datasets, including DomainNet, Office-Home and Office, demonstrate that our proposed approach achieves the state-of-the-art performance in semi-supervised domain adaptation.

Humans learn from life events to form intuitions towards the understanding of visual environments and languages. Envision that you are instructed by a high-level instruction, "Go to the bathroom in the master bedroom and replace the blue towel on the left wall", what would you possibly do to carry out the task? Intuitively, we comprehend the semantics of the instruction to form an overview of where a bathroom is and what a blue towel is in mind; then, we navigate to the target location by consistently matching the bathroom appearance in mind with the current scene. In this paper, we present an agent that mimics such human behaviors. Specifically, we focus on the Remote Embodied Visual Referring Expression in Real Indoor Environments task, called REVERIE, where an agent is asked to correctly localize a remote target object specified by a concise high-level natural language instruction, and propose a two-stage training pipeline. In the first stage, we pretrain the agent with two cross-modal alignment sub-tasks, namely the Scene Grounding task and the Object Grounding task. The agent learns where to stop in the Scene Grounding task and what to attend to in the Object Grounding task respectively. Then, to generate action sequences, we propose a memory-augmented attentive action decoder to smoothly fuse the pre-trained vision and language representations with the agent’s past memory experiences. Without bells and whistles, experimental results show that our method outperforms previous state-of-the-art(SOTA) significantly, demonstrating the effectiveness of our method.

Crowd counting is a fundamental yet challenging task, which desires rich information to generate pixel-wise crowd density maps. However, most previous methods only used the limited information of RGB images and cannot well discover potential pedestrians in unconstrained scenarios. In this work, we find that incorporating optical and thermal information can greatly help to recognize pedestrians. To promote future researches in this field, we introduce a large-scale RGBT Crowd Counting (RGBT-CC) benchmark, which contains 2,030 pairs of RGB-thermal images with 138,389 annotated people. Furthermore, to facilitate the multimodal crowd counting, we propose a cross-modal collaborative representation learning framework, which consists of multiple modality-specific branches, a modality-shared branch, and an Information Aggregation-Distribution Module (IADM) to capture the complementary information of different modalities fully. Specifically, our IADM incorporates two collaborative information transfers to dynamically enhance the modality-shared and modality-specific representations with a dual information propagation mechanism. Extensive experiments conducted on the RGBT-CC benchmark demonstrate the effectiveness of our framework for RGBT crowd counting. Moreover, the proposed approach is universal for multimodal crowd counting and is also capable to achieve superior performance on the ShanghaiTechRGBD [22] dataset. Finally, our source code and benchmark have been released at http://lingboliu.com/RGBT_Crowd_Counting.html.

Referring image segmentation aims to segment the referent that is the corresponding object or stuff referred by a natural language expression in an image. Its main challenge lies in how to effectively and efficiently differentiate between the referent and other objects of the same category as the referent. In this paper, we tackle the challenge by jointly performing compositional visual reasoning and accurate segmentation in a single stage via the proposed novel Bottom-Up Shift (BUS) and Bidirectional Attentive Refinement (BIAR) modules. Specifically, BUS progressively locates the referent along hierarchical reasoning steps implied by the expression. At each step, it locates the corresponding visual region by disambiguating between similar regions, where the disambiguation bases on the relationships between regions. By the explainable visual reasoning, BUS explicitly aligns linguistic components with visual regions so that it can identify all the mentioned entities in the expression. BIAR fuses multi-level features via a two-way attentive message passing, which captures the visual details relevant to the referent to refine segmentation results. Experimental results demonstrate that the proposed method consisting of BUS and BIAR modules, can not only consistently surpass all existing state-of-the-art algorithms across common benchmark datasets but also visualize interpretable reasoning steps for stepwise segmentation. Code is available at https://github.com/incredibleXM/BUSNet.

Open-set semi-supervised learning (open-set SSL) investigates a challenging but practical scenario where out-of-distribution (OOD) samples are contained in the unlabeled data. While the mainstream technique seeks to completely filter out the OOD samples for semi-supervised learning (SSL), we propose a novel training mechanism that could effectively exploit the presence of OOD data for enhanced feature learning while avoiding its adverse impact on the SSL. We achieve this goal by first introducing a warm-up training that leverages all the unlabeled data, including both the in-distribution (ID) and OOD samples. Specifically, we perform a pretext task that enforces our feature extractor to obtain a high-level semantic understanding of the training images, leading to more discriminative features that can benefit the downstream tasks. Since the OOD samples are inevitably detrimental to SSL, we propose a novel cross-modal matching strategy to detect OOD samples. Instead of directly applying binary classification [39], we train the network to predict whether the data sample is matched to an assigned one-hot class label. The appeal of the proposed cross-modal matching over binary classification is the ability to generate a compatible feature space that aligns with the core classification task. Extensive experiments show that our approach substantially lifts the performance on open-set SSL and outperforms the state-of-the-art by a large margin.

The key point of language-guided person search is to construct the cross-modal association between visual and textual input. Existing methods focus on designing multimodal attention mechanisms and novel cross-modal loss functions to learn such association implicitly. We propose a representation learning method for language-guided person search based on color reasoning (LapsCore). It can explicitly build a fine-grained cross-modal association bidirectionally. Specifically, a pair of dual sub-tasks, image colorization and text completion, is designed. In the former task, rich text information is learned to colorize gray images, and the latter one requests the model to understand the image and complete color word vacancies in the captions. The two sub-tasks enable models to learn correct alignments between text phrases and image regions, so that rich multimodal representations can be learned. Extensive experiments on multiple datasets demonstrate the effectiveness and superiority of the proposed method.

Deep networks for Monocular Depth Estimation (MDE) have achieved promising performance recently and it is of great importance to further understand the interpretability of these networks. Existing methods attempt to provide post-hoc explanations by investigating visual cues, which may not explore the internal representations learned by deep networks. In this paper, we find that some hidden units of the network are selective to certain ranges of depth, and thus such behavior can be served as a way to interpret the internal representations. Based on our observations, we quantify the interpretability of a deep MDE network by the depth selectivity of its hidden units. Moreover, we then propose a method to train interpretable MDE deep networks without changing their original architectures, by assigning a depth range for each unit to select. Experimental results demonstrate that our method is able to enhance the interpretability of deep MDE networks by largely improving the depth selectivity of their units, while not harming or even improving the depth estimation accuracy. We further provide comprehensive analysis to show the reliability of selective units, the applicability of our method on different layers, models, and datasets, and a demonstration on analysis of model error. Source code and models are available at https://github.com/youzunzhi/InterpretableMDE.

In this paper, we introduce a novel task, referred to as Weakly-Supervised Spatio-Temporal Anomaly Detection (WSSTAD) in surveillance video. Specifically, given an untrimmed video, WSSTAD aims to localize a spatio-temporal tube (i.e., a sequence of bounding boxes at consecutive times) that encloses the abnormal event, with only coarse video-level annotations as supervision during training. To address this challenging task, we propose a dual-branch network which takes as input the proposals with multi-granularities in both spatial-temporal domains. Each branch employs a relationship reasoning module to capture the correlation between tubes/videolets, which can provide rich contextual information and complex entity relationships for the concept learning of abnormal behaviors. Mutually-guided Progressive Refinement framework is set up to employ dual-path mutual guidance in a recurrent manner, iteratively sharing auxiliary supervision information across branches. It impels the learned concepts of each branch to serve as a guide for its counterpart, which progressively refines the corresponding branch and the whole framework. Furthermore, we contribute two datasets, i.e., ST-UCF-Crime and STRA, consisting of videos containing spatio-temporal abnormal annotations to serve as the benchmarks for WSSTAD. We conduct extensive qualitative and quantitative evaluations to demonstrate the effectiveness of the proposed approach and analyze the key factors that contribute more to handle this task.

Due to the severe lack of labeled data, existing methods of medical visual question answering usually rely on transfer learning to obtain effective image feature representation and use cross-modal fusion of visual and linguistic features to achieve question-related answer prediction. These two phases are performed independently and without considering the compatibility and applicability of the pre-trained features for cross-modal fusion. Thus, we reformulate image feature pre-training as a multi-task learning paradigm and witness its extraordinary superiority, forcing it to take into account the applicability of features for the specific image comprehension task. Furthermore, we introduce a cross-modal self-attention~(CMSA) module to selectively capture the long-range contextual relevance for more effective fusion of visual and linguistic features. Experimental results demonstrate that the proposed method outperforms existing state-of-the-art methods. Our code and models are available at https://github.com/haifangong/CMSA-MTPT-4-MedicalVQA.

