Visual Dialogue Navigation (VDN) aims to enable agents to reach target locations through dialogue with humans. The integration of VDN into Unmanned Aerial Vehicle (UAV) systems enhances human-machine interaction by enabling intuitive, hands-free operation, thereby unlocking vast applications. However, existing VDN models for UAVs can only perform navigation based on dialogue history, lacking proactive interaction capabilities to correct trajectories. Moreover, their sequential observation history recording mechanism struggles to accurately localize landmarks observed in the historical context, leading to ineffective utilization of referential information in new user instructions.To address these, we present AerialVLA, an end-to-end UAV navigation framework integrating dialogue comprehension, action decision-making, and navigational question generation. AerialVLA comprises three core components: i) we propose the Progress-Driven Navigation-Query Alternation mechanism to determine optimal questioning timing through navigation progress estimation autonomously. ii) To effectively model long-horizon history observation sequences, we develop the History Spatial-Temporal Fusion module that extracts discriminative spatial-temporal representations from historical observations. iii) Furthermore, to overcome data scarcity in training, we devise the Online Task-Driven Augmentation strategy that enhances learning through action-conditioned data augmentation. Experimental results demonstrate that AerialVLA achieves state-of-the-art navigation performance while exhibiting effective dialogue capabilities.Moreover, to better evaluate the agent's proactive dialogue and navigation abilities, our evaluation benchmark, named UAV Navigation with Online Dialogue (UNOD), incorporates an online dialogue interaction module. The UNOD assesses UAV agents' real-time questioning capabilities by leveraging an Air Commander Large Language Model to simulate human-UAV interactions during testing.

Retrieval Augmented Generation enhances the response accuracy of Large Language Models (LLMs) by integrating retrieval and generation modules with external knowledge, demonstrating particular strength in real-time queries and Visual Question Answering tasks. However, the effectiveness of RAG is frequently hindered by the precision of the retriever: many retrieved samples fed into the generation phase are irrelevant or misleading, posing a critical bottleneck to LLMs’ performance. To address this challenge, we introduce \textbf{VaccineRAG}, a novel Chain-of-Thought-based retrieval-augmented generation dataset. On one hand, VaccineRAG employs a benchmark to evaluate models using data with varying positive/negative sample ratios, systematically exposing inherent weaknesses in current LLMs. On the other hand, it enhances models’ sample-discrimination capabilities by prompting LLMs to generate explicit Chain-of-Thought (CoT) analysis for each sample before producing final answers. Furthermore, to enhance the model’s ability to learn long-sequence complex CoT content, we propose \textbf{Partial-GRPO}. By modeling the outputs of LLMs as multiple components rather than a single whole, our model can make more informed preference selections for complex sequences, thereby enhancing its capacity to learn complex CoT. Comprehensive evaluations and ablation studies on VaccineRAG validate the effectiveness of the proposed scheme.

Weikang Shi, Aldrich Yu, Rongyao Fang, Houxing Ren, Ke Wang, Aojun Zhou, Changyao Tian, Xinyu Fu, Yuxuan Hu, Zimu Lu, Linjiang Huang, Si Liu, Rui Liu, Hongsheng Li. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Introducing user-specified visual concepts in image editing is highly practical as these concepts convey the user's intent more precisely than text-based descriptions. We propose FreeEdit, a novel approach for achieving such reference-based image editing, which can accurately reproduce the visual concept from the reference image based on user-friendly language instructions. Our approach leverages the multi-modal instruction encoder to encode language instructions to guide the editing process. This implicit way of locating the editing area eliminates the need for manual editing masks. To enhance the reconstruction of reference details, we introduce the Decoupled Residual Refer-Attention (DRRA) module. This module is designed to integrate fine-grained reference features extracted by a detail extractor into the image editing process in a residual way without interfering with the original self-attention. Given that existing datasets are unsuitable for reference-based image editing tasks, particularly due to the difficulty in constructing image triplets that include a reference image, we curate a high-quality dataset, FreeBench, using a newly developed twice-repainting scheme. FreeBench comprises the images before and after editing, detailed editing instructions, as well as a reference image that maintains the identity of the edited object, encompassing tasks such as object addition, replacement, and deletion. By conducting phased training on FreeBench followed by quality tuning, FreeEdit achieves high-quality zero-shot editing through convenient language instructions. We conduct extensive experiments to evaluate the effectiveness of FreeEdit across multiple task types, demonstrating its superiority over existing methods.

Mixture-of-Experts (MoE) has emerged as an effective and efficient scaling mechanism for large language models (LLMs) and vision-language models (VLMs). By expanding a single feed-forward network into multiple expert branches, MoE increases model capacity while maintaining efficiency through sparse activation. However, despite this sparsity, the need to preload all experts into memory and activate multiple experts per input introduces significant computational and memory overhead. The expert module becomes the dominant contributor to model size and inference cost, posing a major challenge for deployment. To address this, we propose MC# (Mixture-Compressor-sharp), a unified framework that combines static quantization and dynamic expert pruning by leveraging the significance of both experts and tokens to achieve aggressive compression of MoE-LLMs/VLMs. To reduce storage and loading overhead, we introduce Pre-Loading Mixed-Precision Quantization (PMQ), which formulates adaptive bit allocation as a linear programming problem. The objective function jointly considers expert importance and quantization error, producing a Pareto-optimal trade-off between model size and performance. To reduce runtime computation, we further introduce Online Top-any Pruning (OTP), which models expert activation per token as a learnable distribution via Gumbel-Softmax sampling. During inference, OTP dynamically selects a subset of experts for each token, allowing fine-grained control over activation. By combining PMQ's static bit-width optimization with OTP's dynamic routing, MC# achieves extreme compression with minimal accuracy degradation. On DeepSeek-VL2, MC# achieves a 6.2 × weight reduction at an average of 2.57 bits, with only a 1.7% drop across five multimodal benchmarks compared to the 16-bit baseline. Moreover, OTP further reduces expert activation by 20% with less than 1% performance loss, demonstrating strong potential for efficient deployment of MoE-based models.

The rise of autonomous vehicles has significantly increased the demand for robust 3D object detection systems. While cameras and LiDAR sensors each offer unique advantages-cameras provide rich texture information and LiDAR offers precise 3D spatial data-relying on a single modality often leads to performance limitations. This paper introduces MV2DFusion, a multi-modal detection framework that integrates the strengths of both worlds through an advanced query-based fusion mechanism. By introducing an image query generator to align with image-specific attributes and a point cloud query generator, MV2DFusion effectively combines modality-specific object semantics without biasing toward one single modality. Then the sparse fusion process can be accomplished based on the valuable object semantics, ensuring efficient and accurate object detection across various scenarios. Our framework's flexibility allows it to integrate with any image and point cloud-based detectors, showcasing its adaptability and potential for future advancements. Extensive evaluations on the nuScenes and Argoverse2 datasets demonstrate that MV2DFusion achieves state-of-the-art performance, particularly excelling in long-range detection scenarios.

In this paper, we propose an Audio-Language-Referenced SAM 2 (AL-Ref-SAM 2) pipeline to explore the training-free paradigm for audio and language-referenced video object segmentation, namely AVS and RVOS tasks. The intuitive solution leverages GroundingDINO to identify the target object from a single frame and SAM 2 to segment the identified object throughout the video, which is less robust to spatiotemporal variations due to a lack of video context exploration. Thus, in our AL-Ref-SAM 2 pipeline, we propose a novel GPT-assisted Pivot Selection (GPT-PS) module to instruct GPT-4 to perform two-step temporal-spatial reasoning for sequentially selecting pivot frames and pivot boxes, thereby providing SAM 2 with a high-quality initial object prompt. Within GPT-PS, two task-specific Chain-of-Thought prompts are designed to unleash GPT’s temporal-spatial reasoning capacity by guiding GPT to make selections based on a comprehensive understanding of video and reference information. Furthermore, we propose a Language-Binded Reference Unification (LBRU) module to convert audio signals into language-formatted references, thereby unifying the formats of AVS and RVOS tasks in the same pipeline. Extensive experiments show that our training-free AL-Ref-SAM 2 pipeline achieves performances comparable to or even better than fully-supervised fine-tuning methods.

In this paper, we present GaussianPainter, the first method to paint a point cloud into 3D Gaussians given a reference image. GaussianPainter introduces an innovative feed-forward approach to overcome the limitations of time-consuming test-time optimization in 3D Gaussian splatting. Our method addresses a critical challenge in the field: the non-uniqueness problem inherent in the large parameter space of 3D Gaussian splatting. This space, encompassing rotation, anisotropic scales, and spherical harmonic coefficients, introduces the challenge of rendering similar images from substantially different Gaussian fields. As a result, feed-forward networks face instability when attempting to directly predict high-quality Gaussian fields, struggling to converge on consistent parameters for a given output. To address this issue, we propose to estimate a surface normal for each point to determine its Gaussian rotation. This strategy enables the network to effectively predict the remaining Gaussian parameters in the constrained space. We further enhance our approach with an appearance injection module, incorporating reference image appearance into Gaussian fields via a multiscale triplane representation. Our method successfully balances efficiency and fidelity in 3D Gaussian generation, achieving high-quality, diverse, and robust 3D content creation from point clouds in a single forward pass. A video is provided in our supplementary material for a more detailed explanation of our method.

Audio-Visual Segmentation (AVS) aims to segment sound-producing objects in video frames based on the associated audio signal. Prevailing AVS methods typically adopt an audio-centric Transformer architecture, where object queries are derived from audio features. However, audiocentric Transformers suffer from two limitations: perception ambiguity caused by the mixed nature of audio, and weakened dense prediction ability due to visual detail loss. To address these limitations, we propose a new Vision-Centric Transformer (VCT) framework that leverages vision-derived queries to iteratively fetch corresponding audio and visual information, enabling queries to better distinguish between different sounding objects from mixed audio and accurately delineate their contours. Additionally, we also introduce a Prototype Prompted Query Generation (PPQG) module within our VCT framework to generate vision-derived queries that are both semantically aware and visually rich through audio prototype prompting and pixel context grouping, facilitating audio-visual information aggregation. Extensive experiments demonstrate that our VCT framework achieves new state-of-the-art performances on three subsets of the AVSBench dataset.

Collaborative perception aims to address the constraint of single-agent perception by exchanging information among multiple agents. Previous works primarily focus on collaborative object detection, exploring compressed transmission and fusion prediction tailored to sparse object features. However, these strategies are not well-suited for dense features in collaborative BEV semantic segmentation. Therefore, we propose CoGMP, a novel Collaborative framework that leverages Generative Map Priors to achieve efficient compression and robust fusion. CoGMP introduces two key innovations: Element Format Feature Compression (EFFC) and Structure Guided Feature Fusion (SGFF). Specifically, EFFC leverages map element priors from codebook to encode BEV features as discrete element indices for transmitted information compression. Meanwhile, SGFF utilizes a diffusion model with structural priors to coherently integrate multi-agent features, thereby achieving consistent fusion predictions. Evaluations on the OPV2V dataset show that CoGMP achieves a 6.89/7.64 Road/Lane IoU improvement and a 32-fold reduction in communication volume.

The advancement of Large Vision Language Models (LVLMs) has significantly improved multimodal understanding, yet challenges remain in video reasoning tasks due to the scarcity of high-quality, large-scale datasets. Existing video question-answering (VideoQA) datasets often rely on costly manual annotations with insufficient granularity or automatic construction methods with redundant frame-by-frame analysis, limiting their scalability and effectiveness for complex reasoning. To address these challenges, we introduce VideoEspresso, a novel dataset that features VideoQA pairs preserving essential spatial details and temporal coherence, along with multimodal annotations of intermediate reasoning steps. Our construction pipeline employs a semantic-aware method to reduce redundancy, followed by generating QA pairs using GPT-4o. We further develop video Chain-of-Thought (CoT) annotations to enrich reasoning processes, guiding GPT-4o in extracting logical relationships from QA pairs and video content. To exploit the potential of high-quality VideoQA pairs, we propose a Hybrid LVLMs Collaboration framework, featuring a Frame Selector and a two-stage instruction fine-tuned reasoning LVLM. This framework adaptively selects core frames and performs CoT reasoning using multimodal evidence. Evaluated on our proposed benchmark with 14 tasks against 9 popular LVLMs, our method outperforms existing baselines on most tasks, demonstrating superior video reasoning capabilities. Our code and dataset have been released at: https://github.com/hshjerry/VideoEspresso

Recent advancements in multimodal large language models (MLLMs) have shown promising results, yet existing approaches struggle to effectively handle both temporal and spatial localization simultaneously. This challenge stems from two key issues: first, incorporating spatial-temporal localization introduces a vast number of coordinate combinations, complicating the alignment of linguistic and visual coordinate representations; second, encoding fine-grained temporal and spatial information during video feature compression is inherently difficult. To address these issues, we propose LLaVA-ST, a MLLM for fine-grained spatial-temporal multimodal understanding. In LLaVA-ST, we propose Language-Aligned Positional Embedding, which embeds the textual coordinate special token into the visual space, simplifying the alignment of fine-grained spatial-temporal correspondences. Additionally, we design the Spatial-Temporal Packer, which decouples the feature compression of temporal and spatial resolutions into two distinct point-to-region attention processing streams. Furthermore, we propose ST-Align dataset with 4.3M training samples for fine-grained spatial-temporal multimodal understanding. With ST-align, we present a progressive training pipeline that aligns the visual and textual feature through sequential coarse-to-fine stages. Additionally, we introduce an ST-Align benchmark to evaluate spatial-temporal interleaved fine-grained understanding tasks, which include Spatial-Temporal Video Grounding (STVG) , Event Localization and Captioning (ELC) and Spatial Video Grounding (SVG). LLaVA-ST achieves outstanding performance on 11 benchmarks requiring fine-grained temporal, spatial, or spatial-temporal interleaving multimodal understanding. Our code, data and benchmark will be released at https://github.com/appletea233/LLaVA-ST.

Driving scene reconstruction and rendering have advanced significantly using the 3D Gaussian Splatting. However, most prior research has focused on the rendering quality along a pre-recorded vehicle path and struggles to generalize to out-of-path viewpoints, which is caused by the lack of high-quality supervision in those out-of-path views. To address this issue, we introduce an Inverse View Warping technique to create compact and high-quality images as supervision for the reconstruction of the out-of-path views, enabling high-quality rendering results for those views. For accurate and robust inverse view warping, a depth bootstrap strategy is proposed to obtain on-the-fly dense depth maps during the optimization process, overcoming the sparsity and incompleteness of LiDAR depth data. Our method achieves superior in-path and out-of-path reconstruction and rendering performance on the widely used Waymo Open dataset. In addition, a simulator-based benchmark is proposed to obtain the out-of-path ground truth and quantitatively evaluate the performance of out-of-path rendering, where our method outperforms previous methods by a significant margin. Our code is available at https://github.com/zhou745/FlexDrive.git.

Existing video-language models (Video-LLMs) typically rely on concatenating visual tokens with textual inputs for joint modeling.However, this token-level alignment leads to significant inefficiency, especially when scaling to long videos with dense visual inputs.In this work, we propose a video-to-parameter efficiency paradigm named ViPE that eliminates redundant visual tokens by transforming video content into visual perceptual weights, which are directly injected into the LLM's parameters.ViPE consists of a visual injection module that compresses video features into a small set of perceptual queries using a hierarchical merge strategy, and a visual perception module that integrates the resulting representations into the LLM through a lightweight LoRA-like mechanism.ViPE achieves performance comparable to token-based baselines such as LLaVA, while reducing FLOPs by 85% and inference time by up to 65%, demonstrating a highly efficient and scalable solution for video understanding.

Existing approaches to drone visual geo-localization predominantly adopt the image-based setting, where a single drone-view snapshot is matched with images from other platforms. Such task formulation, however, underutilizes the inherent video output of the drone and is sensitive to occlusions and viewpoint disparity. To address these limitations, we formulate a new video-based drone geo-localization task and propose the Video2BEV paradigm. This paradigm transforms the video into a Bird's Eye View (BEV), simplifying the subsequent \textbf{inter-platform} matching process. In particular, we employ Gaussian Splatting to reconstruct a 3D scene and obtain the BEV projection. Different from the existing transform methods, \eg, polar transform, our BEVs preserve more fine-grained details without significant distortion. To facilitate the discriminative \textbf{intra-platform} representation learning, our Video2BEV paradigm also incorporates a diffusion-based module for generating hard negative samples. To validate our approach, we introduce UniV, a new video-based geo-localization dataset that extends the image-based University-1652 dataset. UniV features flight paths at $30^\circ$ and $45^\circ$ elevation angles with increased frame rates of up to 10 frames per second (FPS). Extensive experiments on the UniV dataset show that our Video2BEV paradigm achieves competitive recall rates and outperforms conventional video-based methods. Compared to other competitive methods, our proposed approach exhibits robustness at lower elevations with more occlusions.