Recently deep neural networks (DNNs) have achieved significant success in real-world image super-resolution (SR). However, adversarial image samples with quasi-imperceptible noises could threaten deep learning SR models. In this paper, we propose a robust deep learning framework for real-world SR that randomly erases potential adversarial noises in the frequency domain of input images or features. The rationale is that on the SR task clean images or features have a different pattern from the attacked ones in the frequency domain. Observing that existing adversarial attacks usually add high-frequency noises to input images, we introduce a novel random frequency mask module that blocks out high-frequency components possibly containing the harmful perturbations in a stochastic manner. Since the frequency masking may not only destroys the adversarial perturbations but also affects the sharp details in a clean image, we further develop an adversarial sample classifier based on the frequency domain of images to determine if applying the proposed mask module. Based on the above ideas, we devise a novel real-world image SR framework that combines the proposed frequency mask modules and the proposed adversarial classifier with an existing super-resolution backbone network. Experiments show that our proposed method is more insensitive to adversarial attacks and presents more stable SR results than existing models and defenses.

In this paper, we focus on solving the navigation problem of embodied question answering (EmbodiedQA), where the lack of experience and common sense information essentially result in a failure finding target when the robot is spawn in unknown environments. We present a route planning method named Path Estimation and Memory Recalling (PEMR) framework. PEMR includes a “looking ahead” process, i.e. a visual feature extractor module that estimates feasible paths for gathering 3D navigational information; another process “looking behind” process that is a memory recalling mechanism aims at fully leveraging past experience collected by the feature extractor. To encourage the navigator to learn more accurate prior expert experience, we improve the original benchmark dataset and provide a family of evaluation metrics for diagnosing both navigation and question answering modules. We show strong experimental results of PEMR on the EmbodiedQA navigation task.

Grounding referring expressions in images aims to locate the object instance in an image described by a referring expression. It involves a joint understanding of natural language and image content, and is essential for a range of visual tasks related to human-computer interaction. As a language-to-vision matching task, the core of this problem is to not only extract all the necessary information (i.e., objects and the relationships among them) in both the image and referring expression, but also make full use of context information to align cross-modal semantic concepts in the extracted information. Unfortunately, existing work on grounding referring expressions fails to accurately extract multi-order relationships from the referring expression and associate them with the objects and their related contexts in the image. In this paper, we propose a cross-modal relationship extractor (CMRE) to adaptively highlight objects and relationships (spatial and semantic relations) related to the given expression with a cross-modal attention mechanism, and represent the extracted information as a language-guided visual relation graph. In addition, we propose a Gated Graph Convolutional Network (GGCN) to compute multimodal semantic contexts by fusing information from different modes and propagating multimodal information in the structured relation graph. Experimental results on three common benchmark datasets show that our Cross-Modal Relationship Inference Network, which consists of CMRE and GGCN, significantly surpasses all existing state-of-the-art methods.

Recently, deep convolutional neural networks have achieved significant success in salient object detection. However, existing state-of-the-art methods require high-end GPUs to achieve real-time performance, which makes it hard to adapt to low cost or portable devices. Although generic network architectures have been proposed to speed up inference on mobile devices, they are tailored to the task of image classification or semantic segmentation, and struggle to capture intrachannel and interchannel correlations that are essential for contrast modeling in salient object detection. Motivated by the above observations, we design a new deep-learning algorithm for fast salient object detection. The proposed algorithm for the first time achieves competitive accuracy and high inference efficiency simultaneously with a single CPU thread. Specifically, we propose a novel depthwise nonlocal module (DNL), which implicitly models contrast via harvesting intrachannel and interchannel correlations in a self-attention manner. In addition, we introduce a depthwise nonlocal network architecture that incorporates both DNLs module and inverted residual blocks. The experimental results show that our proposed network attains very competitive accuracy on a wide range of salient object detection datasets while achieving state-of-the-art efficiency among all existing deep-learning-based algorithms.

Human-object interaction detection that aims at detecting triplets is critical for the holistic human-centric scene understanding. Existing approaches ignore the modeling of correlations among hierarchical human parts and objects. In this work, we introduce a Hierarchical Reasoning Network (HRNet) to capture relations among human parts at multiple scales (including the holistic human, human region, and human keypoint levels) and objects via a unified graph. In particular, HRNet first constructs one multi-level human parts graph, each level of which consists of human parts at one specific scale, objects, and the unions of human part-object pairs as nodes, and their mutual visual and spatial layout relations as intra-level reasoning. To also capture the relations across scales, we further introduce inter-level reasoning between the nodes of two consecutive levels based on the prior of human body structure. The representations of graph nodes are propagated along intra-level and inter-level reasoning in turn during reasoning. Extensive experiments demonstrate our HRNet obtains new state-of-the-art results on three challenging HICO-DET, V-COCO and HOI-A benchmarks, validating the compelling effectiveness of the proposed method.

Existing vision-based action recognition is susceptible to occlusion and appearance variations, while wearable sensors can alleviate these challenges by capturing human motion with one-dimensional time-series signals (e.g. acceleration, gyroscope, and orientation). For the same action, the knowledge learned from vision sensors (videos or images) and wearable sensors, may be related and complementary. However, there exists a significantly large modality difference between action data captured by wearable-sensor and vision-sensor in data dimension, data distribution, and inherent information content. In this paper, we propose a novel framework, named Semantics-aware Adaptive Knowledge Distillation Networks (SAKDN), to enhance action recognition in vision-sensor modality (videos) by adaptively transferring and distilling the knowledge from multiple wearable sensors. The SAKDN uses multiple wearable-sensors as teacher modalities and uses RGB videos as student modalities. To preserve the local temporal relationship and facilitate employing visual deep learning models, we transform one-dimensional time-series signals of wearable sensors to two-dimensional images by designing a gramian angular field based virtual image generation model. Then, we introduce a novel Similarity-Preserving Adaptive Multi-modal Fusion Module (SPAMFM) to adaptively fuse intermediate representation knowledge from different teacher networks. Finally, to fully exploit and transfer the knowledge of multiple well-trained teacher networks to the student network, we propose a novel Graph-guided Semantically Discriminative Mapping (GSDM) module, which utilizes graph-guided ablation analysis to produce a good visual explanation to highlight the important regions across modalities and concurrently preserve the interrelations of original data. Experimental results on Berkeley-MHAD, UTD-MHAD, and MMAct datasets well demonstrate the effectiveness of our proposed SAKDN for adaptive knowledge transfer from wearable-sensors modalities to vision-sensors modalities. The code is publicly available at https://github.com/YangLiu9208/SAKDN.

As a crucial component in intelligent transportation systems, traffic flow prediction has recently attracted widespread research interest in the field of artificial intelligence (AI) with the increasing availability of massive traffic mobility data. Its key challenge lies in how to integrate diverse factors (such as temporal rules and spatial dependencies) to infer the evolution trend of traffic flow. To address this problem, we propose a unified neural network called Attentive Traffic Flow Machine (ATFM), which can effectively learn the spatial-temporal feature representations of traffic flow with an attention mechanism. In particular, our ATFM is composed of two progressive Convolutional Long Short-Term Memory (ConvLSTM[1]) units connected with a convolutional layer. Specifically, the first ConvLSTM unit takes normal traffic flow features as input and generates a hidden state at each time-step, which is further fed into the connected convolutional layer for spatial attention map inference. The second ConvLSTM unit aims at learning the dynamic spatial-temporal representations from the attentionally weighted traffic flow features. Further, we develop two deep learning frameworks based on ATFM to predict citywide short-term/long-term traffic flow by adaptively incorporating the sequential and periodic data as well as other external influences. Extensive experiments on two standard benchmarks well demonstrate the superiority of the proposed method for traffic flow prediction. Moreover, to verify the generalization of our method, we also apply the customized framework to forecast the passenger pickup/dropoff demands in traffic prediction and show its superior performance. Our code and data are available athttps://github.com/liulingbo918/ATFM.

Identifying and locating diseases in chest X-rays are very challenging, due to the low visual contrast between normal and abnormal regions, and distortions caused by other overlapping tissues. An interesting phenomenon is that there exist many similar structures in the left and right parts of the chest, such as ribs, lung fields and bronchial tubes. This kind of similarities can be used to identify diseases in chest X-rays, according to the experience of broad-certificated radiologists. Aimed at improving the performance of existing detection methods, we propose a deep end-to-end module to exploit the contralateral context information for enhancing feature representations of disease proposals. First of all, under the guidance of the spine line, the spatial transformer network is employed to extract local contralateral patches, which can provide valuable context information for disease proposals. Then, we build up a specific module, based on both additive and subtractive operations, to fuse the features of the disease proposal and the contralateral patch. Our method can be integrated into both fully and weakly supervised disease detection frameworks. It achieves 33.17 AP50 on a carefully annotated private chest X-ray dataset which contains 31,000 images. Experiments on the NIH chest X-ray dataset indicate that our method achieves state-of-the-art performance in weakly-supervised disease localization.