Collaborative perception shares information among different agents and helps solving problems that individual agents may face, e.g., occlusions and small sensing range. Prior methods usually separate the multi-agent fusion and multi-time fusion into two consecutive steps. In contrast, this paper proposes an efficient collaborative perception that aggregates the observations from different agents (space) and different times into a unified spatio-temporal space simultanesouly. The unified spatio-temporal space brings two benefits, i.e., efficient feature transmission and superior feature fusion. 1) Efficient feature transmission: each static object yields a single observation in the spatial temporal space, and thus only requires transmission only once (whereas prior methods re-transmit all the object features multiple times). 2) superior feature fusion: merging the multi-agent and multi-time fusion into a unified spatial-temporal aggregation enables a more holistic perspective, thereby enhancing perception performance in challenging scenarios. Consequently, our Collaborative perception with Spatio-temporal Transformer (CoST) gains improvement in both efficiency and accuracy. Notably, CoST is not tied to any specific method and is compatible with a majority of previous methods, enhancing their accuracy while reducing the transmission bandwidth.

Preference alignment has emerged as an effective strategy to enhance the performance of Multimodal Large Language Models (MLLMs) following supervised fine-tuning. While existing preference alignment methods predominantly target hallucination factors, they overlook the factors essential for multi-modal comprehension capabilities, often narrowing their improvements on hallucination mitigation. To bridge this gap, we propose Instruction-oriented Preference Alignment (IPA), a scalable framework designed to automatically construct alignment preferences grounded in instruction fulfillment efficacy. Our method involves an automated preference construction coupled with a dedicated verification process that identifies instruction-oriented factors, avoiding significant variability in response representations. Additionally, IPA incorporates a progressive preference collection pipeline, further recalling challenging samples through model self-evolution and reference-guided refinement. Experiments conducted on Qwen2VL-7B demonstrate IPA's effectiveness across multiple benchmarks, including hallucination evaluation, visual question answering, and text understanding tasks, highlighting its capability to enhance general comprehension.

The objective of the collaborative perception task is to enhance the individual agent's perception capability through message communication among neighboring agents. A central challenge lies in optimizing the inherent trade-off between perception ability and communication cost. To tackle this bottleneck issue, we argue that a good message unit should encapsulate both semantic and structural information in a sparse format, a feature not present in prior approaches. In this paper, we innovatively propose a compact message unit, namely point cluster, whose core idea is to represent potential objects efficiently with explicitly decoupled low-level structure information and high-level semantic information. Building upon this new message unit, we propose a comprehensive framework CPPC for communication-efficient collaborative perception. The core principle of CPPC is twofold: first, through strategical point sampling, structure information can be well preserved with a few key points, which can significantly reduce communication cost; second, the sequence format of point clusters enables efficient message aggregation by set matching and merging, thereby eliminating unnecessary computation generated when aligning squared BEV maps, especially for long-range collaboration. To handle time latency and pose errors encountered in real-world scenarios, we also carefully design parameter-free solutions that can adapt to different noisy levels without finetuning. Experiments on two widely recognized collaborative perception benchmarks showcase the superior performance of our method compared to the previous state-of-the-art approaches.

Mixture-of-Experts large language models (MoE-LLMs) marks a significant step forward of language models, however, they encounter two critical challenges in practice: 1) expert parameters lead to considerable memory consumption and loading latency; and 2) the current activated experts are redundant, as many tokens may only require a single expert. Motivated by these issues, we investigate the MoE-LLMs and make two key observations: a) different experts exhibit varying behaviors on activation reconstruction error, routing scores, and activated frequencies, highlighting their differing importance, and b) not all tokens are equally important-- only a small subset is critical. Building on these insights, we propose MC, a training-free Mixture-Compressor for MoE-LLMs, which leverages the significance of both experts and tokens to achieve an extreme compression. First, to mitigate storage and loading overheads, we introduce Pre-Loading Mixed-Precision Quantization (PMQ), which formulates the adaptive bit-width allocation as a Linear Programming (LP) problem, where the objective function balances multi-factors reflecting the importance of each expert. Additionally, we develop Online Dynamic Pruning (ODP), which identifies important tokens to retain and dynamically select activated experts for other tokens during inference to optimize efficiency while maintaining performance. Our MC integrates static quantization and dynamic pruning to collaboratively achieve extreme compression for MoE-LLMs with less accuracy loss, ensuring an optimal trade-off between performance and efficiency Extensive experiments confirm the effectiveness of our approach. For instance, at 2.54 bits, MC compresses 76.6% of the model, with only a 3.8% average accuracy loss. During dynamic inference, we further reduce activated parameters by 15%, with a performance drop of less than 0.6%. Remarkably, MC even surpasses floating-point 13b dense LLMs with significantly smaller parameter sizes, suggesting that mixture compression in MoE-LLMs has the potential to outperform both comparable and larger dense LLMs. Our code is available at https://github.com/Aaronhuang-778/MC-MoE

We introduce LLaVA-MoD, a novel framework designed to enable the efficient training of small-scale Multimodal Language Models ($s$-MLLM) distilling knowledge from large-scale MLLM ($l$-MLLM). Our approach tackles two fundamental challenges in MLLM distillation. First, we optimize the network structure of $s$-MLLM by integrating a sparse Mixture of Experts (MoE) architecture into the language model, striking a balance between computational efficiency and model expressiveness. Second, we propose a progressive knowledge transfer strategy for comprehensive knowledge transfer. This strategy begins with mimic distillation, where we minimize the Kullback-Leibler (KL) divergence between output distributions to enable $s$-MLLM to emulate $s$-MLLM's understanding. Following this, we introduce preference distillation via Preference Optimization (PO), where the key lies in treating $l$-MLLM as the reference model. During this phase, the $s$-MLLM's ability to discriminate between superior and inferior examples is significantly enhanced beyond $l$-MLLM, leading to a better $s$-MLLM that surpasses $l$-MLLM, particularly in hallucination benchmarks. Extensive experiments demonstrate that LLaVA-MoD surpasses existing works across various benchmarks while maintaining a minimal activated parameters and low computational costs. Remarkably, LLaVA-MoD-2B surpasses Qwen-VL-Chat-7B with an average gain of 8.8\%, using merely $0.3\%$ of the training data and 23\% trainable parameters. The results underscore LLaVA-MoD's ability to effectively distill comprehensive knowledge from its teacher model, paving the way for developing efficient MLLMs.

Developing agents capable of navigating to a target location based on language instructions and visual information, known as vision-language navigation (VLN), has attracted widespread interest. Most research has focused on ground-based agents, while UAV-based VLN remains relatively underexplored. Recent efforts in UAV vision-language navigation predominantly adopt ground-based VLN settings, relying on predefined discrete action spaces and neglecting the inherent disparities in agent movement dynamics and the complexity of navigation tasks between ground and aerial environments. To address these disparities and challenges, we propose solutions from three perspectives: platform, benchmark, and methodology. To enable realistic UAV trajectory simulation in VLN tasks, we propose the OpenUAV platform, which features diverse environments, realistic flight control, and extensive algorithmic support. We further construct a target-oriented VLN dataset consisting of approximately 12k trajectories on this platform, serving as the first dataset specifically designed for realistic UAV VLN tasks. To tackle the challenges posed by complex aerial environments, we propose an assistant-guided UAV object search benchmark called UAV-Need-Help, which provides varying levels of guidance information to help UAVs better accomplish realistic VLN tasks. We also propose a UAV navigation LLM that, given multi-view images, task descriptions, and assistant instructions, leverages the multimodal understanding capabilities of the MLLM to jointly process visual and textual information, and performs hierarchical trajectory generation. The evaluation results of our method significantly outperform the baseline models, while there remains a considerable gap between our results and those achieved by human operators, underscoring the challenge presented by the UAV-Need-Help task.

Lane topology reasoning plays a critical role in autonomous driving by modeling the connections among lanes and the topological relationships between lanes and traffic elements. Most existing methods adopt a first-detect-then-reason paradigm, where topological relationships are supervised based on the one-to-one assignment results obtained during the detection stage. This supervision strategy results in suboptimal topology reasoning performance due to the limited range of valid supervision. In this paper, we propose RATopo, a Redundancy Assignment strategy for lane Topology reasoning that enables quantity-rich and geometry-diverse topology supervision. Specifically, we restructure the Transformer decoder by swapping the cross-attention and self-attention layers. This allows redundant lane predictions to be retained before suppression, enabling effective one-to-many assignment. We also instantiate multiple parallel cross-attention blocks with independent parameters, which further enhances the diversity of detected lanes. Extensive experiments on OpenLane-V2 demonstrate that our RATopo strategy is model-agnostic and can be seamlessly integrated into existing topology reasoning frameworks, consistently improving both lane-lane and lane-traffic topology performance (e.g., + 15.7% and + 9.5% on TopoLogic for TOP_ll and TOP_lt on OpenLane-V2 subset_B, respectively).

Cross-view object correspondence involves matching objects between egocentric (first-person) and exocentric (third-person) views. It is a critical yet challenging task for visual understanding. In this work, we propose the Dense Object Matching and Refinement (DOMR) framework to establish dense object correspondences across views. The framework centers around the Dense Object Matcher (DOM) module, which jointly models multiple objects. Unlike methods that directly match individual object masks to image features, DOM leverages both positional and semantic relationships among objects to find correspondences. DOM integrates a proposal generation module with a dense matching module that jointly encodes visual, spatial, and semantic cues, explicitly constructing inter-object relationships to achieve dense matching among objects. Furthermore, we combine DOM with a mask refinement head designed to improve the completeness and accuracy of the predicted masks, forming the complete DOMR framework. Extensive evaluations on the Ego-Exo4D benchmark demonstrate that our approach achieves state-of-the-art performance with a mean IoU of 49.7% on Ego→Exo and 55.2% on Exo→Ego. These results outperform those of previous methods by 5.8% and 4.3%, respectively, validating the effectiveness of our integrated approach for cross-view understanding.

Embodied intelligence, evolving from rule-based control to learning-driven systems, has primarily focused on rigid robots, whose limitations in flexibility and adaptability have spurred research into soft-bodied platforms inspired by biological organisms. Soft robots offer adaptive, safe solutions for human collaboration and complex environments but face challenges from underactuation and nonlinear dynamics. This workshop centers on multimodal perception and decision-making in soft robotics, gathering researchers to explore cutting-edge technologies, challenges, and solutions across areas like embodied navigation, manipulation, and control, with presentations and discussions on novel findings and methodologies.

Aerial Vision-and-Language Navigation (VLN) is an emerging task that enables Unmanned Aerial Vehicles (UAVs) to navigate outdoor environments using natural language instructions and visual cues. However, due to the extended trajectories and complex maneuverability of UAVs, achieving reliable UAV-VLN performance is challenging and often requires human intervention or overly detailed instructions. To harness the advantages of UAVs' high mobility, which could provide multi-grained perspectives, while maintaining a manageable motion space for learning, we introduce a novel task called Dual-Altitude UAV Collaborative VLN (DuAl-VLN). In this task, two UAVs operate at distinct altitudes: a high-altitude UAV responsible for broad environmental reasoning, and a low-altitude UAV tasked with precise navigation. To support the training and evaluation of the DuAl-VLN, we construct the HaL-13k, a dataset comprising 13,838 collaborative high-low UAV demonstration trajectories, each paired with target-oriented language instructions. This dataset includes both unseen maps and an unseen object validation set to systematically evaluate the model's generalization capabilities across novel environments and unfamiliar targets. To consolidate their complementary strengths, we propose a dual-UAV collaborative VLN framework, AeroDuo, where the high-altitude UAV integrates a multimodal large language model (Pilot-LLM) for target reasoning, while the low-altitude UAV employs a lightweight multi-stage policy for navigation and target grounding. The two UAVs work collaboratively and only exchange minimal coordinate information to ensure efficiency. Experimental results indicate that AeroDuo achieves an evident 9.71% improvement in success rates compared to existing single-UAV methods, demonstrating the effectiveness of dual-altitude collaboration in balancing environmental coverage, precision, and operational autonomy.

Recent advances in vision-language models (VLMs) have enabled instruction-conditioned robotic systems with improved generalization. However, most existing work focuses on reactive System 1 policies, underutilizing VLMs’ strengths in semantic reasoning and long-horizon planning. These System 2 capabilities—characterized by deliberative, goal-directed thinking—remain underexplored due to the limited temporal scale and structural complexity of current benchmarks. To address this gap, we introduce RoboCerebra, a benchmark for evaluating high-level reasoning in long-horizon robotic manipulation. RoboCerebra includes: (1) a large-scale simulation dataset with extended task horizons and diverse subtask sequences in household environments; (2) a hierarchical framework combining a high-level VLM planner with a low-level vision-language-action (VLA) controller; and (3) an evaluation protocol targeting planning, reflection, and memory through structured System 1–System 2 interaction. The dataset is constructed via a top-down pipeline, where GPT generates task instructions and decomposes them into subtask sequences. Human operators execute the subtasks in simulation, yielding high-quality trajectories with dynamic object variations. Compared to prior benchmarks, RoboCerebra features significantly longer action sequences and denser annotations. We further benchmark state-of-the-art VLMs as System 2 modules and analyze their performance across key cognitive dimensions, advancing the development of more capable and generalizable robotic planners.

Agile Earth Observation Satellites (AEOSs) constellations offer unprecedented flexibility for monitoring the Earth’s surface, but their scheduling remains challenging under large-scale scenarios, dynamic environments, and stringent constraints. Existing methods often simplify these complexities, limiting their real-world performance. We address this gap with a unified framework integrating a standardized benchmark suite and a novel scheduling model. Our benchmark suite, AEOS-Bench, contains $3,907$ finely tuned satellite assets and $16,410$ scenarios. Each scenario features $1$ to $50$ satellites and $50$ to $300$ imaging tasks. These scenarios are generated via a high-fidelity simulation platform, ensuring realistic satellite behavior such as orbital dynamics and resource constraints. Ground truth scheduling annotations are provided for each scenario. To our knowledge, AEOS-Bench is the first large-scale benchmark suite tailored for realistic constellation scheduling. Building upon this benchmark, we introduce AEOS-Former, a Transformer-based scheduling model that incorporates a constraint-aware attention mechanism. A dedicated internal constraint module explicitly models the physical and operational limits of each satellite. Through simulation-based iterative learning, AEOS-Former adapts to diverse scenarios, offering a robust solution for AEOS constellation scheduling. Experimental results demonstrate that AEOS-Former outperforms baseline models in task completion and energy efficiency, with ablation studies highlighting the contribution of each component. Code and data are provided in https://github.com/buaa-colalab/AEOSBench.

Unmanned Aerial Vehicles (UAVs) are evolving into language-interactive platforms, enabling more intuitive forms of human-drone interaction. While prior works have primarily focused on high-level planning and long-horizon navigation, we shift attention to language-guided fine-grained trajectory control, where UAVs execute short-range, reactive flight behaviors in response to language instructions. We formalize this problem as the Flying-on-a-Word (Flow) task and introduce UAV imitation learning as an effective approach. In this framework, UAVs learn fine-grained control policies by mimicking expert pilot trajectories paired with atomic language instructions. To support this paradigm, we present UAV-Flow, the first real-world benchmark for language-conditioned, fine-grained UAV control. It includes a task formulation, a large-scale dataset collected in diverse environments, a deployable control framework, and a simulation suite for systematic evaluation. Our design enables UAVs to closely imitate the precise, expert-level flight trajectories of human pilots and supports direct deployment without sim-to-real gap. We conduct extensive experiments on UAV-Flow, benchmarking VLN and VLA paradigms. Results show that VLA models are superior to VLN baselines and highlight the critical role of spatial grounding in the fine-grained Flow setting.