Few-shot learning aims to learn novel categories from very few samples given some base categories with sufficient training samples. The main challenge of this task is the novel categories are prone to dominated by color, texture, shape of the object or background context (namely specificity), which are distinct for the given few training samples but not common for the corresponding categories (see Figure 1). Fortunately, we find that transferring information of the correlated based categories can help learn the novel concepts and thus avoid the novel concept being dominated by the specificity. Besides, incorporating semantic correlations among different categories can effectively regularize this information transfer. In this work, we represent the semantic correlations in the form of structured knowledge graph and integrate this graph into deep neural networks to promote few-shot learning by a novel Knowledge Graph Transfer Network (KGTN). Specifically, by initializing each node with the classifier weight of the corresponding category, a propagation mechanism is learned to adaptively propagate node message through the graph to explore node interaction and transfer classifier information of the base categories to those of the novel ones. Extensive experiments on the ImageNet dataset show significant performance improvement compared with current leading competitors. Furthermore, we construct an ImageNet-6K dataset that covers larger scale categories, i.e, 6,000 categories, and experiments on this dataset further demonstrate the effectiveness of our proposed model.

Temporally language grounding in untrimmed videos is a newly-raised task in video understanding. Most of the existing methods suffer from inferior efficiency, lacking interpretability, and deviating from the human perception mechanism. Inspired by human's coarse-to-fine decision-making paradigm, we formulate a novel Tree-Structured Policy based Progressive Reinforcement Learning (TSP-PRL) framework to sequentially regulate the temporal boundary by an iterative refinement process. The semantic concepts are explicitly represented as the branches in the policy, which contributes to efficiently decomposing complex policies into an interpretable primitive action. Progressive reinforcement learning provides correct credit assignment via two task-oriented rewards that encourage mutual promotion within the tree-structured policy. We extensively evaluate TSP-PRL on the Charades-STA and ActivityNet datasets, and experimental results show that TSP-PRL achieves competitive performance over existing state-of-the-art methods.

We focus on Unsupervised Domain Adaptation (UDA) for the task of semantic segmentation. Recently, adversarial alignment has been widely adopted to match the marginal distribution of feature representations across two domains globally. However, this strategy fails in adapting the representations of the tail classes or small objects for semantic segmentation since the alignment objective is dominated by head categories or large objects. In contrast to adversarial alignment, we propose to explicitly train a domain-invariant classifier by generating and defensing against pointwise feature space adversarial perturbations. Specifically, we firstly perturb the intermediate feature maps with several attack objectives (i.e., discriminator and classifier) on each individual position for both domains, and then the classifier is trained to be invariant to the perturbations. By perturbing each position individually, our model treats each location evenly regardless of the category or object size and thus circumvents the aforementioned issue. Moreover, the domain gap in feature space is reduced by extrapolating source and target perturbed features towards each other with attack on the domain discriminator. Our approach achieves the state-of-the-art performance on two challenging domain adaptation tasks for semantic segmentation: GTA5 → Cityscapes and SYNTHIA → Cityscapes.

Referring image segmentation aims at segmenting the foreground masks of the entities that can well match the description given in the natural language expression. Previous approaches tackle this problem using implicit feature interaction and fusion between visual and linguistic modalities, but usually fail to explore informative words of the expression to well align features from the two modalities for accurately identifying the referred entity. In this paper, we propose a Cross-Modal Progressive Comprehension (CMPC) module and a Text-Guided Feature Exchange (TGFE) module to effectively address the challenging task. Concretely, the CMPC module first employs entity and attribute words to perceive all the related entities that might be considered by the expression. Then, the relational words are adopted to highlight the correct entity as well as suppress other irrelevant ones by multimodal graph reasoning. In addition to the CMPC module, we further leverage a simple yet effective TGFE module to integrate the reasoned multimodal features from different levels with the guidance of textual information. In this way, features from multi-levels could communicate with each other and be refined based on the textual context. We conduct extensive experiments on four popular referring segmentation benchmarks and achieve new state-of-the-art performances. Code is available at https://github.com/spyflying/CMPC-Refseg.

Referring expression comprehension aims to localize the object instance described by a natural language expression. Current referring expression methods have achieved good performance. However, none of them is able to achieve real-time inference without accuracy drop. The reason for the relatively slow inference speed is that these methods artificially split the referring expression comprehension into two sequential stages including proposal generation and proposal ranking. It does not exactly conform to the habit of human cognition. To this end, we propose a novel Realtime Cross-modality Correlation Filtering method (RCCF). RCCF reformulates the referring expression comprehension as a correlation filtering process. The expression is first mapped from the language domain to the visual domain and then treated as a template (kernel) to perform correlation filtering on the image feature map. The peak value in the correlation heatmap indicates the center points of the target box. In addition, RCCF also regresses a 2-D object size and 2-D offset. The center point coordinates, object size and center point offset together to form the target bounding box. Our method runs at 40 FPS while achieving leading performance in RefClef, RefCOCO, RefCOCO+ and RefCOCOg benchmarks. In the challenging RefClef dataset, our methods almost double the state-of-the-art performance (34.70% increased to 63.79%). We hope this work can arouse more attention and studies to the new cross-modality correlation filtering framework as well as the one-stage framework for referring expression comprehension.

Grounding referring expressions aims to locate in an image an object referred to by a natural language expression. The linguistic structure of a referring expression provides a layout of reasoning over the visual contents, and it is often crucial to align and jointly understand the image and the referring expression. In this paper, we propose a scene graph guided modular network (SGMN), which performs reasoning over a semantic graph and a scene graph with neural modules under the guidance of the linguistic structure of the expression. In particular, we model the image as a structured semantic graph, and parse the expression into a language scene graph. The language scene graph not only decodes the linguistic structure of the expression, but also has a consistent representation with the image semantic graph. In addition to exploring structured solutions to grounding referring expressions, we also propose Ref-Reasoning, a large-scale real-world dataset for structured referring expression reasoning. We automatically generate referring expressions over the scene graphs of images using diverse expression templates and functional programs. This dataset is equipped with real-world visual contents as well as semantically rich expressions with different reasoning layouts. Experimental results show that our SGMN not only significantly outperforms existing state-of-the-art algorithms on the new Ref-Reasoning dataset, but also surpasses state-of-the-art structured methods on commonly used benchmark datasets. It can also provide interpretable visual evidences of reasoning.

Neural network pruning is widely applied to various mobile applications. Previous pruning methods mainly leverage ad-hoc criteria to evaluate channel importance. In this paper, we propose an effective metaheuristic sub-structure selection (MetaSelection) method for neural network pruning. MetaSelection exploits evolutionary algorithm (EA) to search the proper sub-structure satisfying the resource constraints. In comparison with previous AutoML based methods, MetaSelection can automatically achieve the pruning rate and channel selection at the same time instead of hand-crafted criteria in a cascaded way. Regarding the tremendous search space of channel selection as a combinatorial optimization problem, we further utilize a coarse-to-fine strategy and the novel probability distribution crossover (PDC) to speed up the search procedure. Besides, MetaSelection prunes the network globally rather than in a layer-by-layer way. We evaluate MetaSelection on several appealing deep neural networks, achieving superior results with adaptive depth and width. Concretely, on ImageNet, MetaSelection achieves a top-1 accuracy of 71.5% on MobileNetV2 under 70% FLOPs constraint and a FLOPs reduction of 30% with 76.4% top-1 accuracy for ResNet50.

Temporal grounding of natural language in untrimmed videos is a fundamental yet challenging multimedia task facilitating cross-media visual content retrieval. We focus on the weakly supervised setting of this task that merely accesses to coarse video-level language description annotation without temporal boundary, which is more consistent with reality as such weak labels are more readily available in practice. In this paper, we propose a Boundary Adaptive Refinement (BAR) framework that resorts to reinforcement learning (RL) to guide the process of progressively refining the temporal boundary. To the best of our knowledge, we offer the first attempt to extend RL to temporal localization task with weak supervision. As it is non-trivial to obtain a straightforward reward function in the absence of pairwise granular boundary-query annotations, a cross-modal alignment evaluator is crafted to measure the alignment degree of segment-query pair to provide tailor-designed rewards. This refinement scheme completely abandons traditional sliding window based solution pattern and contributes to acquiring more efficient, boundary-flexible and content-aware grounding results. Extensive experiments on two public benchmarks Charades-STA and ActivityNet demonstrate that BAR outperforms the state-of-the-art weakly-supervised method and even beats some competitive fully-supervised ones.