In this paper, we focus on the challenging task of monocular 3D lane detection. Previous methods typically adopt inverse perspective mapping (IPM) to transform the Front-Viewed (FV) images or features into the Bird-Eye-Viewed (BEV) space for lane detection. However, IPM's dependence on flat ground assumption and context information loss in BEV representations lead to inaccurate 3D information estimation. Though efforts have been made to bypass BEV and directly predict 3D lanes from FV representations, their performances still fall behind BEV-based methods due to a lack of structured modeling of 3D lanes. In this paper, we propose a novel BEV-free method named Anchor3DLane++ which defines 3D lane anchors as structural representations and makes predictions directly from FV features. We also design a Prototype-based Adaptive Anchor Generation (PAAG) module to generate sample-adaptive sparse 3D anchors dynamically. In addition, an Equal-Width (EW) loss is developed to leverage the parallel property of lanes for regularization. Furthermore, camera-LiDAR fusion is also explored based on Anchor3DLane++ to leverage complementary information. Extensive experiments on three popular 3D lane detection benchmarks show that our Anchor3DLane++ outperforms previous state-of-the-art methods. Code is available at: https://github.com/tusen-ai/Anchor3DLane.

The goal of RGB-Thermal (RGB-T) tracking is to utilize the synergistic and complementary strengths of RGB and TIR modalities to enhance tracking in diverse situations, with cross-modal interaction being a crucial element. Earlier methods often simply combine the features of the RGB and TIR search frames, leading to a coarse interaction that also introduced unnecessary background noise. Many other approaches sample candidate boxes from search frames and apply different fusion techniques to individual pairs of RGB and TIR boxes, which confines cross-modal interactions to local areas and results in insufficient context modeling. Additionally, mining video temporal contexts is also under-explored in RGB-T tracking. To alleviate these limitations, we propose a novel Template-Bridged Search region Interaction (TBSI) module that exploits templates as the medium to bridge the cross-modal interaction between RGB and TIR search regions by gathering and distributing target-relevant object and environment contexts. An Illumination Guided Fusion (IGF) module is designed to adaptively fuse RGB and TIR search region tokens with a global illumination factor. Furthermore, in the inference stage, we also propose an efficient Target-Preserved Template Updating (TPTU) strategy, leveraging the temporal context within video sequences to accommodate the target's appearance change. Our proposed modules are integrated into a ViT backbone for joint feature extraction, search-template matching, and cross-modal interaction. Extensive experiments on three popular RGB-T tracking benchmarks demonstrate our method achieves new state-of-the-art performances.

Underwater imagery often suffers from light attenuation and color distortion, resulting in images with low contrast and blurriness. Enhancing these images is crucial yet challenging due to the complex degradation and noise inherent in underwater environments. In this study, we introduce a novel diffusion model, termed Underwater Image Enhancement(UIE) Diffusion, which leverages a global feature prior for effective underwater image enhancement. To our knowledge, this is the inaugural application of a diffusion model to the task of underwater image enhancement, setting a new benchmark in performance. Our approach begins with the introduction of a global feature prior to augment the diffusion model, mitigating the impact of noise and distortion during training. We then incorporate an underwater image degradation model to facilitate the learning of mappings between high-quality and degraded underwater images. To address over-enhancement caused by high-frequency components, we employ scaling factors to modulate the influence of frequency features during diffusion. Additionally, we enhance the model's stability during inference by integrating a backward diffusion process into its training. Comprehensive evaluations on multiple public datasets demonstrate that UIE Diffusion surpasses existing state-of-the-art methods in both subjective outcomes and objective assessments.

This paper views the DETR's non-duplicate detection ability as a competition result among object queries. Around each object, there are usually multiple queries, within which only a single one can win the chance to become the final detection. Such a competition is hard: while some competing queries initially have very close prediction scores, their leading query has to dramatically enlarge its score superiority after several decoder layers. To help the leading query stands out, this paper proposes EASE-DETR, which eases the competition by introducing bias that favours the leading one. EASE-DETR is very simple: in every intermediate decoder layer, we identify the “leading / trailing” relationship between any two queries, and encode this binary relationship into the following decoder layer to amplify the superiority of the leading one. More concretely, the leading query is to be protected from mutual query suppression in the self-attention layer and encouraged to absorb more object features in the cross-attention layer, therefore accelerating to win. Experimental results show that EASE-DETR brings consistent and remarkable improvement to various DETRs.

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.

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.

LiDAR-based 3D object detection plays an essential role in autonomous driving. Existing high-performing 3D object detectors usually build dense feature maps in the backbone network and prediction head. However, the computational costs introduced by the dense feature maps grow quadratically as the perception range increases, making these models hard to scale up to long-range detection. Some recent works have attempted to construct fully sparse detectors to solve this issue; nevertheless, the resulting models either rely on a complex multi-stage pipeline or exhibit inferior performance. In this work, we propose a fully sparse adaptive feature diffusion network (SAFDNet) for LiDAR-based 3D object detection. In SAFDNet, an adaptive feature diffusion strategy is designed to address the center feature missing problem. We conducted extensive experiments on Waymo Open, nuScenes, and Argoverse2 datasets. SAFDNet performed slightly better than the previous SOTA on the first two datasets but much better on the last dataset, which features long-range detection, verifying the efficacy of SAFDNet in scenarios where long-range detection is required. Notably, on Argoverse2, SAFDNet surpassed the previous best hybrid detector HEDNet by 2.6% mAP while being 2.1 × faster, and yielded 2.1% mAP gains over the previous best sparse detector FSDv2 while being 1.3 × faster. The code will be available at https://github.com/zhanggang001/HEDNet.

Domain shifts such as sensor type changes and geographical situation variations are prevalent in Autonomous Driving (AD), which poses a challenge since AD model relying on the previous domain knowledge can be hardly directly deployed to a new domain without additional costs. In this paper, we provide a new perspective and approach of alleviating the domain shifts, by proposing a Reconstruction-Simulation-Perception (ReSimAD) scheme. Specifically, the implicit reconstruction process is based on the knowledge from the previous old domain, aiming to convert the domain-related knowledge into domain-invariant representations, e.g., 3D scene-level meshes. Besides, the point clouds simulation process of multiple new domains is conditioned on the above reconstructed 3D meshes, where the target-domain-like simulation samples can be obtained, thus reducing the cost of collecting and annotating new-domain data for the subsequent perception process. For experiments, we consider different cross-domain situations such as Waymo-to-KITTI, Waymo-to-nuScenes, etc, to verify the zero-shot target-domain perception using ReSimAD. Results demonstrate that our method is beneficial to boost the domain generalization ability, even promising for 3D pre-training. Code and simulated points are available at: https://github.com/PJLab-ADG/3DTrans

Recent studies have demonstrated Large Language Models (LLMs) can extend their zero-shot generalization capabilities to multimodal learning through instruction tuning. As more modalities and downstream tasks are introduced, negative conflicts and interference may have a worse impact on performance. While this phenomenon has been overlooked in previous work, we propose a novel and extensible framework, called Octavius, for comprehensive studies and experimentation on multimodal learning with Multimodal Large Language Models (MLLMs). Specifically, to mitigate the interference, we combine the concept of Mixture-of-Experts (MoE) with LoRA and design a multimodal LoRA-MoE decoder for task- and modality-specific learning. To the best of our knowledge, we are one of the pioneering efforts to introduce MoE into MLLMs to address this problem. The experimental results (about 20% improvement) have shown the effectiveness and versatility of our design in various 2D and 3D downstream tasks. Code and corresponding dataset will be available soon.

Visual prompting (VP) is an emerging parameter-efficient fine-tuning approach to adapting pre-trained vision models to solve various downstream image-classification tasks. However, there has hitherto been little systematic study of the design space of VP and no clear benchmark for evaluating its performance. To bridge this gap, we propose AutoVP, an end-to-end expandable framework for automating VP design choices, along with 12 downstream image-classification tasks that can serve as a holistic VP-performance benchmark. Our design space covers 1) the joint optimization of the prompts; 2) the selection of pre-trained models, including image classifiers and text-image encoders; and 3) model output mapping strategies, including nonparametric and trainable label mapping. Our extensive experimental results show that AutoVP outperforms the best-known current VP methods by a substantial margin, having up to 6.7% improvement in accuracy; and attains a maximum performance increase of 27.5% compared to linear-probing (LP) baseline. AutoVP thus makes a two-fold contribution: serving both as an efficient tool for hyperparameter tuning on VP design choices, and as a comprehensive benchmark that can reasonably be expected to accelerate VP’s development. The source code is available at https://github.com/IBM/AutoVP.

The goal of referring camouflaged object detection is to identify and segment the specified object hidden in the surroundings given text or images as references. The previous method still faces limitations in learning discriminative object features and comprehensively exploiting reference information due to coarse reference-image fusion upon disunified network components. In this paper, we propose a novel Reference Prompted Model Adaptation (RPMA) pipeline that employs rich and fine-grained semantic knowledge in a generic segmentation network to enhance the Ref-COD model’s capability. Within RPMA, we design a Cross Reference Adapter (CRA) to integrate reference information into the generic segmentation network to prompt reference-relevant camouflaged image features, and also devise a Reference-guided Dynamic Convolution (RDC) for foreground-background segmentation via reference-generated kernels. Extensive experiments on the Ref-COD benchmark show that our method achieves new state-of-the-art performance.

Recent 3D object detectors typically utilize multi-sensor data and unify multi-modal features in the shared bird’s-eye view (BEV) representation space. However, our empirical findings indicate that previous methods have limitations in generating fusion BEV features free from cross-modal conflicts. These conflicts encompass extrinsic conflicts caused by BEV feature construction and inherent conflicts stemming from heterogeneous sensor signals. Therefore, we propose a novel Eliminating Conflicts Fusion (ECFusion) method to explicitly eliminate the extrinsic/inherent conflicts in BEV space and produce improved multi-modal BEV features. Specifically, we devise a Semantic-guided Flow-based Alignment (SFA) module to resolve extrinsic conflicts via unifying spatial distribution in BEV space before fusion. Moreover, we design a Dissolved Query Recovering (DQR) mechanism to remedy inherent conflicts by preserving objectness clues that are lost in the fusion BEV feature. In general, our method maximizes the effective information utilization of each modality and leverages inter-modal complementarity. Our method achieves state-of-the-art performance in the highly competitive nuScenes 3D object detection dataset. The code is released at https://github.com/fjhzhixi/ECFusion.

Data augmentation methods to enhance perception performance in adverse weather have recently attracted considerable attention. Most of the LiDAR data augmentation methods post-process the existing dataset by physics-based models or machine-learning methods. However, due to the limited environmental annotations and the fixed vehicle trajectories in existing datasets, it is challenging to edit the scene and expand the diversity of traffic flow and scenario. To this end, we propose a simulator-based physical modeling approach to augment LiDAR data in rainy weather, enhancing the performance of the perception model. We complete the modeling task of the rainy weather effect in the CARLA simulator and establish a data collection pipeline for LiDAR. Furthermore, we pay special attention to the spray generated by vehicles in rainy weather and simulate this phenomenon through the Spray Emitter method we developed. In addition, considering the influence of different weather conditions on point cloud intensity, we develop a prediction network to forecast the intensity of the LiDAR echo. This enables us to complete the rainy weather simulation of 4D point cloud data. In the experiment, we observe that the model augmented by our synthetic dataset improves the performance for 3D object detection in rainy weather. Both code and dataset are available at https://github.com/PJLab-ADG/PCSim#rainypcsim.

Panoptic narrative grounding (PNG), whose core target is fine-grained image-text alignment, requires a panoptic segmentation of referred objects given a narrative caption. Previous discriminative methods achieve only weak or coarse-grained alignment by panoptic segmentation pretraining or CLIP model adaptation. Given the recent progress of text-to-image Diffusion models, several works have shown their capability to achieve fine-grained image-text alignment through cross-attention maps and improved general segmentation performance. However, the direct use of phrase features as static prompts to apply frozen Diffusion models to the PNG task still suffers from a large task gap and insufficient vision-language interaction, yielding inferior performance. Therefore, we propose an Extractive-Injective Phrase Adapter (EIPA) bypass within the Diffusion UNet to dynamically update phrase prompts with image features and inject the multimodal cues back, which leverages the fine-grained image-text alignment capability of Diffusion models more sufficiently. In addition, we also design a Multi-Level Mutual Aggregation (MLMA) module to reciprocally fuse multi-level image and phrase features for segmentation refinement. Extensive experiments on the PNG benchmark show that our method achieves new state-of-the-art performance.

Recently, large vision language models (LVLMs) have advanced AI by integrating visual and linguistic data for tasks like visual conversation, image captioning, and visual question answering. Current LVLM research either scales up model size for performance or reduces parameters for limited computational resources. We believe both large and tiny models have unique strengths and that collaborative training yields better results than independent training. We propose Collaborative Training of Tiny-Large Vision Language Models (CTVLMs), a framework connecting large and tiny models via a projection layer and leveraging a synergistic training strategy. Our framework improves training efficiency by strengthening the interconnection between large and tiny models. Using the parameter efficiency of tiny models, we effectively align image-text features, then apply knowledge distillation to help large models better align cross-modal information. During fine-tuning, the large model's extensive knowledge enhances tiny model's performance. This collaborative approach allows models to adapt to various computational resources and outperforms existing methods in vision-language tasks.

Video Virtual Try-On aims to transfer a garment onto a person in the video. Previous methods typically focus on image-based virtual try-on, but directly applying these methods to videos often leads to temporal discontinuity due to inconsistencies between frames. Limited attempts in video virtual try-on also suffer from unrealistic results and poor generalization ability. In light of previous research, we posit that the task of video virtual try-on can be decomposed into two key aspects: (1) single-frame results are realistic and natural, while retaining consistency with the garment; (2) the person's actions and the garment are coherent throughout the entire video. To address these two aspects, we propose a novel two-stage framework based on Latent Diffusion Model, namely Garment-Preserving Diffusion for Video Virtual Try-On (GPD-VVTO). In the first stage, the model is trained on single-frame data to improve the ability of generating high-quality try-on images. We integrate both low-level texture features and high-level semantic features of the garment into the denoising network to preserve garment details while ensuring a natural fit between the garment and the person. In the second stage, the model is trained on video data to enhance temporal consistency. We devise a novel Garment-aware Temporal Attention (GTA) module that incorporates garment features into temporal attention, enabling the model to maintain the fidelity to the garment during temporal modeling. Furthermore, we collect a video virtual try-on dataset containing high-resolution videos from diverse scenes, addressing the limited variety of current datasets in terms of video background and human actions. Extensive experiments demonstrate that our method outperforms existing state-of-the-art methods in both image-based and video-based virtual try-on tasks, indicating the effectiveness of our proposed framework.

Modern image generation (IG) models have been shown to capture rich semantics valuable for image understanding (IU) tasks. However, the potential of IU models to improve IG performance remains uncharted. We address this issue using a token-based IG framework, which relies on effective tokenizers to project images into token sequences. Currently, **pixel reconstruction** (e.g., VQGAN) dominates the training objective for image tokenizers. In contrast, our approach adopts the **feature reconstruction** objective, where tokenizers are trained by distilling knowledge from pretrained IU encoders. Comprehensive comparisons indicate that tokenizers with strong IU capabilities achieve superior IG performance across a variety of metrics, datasets, tasks, and proposal networks. Notably, VQ-KD CLIP achieves $4.10$ FID on ImageNet-1k (IN-1k). Visualization suggests that the superiority of VQ-KD can be partly attributed to the rich semantics within the VQ-KD codebook. We further introduce a straightforward pipeline to directly transform IU encoders into tokenizers, demonstrating exceptional effectiveness for IG tasks. These discoveries may energize further exploration into image tokenizer research and inspire the community to reassess the relationship between IU and IG. The code is released at https://github.com/magic-research/vector_quantization.