Crowd counting is an application-oriented task and its inference efficiency is crucial for real-world applications. However, most previous works relied on heavy backbone networks and required prohibitive run-time consumption, which would seriously restrict their deployment scopes and cause poor scalability. To liberate these crowd counting models, we propose a novel Structured Knowledge Transfer (SKT) framework, which fully exploits the structured knowledge of a well-trained teacher network to generate a lightweight but still highly effective student network. Specifically, it is integrated with two complementary transfer modules, including an Intra-Layer Pattern Transfer which sequentially distills the knowledge embedded in layer-wise features of the teacher network to guide feature learning of the student network and an Inter-Layer Relation Transfer which densely distills the cross-layer correlation knowledge of the teacher to regularize the student's feature evolution. Consequently, our student network can derive the layer-wise and cross-layer knowledge from the teacher network to learn compact yet effective features. Extensive evaluations on three benchmarks well demonstrate the effectiveness of our SKT for extensive crowd counting models. In particular, only using around $6%$ of the parameters and computation cost of original models, our distilled VGG-based models obtain at least 6.5× speed-up on an Nvidia 1080 GPU and even achieve state-of-the-art performance. Our code and models are available at https://github.com/HCPLab-SYSU/SKT.

Anomaly detection in the city scenario is a fundamental computer vision task and plays a critical role in city management and public safety. Although it has attracted intense attention in recent years, it remains a very challenging problem due to the complexity of the city environment, the serious imbalance between normal and abnormal samples, and the ambiguity of the concept of abnormal behavior. In this paper, we propose a modularized framework to perform general and specific anomaly detection. A video segment extraction module is first employed to obtain the candidate video segments. Then an anomaly classification network is introduced to predict the abnormal score for each category. A category-sensitive abnormal filter is concatenated after the classification model to filter the abnormal event from the candidate video clips. It is helpful to alleviate the impact of the imbalance of abnormal categories in the test phase and obtain more accurate localization results. The experimental results reveal that our framework obtains a 66.41 MF1 in the test set of the CitySCENE Challenge 2020, which ranks first in the specific anomaly detection task.

Face hallucination is a domain-specific super-resolution problem that aims to generate a high-resolution (HR) face image from a low-resolution (LR) input. In contrast to the existing patch-wise super-resolution models that divide a face image into regular patches and independently apply LR to HR mapping to each patch, we implement deep reinforcement learning and develop a novel attention-aware face hallucination (Attention-FH) framework, which recurrently learns to attend a sequence of patches and performs facial part enhancement by fully exploiting the global interdependency of the image. Specifically, our proposed framework incorporates two components: a recurrent policy network for dynamically specifying a new attended region at each time step based on the status of the super-resolved image and the past attended region sequence, and a local enhancement network for selected patch hallucination and global state updating. The Attention-FH model jointly learns the recurrent policy network and local enhancement network through maximizing a long-term reward that reflects the hallucination result with respect to the whole HR image. Extensive experiments demonstrate that our Attention-FH significantly outperforms the state-of-the-art methods on in-the-wild face images with large pose and illumination variations.

Recently, salient object detection has witnessed remarkable improvement owing to the deep convolutional neural networks which can harvest powerful features for images. In particular, the state-of-the-art salient object detection methods enjoy high accuracy and efficiency from fully convolutional network (FCN)-based frameworks which are trained from end to end and predict pixel-wise labels. However, such framework suffers from adversarial attacks which confuse neural networks via adding quasi-imperceptible noises to input images without changing the ground truth annotated by human subjects. To our knowledge, this paper is the first one that mounts successful adversarial attacks on salient object detection models and verifies that adversarial samples are effective on a wide range of existing methods. Furthermore, this paper proposes a novel end-to-end trainable framework to enhance the robustness for arbitrary FCN-based salient object detection models against adversarial attacks. The proposed framework adopts a novel idea that first introduces some new generic noise to destroy adversarial perturbations, and then learns to predict saliency maps for input images with the introduced noise. Specifically, our proposed method consists of a segment-wise shielding component, which preserves boundaries and destroys delicate adversarial noise patterns and a context-aware restoration component, which refines saliency maps through global contrast modeling. The experimental results suggest that our proposed framework improves the performance significantly for state-of-the-art models on a series of datasets.

As a domain-specific super-resolution problem, facial image hallucination has enjoyed a series of breakthroughs thanks to the advances of deep convolutional neural networks. However, the direct migration of existing methods to video is still difficult to achieve good performance due to its lack of alignment and consistency modelling in temporal domain. Taking advantage of high inter-frame dependency in videos, we propose a selfenhanced convolutional network for facial video hallucination. It is implemented by making full usage of preceding super-resolved frames and a temporal window of adjacent low-resolution frames. Specifically, the algorithm first obtains the initial high-resolution inference of each frame by taking into consideration a sequence of consecutive low-resolution inputs through temporal consistency modelling. It further recurrently exploits the reconstructed results and intermediate features of a sequence of preceding frames to improve the initial super-resolution of the current frame by modelling the coherence of structural facial features across frames. Quantitative and qualitative evaluations demonstrate the superiority of the proposed algorithm against state-of-theart methods. Moreover, our algorithm also achieves excellent performance in the task of general video super-resolution in a single-shot setting.

The field of computer vision has witnessed phenomenal progress in recent years partially due to the development of deep convolutional neural networks. However, deep learning models are notoriously sensitive to adversarial examples which are synthesized by adding quasi-perceptible noises on real images. Some existing defense methods require to re-train attacked target networks and augment the train set via known adversarial attacks, which is inefficient and might be unpromising with unknown attack types. To overcome the above issues, we propose a portable defense method, online alternate generator, which does not need to access or modify the parameters of the target networks. The proposed method works by online synthesizing another image from scratch for an input image, instead of removing or destroying adversarial noises. To avoid pretrained parameters exploited by attackers, we alternately update the generator and the synthesized image at the inference stage. Experimental results demonstrate that the proposed defensive scheme and method outperforms a series of state-of-the-art defending models against gray-box adversarial attacks.

Recent progress in biomedical image segmentation based on deep convolutional neural networks (CNNs) has drawn much attention. However, its vulnerability towards adversarial samples cannot be overlooked. This paper is the first one that discovers that all the CNN-based state-of-the-art biomedical image segmentation models are sensitive to adversarial perturbations. This limits the deployment of these methods in safety-critical biomedical fields. In this paper, we discover that global spatial dependencies and global contextual information in a biomedical image can be exploited to defend against adversarial attacks. To this end, non-local context encoder (NLCE) is proposed to model short- and long-range spatial dependencies and encode global contexts for strengthening feature activations by channel-wise attention. The NLCE modules enhance the robustness and accuracy of the non-local context encoding network (NLCEN), which learns robust enhanced pyramid feature representations with NLCE modules, and then integrates the information across different levels. Experiments on both lung and skin lesion segmentation datasets have demonstrated that NLCEN outperforms any other state-of-the-art biomedical image segmentation methods against adversarial attacks. In addition, NLCE modules can be applied to improve the robustness of other CNN-based biomedical image segmentation methods.

Facial action unit (AU) recognition is a crucial task for facial expressions analysis and has attracted extensive attention in the field of artificial intelligence and computer vision. Existing works have either focused on designing or learning complex regional feature representations, or delved into various types of AU relationship modeling. Albeit with varying degrees of progress, it is still arduous for existing methods to handle complex situations. In this paper, we investigate how to integrate the semantic relationship propagation between AUs in a deep neural network framework to enhance the feature representation of facial regions, and propose an AU semantic relationship embedded representation learning (SRERL) framework. Specifically, by analyzing the symbiosis and mutual exclusion of AUs in various facial expressions, we organize the facial AUs in the form of structured knowledge-graph and integrate a Gated Graph Neural Network (GGNN) in a multi-scale CNN framework to propagate node information through the graph for generating enhanced AU representation. As the learned feature involves both the appearance characteristics and the AU relationship reasoning, the proposed model is more robust and can cope with more challenging cases, e.g., illumination change and partial occlusion. Extensive experiments on the two public benchmarks demonstrate that our method outperforms the previous work and achieves state of the art performance.