Enabling humanoid robots to clean rooms has long been a pursued dream within humanoid research communities. However, many tasks require multi-humanoid collaboration, such as carrying large and heavy furniture together. Given the scarcity of motion capture data on multi-humanoid collaboration and the efficiency challenges associated with multi-agent learning, these tasks cannot be straightforwardly addressed using training paradigms designed for single-agent scenarios. In this paper, we introduce **Coo**perative **H**uman-**O**bject **I**nteraction (**CooHOI**), a framework designed to tackle the challenge of multi-humanoid object transportation problem through a two-phase learning paradigm: individual skill learning and subsequent policy transfer. First, a single humanoid character learns to interact with objects through imitation learning from human motion priors. Then, the humanoid learns to collaborate with others by considering the shared dynamics of the manipulated object using centralized training and decentralized execution (CTDE) multi-agent RL algorithms. When one agent interacts with the object, resulting in specific object dynamics changes, the other agents learn to respond appropriately, thereby achieving implicit communication and coordination between teammates. Unlike previous approaches that relied on tracking-based methods for multi-humanoid HOI, CooHOI is inherently efficient, does not depend on motion capture data of multi-humanoid interactions, and can be seamlessly extended to include more participants and a wide range of object types.

Lumina-T2X is a nascent family of Flow-based Large Diffusion Transformers (Flag-DiT) that establishes a unified framework for transforming noise into various modalities, such as images and videos, conditioned on text instructions. Despite its promising capabilities, Lumina-T2X still encounters challenges including training instability, slow inference, and extrapolation artifacts. In this paper, we present Lumina-Next, an improved version of Lumina-T2X, showcasing stronger generation performance with increased training and inference efficiency. We begin with a comprehensive analysis of the Flag-DiT architecture and identify several suboptimal components, which we address by introducing the Next-DiT architecture with 3D RoPE and sandwich normalizations. To enable better resolution extrapolation, we thoroughly compare different context extrapolation methods applied to text-to-image generation with 3D RoPE, and propose Frequency- and Time-Aware Scaled RoPE tailored for diffusion transformers. Additionally, we introduce a sigmoid time discretization schedule for diffusion sampling, which achieves high-quality generation in 5-10 steps combined with higher-order ODE solvers. Thanks to these improvements, Lumina-Next not only improves the basic text-to-image generation but also demonstrates superior resolution extrapolation capabilities as well as multilingual generation using decoder-based LLMs as the text encoder, all in a zero-shot manner. To further validate Lumina-Next as a versatile generative framework, we instantiate it on diverse tasks including visual recognition, multi-views, audio, music, and point cloud generation, showcasing strong performance across these domains. By releasing all codes and model weights at https://github.com/Alpha-VLLM/Lumina-T2X, we aim to advance the development of next-generation generative AI capable of universal modeling.

One-to-one matching is a crucial design in DETR- like object detection frameworks. It enables the DETR to perform end-to-end detection. However, it also faces challenges of lacking positive sample supervision and slow convergence speed. Several recent works proposed the one-to-many matching mechanism to accelerate training and boost detection performance. We revisit these methods and model them in a unified format of augmenting the object queries. In this paper, we propose two methods that realize one-to-many matching from a different perspective of augmenting images or image features. The first method is One-to-many Matching via Data Augmentation (denoted asDataAug-DETR). It spatially transforms the images and includes multiple augmented versions of each image in the same training batch. Such a simple augmentation strategy already achieves one-to-many matching and surprisingly improves DETR's performance. The second method is One-to-many matching via Feature Augmentation (denoted asFeatAug-DETR). UnlikeDataAug-DETR, it augments the image features instead of the original images and includes multiple augmented features in the same batch to realize one-to-many matching.FeatAug-DETRsignificantly accelerates DETR training and boosts detection performance while keeping the inference speed unchanged. We conduct extensive experiments to evaluate the effectiveness of the proposed approach on DETR variants, including DAB-DETR, Deformable-DETR, and$\mathcal {H}$-Deformable-DETR. Without extra training data,FeatAug-DETRshortens the training convergence periods of Deformable-DETR [1] to 24 epochs and achieves 58.3 AP on COCOval2017set with Swin-L as the backbone.

Given a high-level instruction, the task of Embodied Referring Expression (REVERIE) requires an embodied agent to localise a remote referred object via navigating in the unseen environment. Previous vision-language navigation methods utilise the provided fine-grained instruction as step-by-step navigation guidance to conduct strict instruction-following, while REVERIE aims to achieve efficient goal-oriented exploration according to the high-level command. In this work, we propose a Cross-modal Knowledge Reasoning (abbreviated as CKR+) framework, which incorporates the prior knowledge as decision guidance to learn the navigation scheme comprehensively. Specifically, we design a Room-Object Aware (ROA) mechanism to explicitly decouple the room- and object-related clues from instruction and visual observations. Moreover, we propose a Knowledge-enabled Entity Relation Reasoning (KERR+) module to leverage the structured knowledge from the knowledge graph explicitly and unstructured knowledge from pre-trained model implicitly, to learn the internal-external correlations among room- and object-entities for the agent to make proper decisions. We devise an Entity Prompter (EP) that embeds in the KERR+ module, which utilises the navigation history and visual entities as prompts to transfer knowledge from the pre-trained CLIP model. In addition, we develop a Reinforced End Decider (RED) to learn the stopping scheme specifically, which is achieved by a customised reinforcement learning strategy and knowledge enhanced matching. Two techniques are also introduced to improve navigation efficiency further. Extensive experiments conducted on the REVERIE benchmark demonstrate the effectiveness and superiority of our proposed methods, which boosts the key metrics, i.e., SPL and REVERIE-success rate, to 14.46% and 13.81% respectively.

Learning powerful representations in bird's-eye-view (BEV) for perception tasks is trending and drawing extensive attention both from industry and academia. Conventional approaches for most autonomous driving algorithms perform detection, segmentation, tracking, etc., in a front or perspective view. As sensor configurations get more complex, integrating multi-source information from different sensors and representing features in a unified view come of vital importance. BEV perception inherits several advantages, as representing surrounding scenes in BEV is intuitive and fusion-friendly; and representing objects in BEV is most desirable for subsequent modules as in planning and/or control. The core problems for BEV perception lie in (a) how to reconstruct the lost 3D information via view transformation from perspective view to BEV; (b) how to acquire ground truth annotations in BEV grid; (c) how to formulate the pipeline to incorporate features from different sources and views; and (d) how to adapt and generalize algorithms as sensor configurations vary across different scenarios. In this survey, we review the most recent works on BEV perception and provide an in-depth analysis of different solutions. Moreover, several systematic designs of BEV approach from the industry are depicted as well. Furthermore, we introduce a full suite of practical guidebook to improve the performance of BEV perception tasks, including camera, LiDAR and fusion inputs. At last, we point out the future research directions in this area. We hope this report will shed some light on the community and encourage more research effort on BEV perception.

Human-Object Interaction (HOI) detection aims to understand human activities by detecting interaction triplets. Previous HOI detection methods adopt a two-stage instance-driven paradigm. Unfortunately, many non-interactive human-object pairs generated by the first stage are the main obstacle impeding HOI detectors from high efficiency and promising performance. To remedy this, we propose a novel top-down interaction-driven paradigm, detecting interactions first and bridging interactive human-object pairs through interactions. We formulate HOI as a point triplet human point, interaction point, object point and design a Parallel Point Detection and Matching (PPDM) framework. We further take advantage of two-stage methods and propose a novel framework, PPDM++, that detects the interactive human-object pairs by PPDM, then extracts region features for each pair to predict actions. The core of PPDM/PPDM++ is to convert the instance-driven bottom-up paradigm to an interaction-driven top-down paradigm, thus avoiding additional computation costs from traversing a tremendous number of non-interactive pairs. Benefiting from the advanced paradigm, PPDM/PPDM++ has achieved significant performance gains with high efficiency. PPDM-DLA-34 has achieved 19.94 mAP with 42 FPS as the first real-time HOI detector, and PPDM++-SwinB achieves 30.1 mAP with 17 FPS on HICO-DET dataset. We also built an application-oriented database named HOI-A, a supplement to the existing datasets.