To force convolutional networks to explore more discriminative evidence throughout spatial regions, this paper presents a novel CamDrop to improve the conventional dropout in two aspects. First, by considering the intensity of class activation mapping (CAM) all around, CamDrop selectively abandons some specific spatial regions in predominating visual patterns at each iteration. In many classification tasks, CamDrop demonstrates its effectiveness and achieves considerable improvements on robust predictions for adversarial examples. Second, although dropout is a widely adopted technique that has been applied to regularize large models, the improvement in performance always attributes to better preventing DNN from overfitting. Here we give a new explanation of dropout from the perspective of optimization that it makes the upper bound of the magnitude of gradients much tighter, which leads to a more stable behavior of the gradients and effectively avoids neurons falling into the saturation region of the nonlinear activation, even when using high learning rates. Extensive experiments have been performed to prove the above two strengths of CamDrop.

Current neural networks for 3D object recognition are vulnerable to 3D rotation. Existing works mostly rely on massive amounts of rotation-augmented data to alleviate the problem, which lacks solid guarantee of the 3D rotation invariance. In this paper, we address the issue by introducing a novel point cloud representation that can be mathematically proved rigorously rotation-invariant, i.e., identical point clouds in different orientations are unified as a unique and consistent representation. Moreover, the proposed representation is conditional information-lossless, because it retains all necessary information of point cloud except for orientation information. In addition, the proposed representation is complementary with existing network architectures for point cloud and fundamentally improves their robustness against rotation transformation. Finally, we propose a deep hierarchical cluster network called ClusterNet to better adapt to the proposed representation. We employ hierarchical clustering to explore and exploit the geometric structure of point cloud, which is embedded in a hierarchical structure tree. Extensive experimental results have shown that our proposed method greatly outperforms the state-of-the-arts in rotation robustness on rotation-augmented 3D object classification benchmarks.

Grounding referring expressions is a fundamental yet challenging task facilitating human-machine communication in the physical world. It locates the target object in an image on the basis of the comprehension of the relationships between referring natural language expressions and the image. A feasible solution for grounding referring expressions not only needs to extract all the necessary information (i.e. objects and the relationships among them) in both the image and referring expressions, but also compute and represent multimodal contexts from the extracted information. Unfortunately, existing work on grounding referring expressions cannot extract multi-order relationships from the referring expressions accurately and the contexts they obtain have discrepancies with the contexts described by referring expressions. In this paper, we propose a Cross-Modal Relationship Extractor (CMRE) to adaptively highlight objects and relationships, that have connections with a given expression, with a cross-modal attention mechanism, and represent the extracted information as a language-guided visual relation graph. In addition, we propose a Gated Graph Convolutional Network (GGCN) to compute multimodal semantic contexts by fusing information from different modes and propagating multimodal information in the structured relation graph. Experiments on various common benchmark datasets show that our Cross-Modal Relationship Inference Network, which consists of CMRE and GGCN, outperforms all existing state-of-the-art methods.

We present a new data-driven method for robust skin detection from a single human portrait image. Unlike previous methods, we incorporate human body as a weak semantic guidance into this task, considering acquiring large-scale of human labeled skin data is commonly expensive and time-consuming. To be specific, we propose a dual-task neural network for joint detection of skin and body via a semi-supervised learning strategy. The dual-task network contains a shared encoder but two decoders for skin and body separately. For each decoder, its output also serves as a guidance for its counterpart, making both decoders mutually guided. Extensive experiments were conducted to demonstrate the effectiveness of our network with mutual guidance, and experimental results show our network outperforms the state-of-the-art in skin detection.

Matching clothing images from customers and online shopping stores has rich applications in E-commerce. Existing algorithms encoded an image as a global feature vector and performed retrieval with the global representation. However, discriminative local information on clothes are submerged in this global representation, resulting in sub-optimal performance. To address this issue, we propose a novel Graph Reasoning Network (GRNet) on a Similarity Pyramid, which learns similarities between a query and a gallery cloth by using both global and local representations in multiple scales. The similarity pyramid is represented by a Graph of similarity, where nodes represent similarities between clothing components at different scales, and the final matching score is obtained by message passing along edges. In GRNet, graph reasoning is solved by training a graph convolutional network, enabling to align salient clothing components to improve clothing retrieval. To facilitate future researches, we introduce a new benchmark FindFashion, containing rich annotations of bounding boxes, views, occlusions, and cropping. Extensive experiments show that GRNet obtains new state-of-the-art results on two challenging benchmarks, e.g. pushing the top-1, top-20, and top-50 accuracies on DeepFashion to 26%, 64%, and 75% (i.e. 4%, 10%, and 10% absolute improvements), outperforming competitors with large margins. On FindFashion, GRNet achieves considerable improvements on all empirical settings.

Video salient object detection aims at discovering the most visually distinctive objects in a video. How to effectively take object motion into consideration during video salient object detection is a critical issue. Existing state-of-the-art methods either do not explicitly model and harvest motion cues or ignore spatial contexts within optical flow images. In this paper, we develop a multi-task motion guided video salient object detection network, which learns to accomplish two sub-tasks using two sub-networks, one sub-network for salient object detection in still images and the other for motion saliency detection in optical flow images. We further introduce a series of novel motion guided attention modules, which utilize the motion saliency sub-network to attend and enhance the sub-network for still images. These two sub-networks learn to adapt to each other by end-to-end training. Experimental results demonstrate that the proposed method significantly outperforms existing state-of-the-art algorithms on a wide range of benchmarks. We hope our simple and effective approach will serve as a solid baseline and help ease future research in video salient object detection. Code and models will be made available.

Automatic estimation of the number of people in unconstrained crowded scenes is a challenging task and one major difficulty stems from the huge scale variation of people. In this paper, we propose a novel Deep Structured Scale Integration Network (DSSINet) for crowd counting, which addresses the scale variation of people by using structured feature representation learning and hierarchically structured loss function optimization. Unlike conventional methods which directly fuse multiple features with weighted average or concatenation, we first introduce a Structured Feature Enhancement Module based on conditional random fields (CRFs) to refine multiscale features mutually with a message passing mechanism. Specifically, each scale-specific feature is considered as a continuous random variable and passes complementary information to refine the features at other scales. Second, we utilize a Dilated Multiscale Structural Similarity loss to enforce our DSSINet to learn the local correlation of people's scales within regions of various size, thus yielding high-quality density maps. Extensive experiments on four challenging benchmarks well demonstrate the effectiveness of our method. In particular, our DSSINet achieves improvements of 9.5% error reduction on Shanghaitech dataset and 24.9% on UCF-QNRF dataset against the state-of-the-art methods.

Domain adaptation enables the learner to safely generalize into novel environments by mitigating domain shifts across distributions. Previous works may not effectively uncover the underlying reasons that would lead to the drastic model degradation on the target task. In this paper, we empirically reveal that the erratic discrimination of the target domain mainly stems from its much smaller feature norms with respect to that of the source domain. To this end, we propose a novel parameter-free Adaptive Feature Norm approach. We demonstrate that progressively adapting the feature norms of the two domains to a large range of values can result in significant transfer gains, implying that those task-specific features with larger norms are more transferable. Our method successfully unifies the computation of both standard and partial domain adaptation with more robustness against the negative transfer issue. Without bells and whistles but a few lines of code, our method substantially lifts the performance on the target task and exceeds state-of-the-arts by a large margin (11.5% on Office-Home and 17.1% on VisDA2017). We hope our simple yet effective approach will shed some light on the future research of transfer learning. Code is available at https://github.com/jihanyang/AFN.

Deep learning-based video salient object detection has recently achieved great success with its performance significantly outperforming any other unsupervised methods. However, existing data-driven approaches heavily rely on a large quantity of pixel-wise annotated video frames to deliver such promising results. In this paper, we address the semi-supervised video salient object detection task using pseudo-labels. Specifically, we present an effective video saliency detector that consists of a spatial refinement network and a spatiotemporal module. Based on the same refinement network and motion information in terms of optical flow, we further propose a novel method for generating pixel-level pseudo-labels from sparsely annotated frames. By utilizing the generated pseudo-labels together with a part of manual annotations, our video saliency detector learns spatial and temporal cues for both contrast inference and coherence enhancement, thus producing accurate saliency maps. Experimental results demonstrate that our proposed semi-supervised method even greatly outperforms all the state-of-the-art fully supervised methods across three public benchmarks of VOS, DAVIS, and FBMS.

Referring expression comprehension aims to locate the object instance described by a natural language referring expression in an image. This task is compositional and inherently requires visual reasoning on top of the relationships among the objects in the image. Meanwhile, the visual reasoning process is guided by the linguistic structure of the referring expression. However, existing approaches treat the objects in isolation or only explore the first-order relationships between objects without being aligned with the potential complexity of the expression. Thus it is hard for them to adapt to the grounding of complex referring expressions. In this paper, we explore the problem of referring expression comprehension from the perspective of language-driven visual reasoning, and propose a dynamic graph attention network to perform multi-step reasoning by modeling both the relationships among the objects in the image and the linguistic structure of the expression. In particular, we construct a graph for the image with the nodes and edges corresponding to the objects and their relationships respectively, propose a differential analyzer to predict a language-guided visual reasoning process, and perform stepwise reasoning on top of the graph to update the compound object representation at every node. Experimental results demonstrate that the proposed method can not only significantly surpass all existing state-of-the-art algorithms across three common benchmark datasets, but also generate interpretable visual evidences for stepwise locating the objects referred to in complex language descriptions.

Taxi demand prediction has recently attracted increasing research interest due to its huge potential application in large-scale intelligent transportation systems. However, most of the previous methods only considered the taxi demand prediction in origin regions, while ignoring the modeling of the specific situation of the destination passengers. In this paper, we present a more challenging task, called taxi origin-destination demand prediction, which aims at predicting the taxi demand between all origin-destination (OD) pairs in a future time interval. Its main challenges lie in how to effectively capture the diverse contextual information to learn the demand patterns. We address this problem with a novel Contextualized Spatial-Temporal Network (CSTN), which can effectively capture various context of taxi demand into a unified framework. Specifically, the proposed network consists of three components for the modeling of local spatial context (LSC), temporal evolution context (TEC) and global correlation context (GCC) respectively. Extensive experiments and evaluations on a large-scale dataset well demonstrate the significant superiority of our CSTN over other compared methods of taxi origin-destination demand prediction.

Crowd counting, aiming at estimating the total number of people in unconstrained crowded scenes, has increasingly received attention. But it is greatly challenged by the huge variation in people scale. In this paper, we propose a novel Multi-View Scale Aggregation Network (MVSAN), which handle the scale variation from feature, input and criterion view comprehensively. Firstly, we design a simple but effective Multi-Scale Feature Encoder, which exploits dilated convolution layers with various dilation rates to improve the representation ability and scale diversity of features. Secondly, we feed multiple scales of input images into networks to generate high-quality density maps in a coarse-to-fine manner. Finally, we propose a Multi-Scale Structural Similarity loss to force our networks to learn the local correlation of density maps. Extensive experiments on two standard benchmarks show that the proposed method can generate high-quality crowd density map and accurate count estimation, outperforming the state-of-the-art methods with a large margin.

A broad range of cross-$m$-domain generation researches boil down to matching a joint distribution by deep generative models (DGMs). Hitherto algorithms excel in pairwise domains while as $m$ increases, remain struggling to scale themselves to fit a joint distribution. In this paper, we propose a domain-scalable DGM, i.e., MMI-ALI for $m$-domain joint distribution matching. As an $m$-domain ensemble model of ALIs (Dumoulin et al., 2016), MMI-ALI is adversarially trained with maximizing Multivariate Mutual Information (MMI) w.r.t. joint variables of each pair of domains and their shared feature. The negative MMIs are upper bounded by a series of feasible losses provably leading to matching $m$-domain joint distributions. MMI-ALI linearly scales as $m$ increases and thus, strikes a right balance between efficacy and scalability. We evaluate MMI-ALI in diverse challenging $m$-domain scenarios and verify its superiority.

Salient object detection, which aims at localizing the attention-aware visual objects, is the indispensable technology for intelligent robots to understand and interact with the complicated environments. Existing salient object detection approaches mainly focus on the optimization of detection performance, while ignoring the considerations for computational resource consumption and algorithm efficiency. Contrarily, we build a superior lightweight network architecture to simultaneously improve performance on both accuracy and efficiency for salient object detection. Specifically, our proposed approach adopts the lightweight bottleneck as its primary building block to significantly reduce the number of parameters and to speed up the process of training and inference. In practice, the visual contrast is insufficiently discovered with the limitation of the small empirical receptive field of CNN. To alleviate this issue, we design a multi-scale convolution module to rapidly discover high-level visual contrast. Moreover, a lightweight refinement module is utilized to restore object saliency details with negligible extra cost. Extensive experiments on efficiency and accuracy trade-offs show that our model is more competitive than the state-of-the-art works on salient object detection task and has prominent potentials for robots applications in real time.

In recent times, image inpainting has witnessed rapid progress due to the generative adversarial networks (GANs) that are able to synthesize realistic contents. However, most existing GAN-based methods for semantic inpainting apply an auto-encoder architecture with a fully connected layer, which cannot accurately maintain spatial information. In addition, the discriminator in existing GANs struggles to comprehend high-level semantics within the image context and yields semantically consistent content. Existing evaluation criteria are biased toward blurry results and cannot well characterize edge preservation and visual authenticity in the inpainting results. In this paper, we propose an improved GAN to overcome the aforementioned limitations. Our proposed GAN-based framework consists of a fully convolutional design for the generator which helps to better preserve spatial structures and a joint loss function with a revised perceptual loss to capture high-level semantics in the context. Furthermore, we also introduce two novel measures to better assess the quality of image inpainting results. The experimental results demonstrate that our method outperforms the state-of-the-art under a wide range of criteria.

Recognizing objects from simultaneously sensed photometric (RGB) and depth channels is a fundamental yet practical problem in many machine vision applications, such as robot grasping and autonomous driving. In this paper, we address this problem by developing a cross-modal attentional context (CMAC) learning framework, which enables the full exploitation of the context information from both RGB and depth data. Compared to existing RGB-D object detection frameworks, our approach has several appealing properties. First, it consists of an attention-based global context model for exploiting adaptive contextual information and incorporating this information into a region-based CNN (e.g., fast RCNN) framework to achieve improved object detection performance. Second, our CMAC framework further contains a fine-grained object part attention module to harness multiple discriminative object parts inside each possible object region for superior local feature representation. While greatly improving the accuracy of RGB-D object detection, the effective cross-modal information fusion as well as attentional context modeling in our proposed model provide an interpretable visualization scheme. Experimental results demonstrate that the proposed method significantly improves upon the state of the art on all public benchmarks.

Taxi demand prediction has recently attracted increasing research interest due to its huge potential application in large-scale intelligent transportation systems. However, most of the previous methods only considered the taxi demand prediction in origin regions, but neglected the modeling of the specific situation of the destination passengers. We believe it is suboptimal to preallocate the taxi into each region-based solely on the taxi origin demand. In this paper, we present a challenging and worth-exploring task, called taxi origin-destination demand prediction, which aims at predicting the taxi demand between all-region pairs in a future time interval. Its main challenges come from how to effectively capture the diverse contextual information to learn the demand patterns. We address this problem with a novel contextualized spatial-temporal network (CSTN), which consists of three components for the modeling of local spatial context (LSC), temporal evolution context (TEC), and global correlation context (GCC), respectively. First, an LSC module utilizes two convolution neural networks to learn the local spatial dependencies of taxi, demand respectively, from the origin view and the destination view. Second, a TEC module incorporates the local spatial features of taxi demand and the meteorological information to a Convolutional Long Short-term Memory Network (ConvLSTM) for the analysis of taxi demand evolution. Finally, a GCC module is applied to model the correlation between all regions by computing a global correlation feature as a weighted sum of all regional features, with the weights being calculated as the similarity between the corresponding region pairs. The extensive experiments and evaluations on a large-scale dataset well demonstrate the superiority of our CSTN over other compared methods for the taxi origin-destination demand prediction.

Facial landmark localization plays a critical role in face recognition and analysis. In this paper, we propose a novel cascaded backbone-branches fully convolutional neural network (BB-FCN) for rapidly and accurately localizing facial landmarks in unconstrained and cluttered settings. Our proposed BB-FCN generates facial landmark response maps directly from raw images without any preprocessing. BB-FCN follows a coarse-to-fine cascaded pipeline, which consists of a backbone network to roughly detect the locations of all facial landmarks and one branch network for each type of detected landmark to further refine its location. Furthermore, to facilitate the facial landmark localization under unconstrained settings, we propose a large-scale benchmark named SYSU16K, which contains 16 000 faces with large variations in pose, expression, illumination, and resolution. Extensive experimental evaluations demonstrate that our proposed BB-FCN can significantly outperform the state of the art under both constrained (i.e., within detected facial regions only) and unconstrained settings. We further confirm that high-quality facial landmarks localized with our proposed network can also improve the precision and recall of face detection.

The collection of internet images has been growing in an astonishing speed. It is undoubted that these images contain rich visual information that can be useful in many applications, such as visual media creation and data-driven image synthesis. In this article, we focus on the methodologies for building a visual object database from a collection of internet images. Such database is built to contain a large number of high-quality visual objects that can help with various data-driven image applications. Our method is based on dense proposal generation and objectness-based re-ranking. A novel deep convolutional neural network is designed for the inference of proposal objectness , the probability of a proposal containing optimally located foreground object. In our work, the objectness is quantitatively measured in regard of completeness and fullness , reflecting two complementary features of an optimal proposal: a complete foreground and relatively small background. Our experiments indicate that object proposals re-ranked according to the output of our network generally achieve higher performance than those produced by other state-of-the-art methods. As a concrete example, a database of over 1.2 million visual objects has been built using the proposed method, and has been successfully used in various data-driven image applications.

Recognizing multiple labels of images is a fundamental but challenging task in computer vision, and remarkable progress has been attained by localizing semantic-aware image regions and predicting their labels with deep convolutional neural networks. The step of hypothesis regions (region proposals) localization in these existing multi-label image recognition pipelines, however, usually takes redundant computation cost, e.g., generating hundreds of meaningless proposals with non-discriminative information and extracting their features, and the spatial contextual dependency modeling among the localized regions are often ignored or over-simplified. To resolve these issues, this paper proposes a recurrent attention reinforcement learning framework to iteratively discover a sequence of attentional and informative regions that are related to different semantic objects and further predict label scores conditioned on these regions. Besides, our method explicitly models long-term dependencies among these attentional regions that help to capture semantic label co-occurrence and thus facilitate multi-label recognition. Extensive experiments and comparisons on two large-scale benchmarks (i.e., PASCAL VOC and MS-COCO) show that our model achieves superior performance over existing state-of-the-art methods in both performance and efficiency as well as explicitly identifying image-level semantic labels to specific object regions.

Deep learning based salient object detection has recently achieved great success with its performance greatly outperforms any other unsupervised methods. However, annotating per-pixel saliency masks is a tedious and inefficient procedure. In this paper, we note that superior salient object detection can be obtained by iteratively mining and correcting the labeling ambiguity on saliency maps from traditional unsupervised methods. We propose to use the combination of a coarse salient object activation map from the classification network and saliency maps generated from unsupervised methods as pixel-level annotation, and develop a simple yet very effective algorithm to train fully convolutional networks for salient object detection supervised by these noisy annotations. Our algorithm is based on alternately exploiting a graphical model and training a fully convolutional network for model updating. The graphical model corrects the internal labeling ambiguity through spatial consistency and structure preserving while the fully convolutional network helps to correct the cross-image semantic ambiguity and simultaneously update the coarse activation map for next iteration. Experimental results demonstrate that our proposed method greatly outperforms all state-of-the-art unsupervised saliency detection methods and can be comparable to the current best strongly-supervised methods training with thousands of pixel-level saliency map annotations on all public benchmarks.

The collaborative reasoning for understanding each image-question pair is very critical but under-explored for an interpretable Visual Question Answering (VQA) system. Although very recent works also tried the explicit compositional processes to assemble multiple sub-tasks embedded in the questions, their models heavily rely on the annotations or hand-crafted rules to obtain valid reasoning layout, leading to either heavy labor or poor performance on composition reasoning. In this paper, to enable global context reasoning for better aligning image and language domains in diverse and unrestricted cases, we propose a novel reasoning network called Adversarial Composition Modular Network (ACMN). This network comprises of two collaborative modules: i) an adversarial attention module to exploit the local visual evidence for each word parsed from the question; ii) a residual composition module to compose the previously mined evidence. Given a dependency parse tree for each question, the adversarial attention module progressively discovers salient regions of one word by densely combining regions of child word nodes in an adversarial manner. Then residual composition module merges the hidden representations of an arbitrary number of children through sum pooling and residual connection. Our ACMN is thus capable of building an interpretable VQA system that gradually dives the image cues following a question-driven reasoning route and makes global reasoning by incorporating the learned knowledge of all attention modules in a principled manner. Experiments on relational datasets demonstrate the superiority of our ACMN and visualization results show the explainable capability of our reasoning system.

Image saliency detection has recently witnessed significant progress due to deep convolutional neural networks. However, extending state-of-the-art saliency detectors from image to video is challenging. The performance of salient object detection suffers from object or camera motion and the dramatic change of the appearance contrast in videos. In this paper, we present flow guided recurrent neural encoder (FGRNE), an accurate and end-to-end learning framework for video salient object detection. It works by enhancing the temporal coherence of the per-frame feature by exploiting both motion information in terms of optical flow and sequential feature evolution encoding in terms of LSTM networks. It can be considered as a universal framework to extend any FCN based static saliency detector to video salient object detection. Intensive experimental results verify the effectiveness of each part of FGRNE and confirm that our proposed method significantly outperforms state-of-the-art methods on the public benchmarks of DAVIS and FBMS.

Automatically describing open-domain videos with natural language are attracting increasing interest in the field of artificial intelligence. Most existing methods simply borrow ideas from image captioning and obtain a compact video representation from an ensemble of global image feature before feeding to an RNN decoder which outputs a sentence of variable length. However, it is not only arduous for the generator to focus on specific salient objects at different time given the global video representation, it is more formidable to capture the fine-grained motion information and the relation between moving instances for more subtle linguistic descriptions. In this paper, we propose a Trajectory Structured Attentional Encoder-Decoder (TSA-ED) neural network framework for more elaborate video captioning which works by integrating local spatial-temporal representation at trajectory level through structured attention mechanism. Our proposed method is based on a LSTM-based encoder-decoder framework, which incorporates an attention modeling scheme to adaptively learn the correlation between sentence structure and the moving objects in videos, and consequently generates more accurate and meticulous statement description in the decoding stage. Experimental results demonstrate that the feature representation and structured attention mechanism based on the trajectory cluster can efficiently obtain the local motion information in the video to help generate a more fine-grained video description, and achieve the state-of-the-art performance on the well-known Charades and MSVD datasets.

Crowd counting from unconstrained scene images is a crucial task in many real-world applications like urban surveillance and management, but it is greatly challenged by the camera’s perspective that causes huge appearance variations in people’s scales and rotations. Conventional methods address such challenges by resorting to fixed multi-scale architectures that are often unable to cover the largely varied scales while ignoring the rotation variations. In this paper, we propose a unified neural network framework, named Deep Recurrent Spatial-Aware Network, which adaptively addresses the two issues in a learnable spatial transform module with a region-wise refinement process. Specifically, our framework incorporates a Recurrent Spatial-Aware Refinement (RSAR) module iteratively conducting two components: i) a Spatial Transformer Network that dynamically locates an attentional region from the crowd density map and transforms it to the suitable scale and rotation for optimal crowd estimation; ii) a Local Refinement Network that refines the density map of the attended region with residual learning. Extensive experiments on four challenging benchmarks show the effectiveness of our approach. Specifically, comparing with the existing best-performing methods, we achieve an improvement of 12\% on the largest dataset WorldExpo’10 and 22.8\% on the most challenging dataset UCF\_CC\_50

Single image rain streaks removal has recently witnessed substantial progress due to the development of deep convolutional neural networks. However, existing deep learning based methods either focus on the entrance and exit of the network by decomposing the input image into high and low frequency information and employing residual learning to reduce the mapping range, or focus on the introduction of cascaded learning scheme to decompose the task of rain streaks removal into multi-stages. These methods treat the convolutional neural network as an encapsulated end-to-end mapping module without deepening into the rationality and superiority of neural network design. In this paper, we delve into an effective end-to-end neural network structure for stronger feature expression and spatial correlation learning. Specifically, we propose a non-locally enhanced encoder-decoder network framework, which consists of a pooling indices embedded encoder-decoder network to efficiently learn increasingly abstract feature representation for more accurate rain streaks modeling while perfectly preserving the image detail. The proposed encoder-decoder framework is composed of a series of non-locally enhanced dense blocks that are designed to not only fully exploit hierarchical features from all the convolutional layers but also well capture the long-distance dependencies and structural information. Extensive experiments on synthetic and real datasets demonstrate that the proposed method can effectively remove rain-streaks on rainy image of various densities while well preserving the image details, which achieves significant improvements over the recent state-of-the-art methods.

Traffic flow prediction is crucial for urban traffic management and public safety. Its key challenges lie in how to adaptively integrate the various factors that affect the flow changes. In this paper, we propose a unified neural network module to address this problem, called Attentive Crowd Flow Machine~(ACFM), which is able to infer the evolution of the crowd flow by learning dynamic representations of temporally-varying data with an attention mechanism. Specifically, the ACFM is composed of two progressive ConvLSTM units connected with a convolutional layer for spatial weight prediction. The first LSTM takes the sequential flow density representation as input and generates a hidden state at each time-step for attention map inference, while the second LSTM aims at learning the effective spatial-temporal feature expression from attentionally weighted crowd flow features. Based on the ACFM, we further build a deep architecture with the application to citywide crowd flow prediction, which naturally incorporates the sequential and periodic data as well as other external influences. Extensive experiments on two standard benchmarks (i.e., crowd flow in Beijing and New York City) show that the proposed method achieves significant improvements over the state-of-the-art methods.

Deep convolutional neural networks (CNNs) have become a key element in the recent breakthrough of salient object detection. However, existing CNN-based methods are based on either patchwise (regionwise) training and inference or fully convolutional networks. Methods in the former category are generally time-consuming due to severe storage and computational redundancies among overlapping patches. To overcome this deficiency, methods in the second category attempt to directly map a raw input image to a predicted dense saliency map in a single network forward pass. Though being very efficient, it is arduous for these methods to detect salient objects of different scales or salient regions with weak semantic information. In this paper, we develop hybrid contrast-oriented deep neural networks to overcome the aforementioned limitations. Each of our deep networks is composed of two complementary components, including a fully convolutional stream for dense prediction and a segment-level spatial pooling stream for sparse saliency inference. We further propose an attentional module that learns weight maps for fusing the two saliency predictions from these two streams. A tailored alternate scheme is designed to train these deep networks by fine-tuning pretrained baseline models. Finally, a customized fully connected conditional random field model incorporating a salient contour feature embedding can be optionally applied as a postprocessing step to improve spatial coherence and contour positioning in the fused result from these two streams. Extensive experiments on six benchmark data sets demonstrate that our proposed model can significantly outperform the state of the art in terms of all popular evaluation metrics.

Face hallucination is a domain-specific super-resolution problem with the goal to generate high-resolution (HR) faces from low-resolution (LR) input images. In contrast to existing methods that often learn a single patch-to-patch mapping from LR to HR images and are regardless of the contextual interdependency between patches, we propose a novel Attention-aware Face Hallucination (Attention-FH) framework which resorts to deep reinforcement learning for sequentially discovering attended patches and then performing the facial part enhancement by fully exploiting the global interdependency of the image. Specifically, in each time step, the recurrent policy network is proposed to dynamically specify a new attended region by incorporating what happened in the past. The state (i.e., face hallucination result for the whole image) can thus be exploited and updated by the local enhancement network on the selected region. The Attention-FH approach jointly learns the recurrent policy network and local enhancement network through maximizing the long-term reward that reflects the hallucination performance over the whole image. Therefore, our proposed Attention-FH is capable of adaptively personalizing an optimal searching path for each face image according to its own characteristic. Extensive experiments show our approach significantly surpasses the state-of-the-arts on in-the-wild faces with large pose and illumination variations. The state (i.e., face hallucination result for the whole image) can thus be exploited and updated by the local enhancement network on the selected region. The Attention-FH approach jointly learns the recurrent policy network and local enhancement network through maximizing the long-term reward that reflects the hallucination performance over the whole image. Therefore, our proposed Attention-FH is capable of adaptively personalizing an optimal searching path for each face image according to its own characteristic. Extensive experiments show our approach significantly surpasses the state-of-the-arts on in-the-wild faces with large pose and illumination variations.

Image saliency detection has recently witnessed rapid progress due to deep convolutional neural networks. However, none of the existing methods is able to identify object instances in the detected salient regions. In this paper, we present a salient instance segmentation method that produces a saliency mask with distinct object instance labels for an input image. Our method consists of three steps, estimating saliency map, detecting salient object contours and identifying salient object instances. For the first two steps, we propose a multiscale saliency refinement network, which generates high-quality salient region masks and salient object contours. Once integrated with multiscale combinatorial grouping and a MAP-based subset optimization framework, our method can generate very promising salient object instance segmentation results. To promote further research and evaluation of salient instance segmentation, we also construct a new database of 1000 images and their pixelwise salient instance annotations. Experimental results demonstrate that our proposed method is capable of achieving state-of-the-art performance on all public benchmarks for salient region detection as well as on our new dataset for salient instance segmentation.

This paper proposes a novel deep architecture to address multi-label image recognition, a fundamental and practical task towards general visual understanding. Current solutions for this task usually rely on an extra step of extracting hypothesis regions (i.e., region proposals), resulting in redundant computation and sub-optimal performance. In this work, we achieve the interpretable and contextualized multi-label image classification by developing a recurrent memorized-attention module. This module consists of two alternately performed components: i) a spatial transformer layer to locate attentional regions from the convolutional feature maps in a region-proposal-free way and ii) an LSTM (Long-Short Term Memory) sub-network to sequentially predict semantic labeling scores on the located regions while capturing the global dependencies of these regions. The LSTM also output the parameters for computing the spatial transformer. On large-scale benchmarks of multi-label image classification (e.g., MS-COCO and PASCAL VOC 07), our approach demonstrates superior performances over other existing state-of-the-arts in both accuracy and efficiency.

Salient object detection has recently witnessed substantial progress due to powerful features extracted using deep convolutional neural networks (CNNs). However, existing CNN-based methods operate at the patch level instead of the pixel level. Resulting saliency maps are typically blurry, especially near the boundary of salient objects. Furthermore, image patches are treated as independent samples even when they are overlapping, giving rise to significant redundancy in computation and storage. In this paper, we propose an end-to-end deep contrast network to overcome the aforementioned limitations. Our deep network consists of two complementary components, a pixel-level fully convolutional stream and a segment-wise spatial pooling stream. The first stream directly produces a saliency map with pixel-level accuracy from an input image. The second stream extracts segment-wise features very efficiently, and better models saliency discontinuities along object boundaries. Finally, a fully connected CRF model can be optionally incorporated to improve spatial coherence and contour localization in the fused result from these two streams. Experimental results demonstrate that our deep model significantly improves the state of the art.

Visual saliency is a fundamental problem in both cognitive and computational sciences, including computer vision. In this paper, we discover that a high-quality visual saliency model can be learned from multiscale features extracted using deep convolutional neural networks (CNNs), which have had many successes in visual recognition tasks. For learning such saliency models, we introduce a neural network architecture, which has fully connected layers on top of CNNs responsible for feature extraction at three different scales. The penultimate layer of our neural network has been confirmed to be a discriminative high-level feature vector for saliency detection, which we call deep contrast feature. To generate a more robust feature, we integrate handcrafted low-level features with our deep contrast feature. To promote further research and evaluation of visual saliency models, we also construct a new large database of 4447 challenging images and their pixelwise saliency annotations. Experimental results demonstrate that our proposed method is capable of achieving the state-of-the-art performance on all public benchmarks, improving the F-measure by 6.12% and 10%, respectively, on the DUT-OMRON data set and our new data set (HKU-IS), and lowering the mean absolute error by 9% and 35.3%, respectively, on these two data sets.

Visual saliency is a fundamental problem in both cognitive and computational sciences, including computer vision. In this paper, we discover that a high-quality visual saliency model can be learned from multiscale features extracted using deep convolutional neural networks (CNNs), which have had many successes in visual recognition tasks. For learning such saliency models, we introduce a neural network architecture, which has fully connected layers on top of CNNs responsible for feature extraction at three different scales. We then propose a refinement method to enhance the spatial coherence of our saliency results. Finally, aggregating multiple saliency maps computed for different levels of image segmentation can further boost the performance, yielding saliency maps better than those generated from a single segmentation. To promote further research and evaluation of visual saliency models, we also construct a new large database of 4447 challenging images and their pixelwise saliency annotations. Experimental results demonstrate that our proposed method is capable of achieving state-of-the-art performance on all public benchmarks, improving the F-Measure by 5.0% and 13.2% respectively on the MSRA-B dataset and our new dataset (HKU-IS), and lowering the mean absolute error by 5.7% and 35.1% respectively on these two datasets.

We track the object by separating it from the surrounding with an ensemble of boosted classifiers, which are trained in a discriminative feature space that is determined on the fly. Contour refinement and weight thresholding techniques are used to select good examples for training. While tracking, location calibration and scale adaptation are used to improve the tracker's performance. We update the ensemble of weak classifiers online to adapt to appearance changes, and use the positive occupancy ratio to detect occlusion. A center-surround discrepancy measure is presented to evaluate the discriminative power of the current feature space and to invoke re-initialization of feature selection and classifier training if necessary. Experiments on challenging video sequences demonstrate the effectiveness of the proposed approach.