Understanding human posture is a challenging topic, which encompasses several tasks, e.g., pose estimation, body mesh recovery and pose tracking. In this article, we propose a novel Distribution-Aware Single-stage (DAS) model for the pose-related tasks. The proposed DAS model estimates human position and localizes joints simultaneously, which requires only a single pass. Meanwhile, we utilize normalizing flow to enable DAS to learn the true distribution of joint locations, rather than making simple Gaussian or Laplacian assumptions. This provides a pivotal prior and greatly boosts the accuracy of regression-based methods, thus making DAS achieve comparable performance to the volumetric-based methods. We also introduce a recursively update strategy to progressively approach the regression target, reducing the difficulty of regression and improving the regression performance. We further adapt DAS to multi-person mesh recovery and pose tracking tasks and achieve considerable performance on both tasks. Comprehensive experiments on CMU Panoptic and MuPoTS-3D demonstrate the superior efficiency of DAS, specifically 1.5 times speedup over previous best method, and its state-of-the-art accuracy for multi-person pose estimation. Extensive experiments on 3DPW and PoseTrack2018 indicate the effectiveness and efficiency of DAS for human body mesh recovery and pose tracking, respectively, which prove the generality of our proposed DAS model.

We present a simple yet effective end-to-end Video-language Pre-training (VidLP) framework, Masked Contrastive Video-language Pre-training (MAC), for video-text retrieval tasks. Our MAC aims to reduce video representation's spatial and temporal redundancy in the VidLP model by a mask sampling mechanism to improve pre-training efficiency. Comparing conventional temporal sparse sampling, we propose to randomly mask a high ratio of spatial regions and only take visible regions into the encoder as sparse spatial sampling. Similarly, we adopt the mask sampling technique for text inputs for consistency. Instead of blindly applying the mask-then-prediction paradigm from MAE, we propose a masked-then-alignment paradigm for efficient video-text alignment. The motivation is that video-text retrieval tasks rely on high-level alignment rather than low-level reconstruction, and multimodal alignment with masked modeling encourages the model to learn a robust and general multimodal representation from incomplete and unstable inputs. Coupling these designs enables efficient end-to-end pre-training: 3× speed up, 60%+ computation reduction, and 4%+ performance improvement. Our MAC achieves state-of-the-art results on various video-text retrieval datasets including MSR-VTT, DiDeMo, and ActivityNet. Our approach is omnivorous to input modalities. With minimal modifications, we achieve competitive results on image-text retrieval tasks.

iamese and Transformer trackers have demon strated exceptional performance in visual object tracking. These methods utilize initial and potentially online templates to locate the target in subsequent frames. Despite their success, these trackers are vulnerable to changes in the target's appearance due to slow template updates and interference from similar objects, resulting from the absence of scene information. To address these issues, we introduce a reference region within our tracker. The reference region is updated rapidly, providing short-term scene information. By associating the initial template, reference region, and current search region, we enhance the tracker's ability to adapt to changes in target appearance and discriminate between the target and other objects. Additionally, we propose a novel Reference-Enhance (RE) module, which aggregates contextually relevant information from the reference region to enhance the template feature. Extensive experiments show our method achieves state-of-the-art performance on six popular visual object tracking benchmarks while running at over 40 FPS.

Open-vocabulary object detection aims to provide object detectors trained on a fixed set of object categories with the generalizability to detect objects described by arbitrary text queries. Previous methods adopt knowledge distillation to extract knowledge from Pretrained Vision-and-Language Models (PVLMs) and transfer it to detectors. However, due to the non-adaptive proposal cropping and single-level feature mimicking processes, they suffer from information destruction during knowledge extraction and inefficient knowledge transfer. To remedy these limitations, we propose an Object-Aware Distillation Pyramid (OADP) framework, including an Object-Aware Knowledge Extraction (OAKE) module and a Distillation Pyramid (DP) mechanism. When extracting object knowledge from PVLMs, the former adaptively transforms object proposals and adopts object-aware mask attention to obtain precise and complete knowledge of objects. The latter introduces global and block distillation for more comprehensive knowledge transfer to compensate for the missing relation information in object distillation. Extensive experiments show that our method achieves significant improvement compared to current methods. Especially on the MS-COCO dataset, our OADP framework reaches 35.6 mAPN50, surpassing the current state-of-the-art method by 3.3 mAPN50. Code is released at https://github.com/LutingWang/OADP.

The task of Vision-Language Navigation (VLN) is for an embodied agent to reach the global goal according to the instruction. Essentially, during navigation, a series of sub-goals need to be adaptively set and achieved, which is naturally a hierarchical navigation process. However, previous methods leverage a single-step planning scheme, i.e., directly performing navigation action at each step, which is unsuitable for such a hierarchical navigation process. In this paper, we propose an Adaptive Zone-aware Hierarchical Planner (AZHP) to explicitly divides the navigation process into two heterogeneous phases, i.e., sub-goal setting via zone partition/selection (high-level action) and sub-goal executing (low-level action), for hierarchical planning. Specifically, AZHP asynchronously performs two levels of action via the designed State-Switcher Module (SSM). For high-level action, we devise a Scene-aware adaptive Zone Partition (SZP) method to adaptively divide the whole navigation area into different zones on-the-fly. Then the Goal-oriented Zone Selection (GZS) method is proposed to select a proper zone for the current sub-goal. For low-level action, the agent conducts navigation-decision multi-steps in the selected zone. Moreover, we design a Hierarchical RL (HRL) strategy and auxiliary losses with curriculum learning to train the AZHP framework, which provides effective supervision signals for each stage. Extensive experiments demonstrate the superiority of our proposed method, which achieves state-of-the-art performance on three VLN benchmarks (REVERIE, SOON, R2R).

Monocular 3D lane detection is a challenging task due to its lack of depth information. A popular solution is to first transform the front-viewed (FV) images or features into the bird-eye-view (BEV) space with inverse perspective mapping (IPM) and detect lanes from BEV features. However, the reliance of IPM on flat ground assumption and loss of context information make it inaccurate to restore 3D information from BEV representations. An attempt has been made to get rid of BEV and predict 3D lanes from FV representations directly, while it still underperforms other BEV-based methods given its lack of structured representation for 3D lanes. In this paper, we define 3D lane anchors in the 3D space and propose a BEV-free method named Anchor3DLane to predict 3D lanes directly from FV representations. 3D lane anchors are projected to the FV features to extract their features which contain both good structural and context information to make accurate predictions. In addition, we also develop a global optimization method that makes use of the equal-width property between lanes to reduce the lateral error of predictions. Extensive experiments on three popular 3D lane detection benchmarks show that our Anchor3DLane outperforms previous BEV-based methods and achieves state-of-the-art performances. The code is available at: https://github.com/tusenai/Anchor3DLane.

RGB-T tracking aims to leverage the mutual enhancement and complement ability of RGB and TIR modalities for improving the tracking process in various scenarios, where cross-modal interaction is the key component. Some previous methods concatenate the RGB and TIR search region features directly to perform a coarse interaction process with redundant background noises introduced. Many other methods sample candidate boxes from search frames and conduct various fusion approaches on isolated pairs of RGB and TIR boxes, which limits the cross-modal interaction within local regions and brings about inadequate context modeling. To alleviate these limitations, we propose a novel Template-Bridged Search region Interaction (TBSI) module which exploits templates as the medium to bridge the cross-modal interaction between RGB and TIR search regions by gathering and distributing target-relevant object and environment contexts. Original templates are also updated with enriched multimodal contexts from the template medium. Our TBSI module is inserted into a ViT backbone for joint feature extraction, search-template matching, and cross-modal interaction. Extensive experiments on three popular RGB-T tracking benchmarks demonstrate our method achieves new state-of-the-art performances. Code is available at https://github.com/RyanHTR/TBSI.

This paper presents a DETR-based method for cross-domain weakly supervised object detection (CDWSOD), aiming at adapting the detector from source to target domain through weak supervision. We think DETR has strong potential for CDWSOD due to an insight: the encoder and the decoder in DETR are both based on the attention mechanism and are thus capable of aggregating semantics across the entire image. The aggregation results, i.e., image-level predictions, can naturally exploit the weak supervision for domain alignment. Such motivated, we propose DETR with additional Global Aggregation (DETR-GA), a CDWSOD detector that simultaneously makes “instance-level + image-level” predictions and utilizes “strong + weak” supervisions. The key point of DETR-GA is very simple: for the encoder / decoder, we respectively add multiple class queries / a foreground query to aggregate the semantics into image-level predictions. Our query-based aggregation has two advantages. First, in the encoder, the weakly-supervised class queries are capable of roughly locating the corresponding positions and excluding the distraction from non-relevant regions. Second, through our design, the object queries and the foreground query in the decoder share consensus on the class semantics, therefore making the strong and weak supervision mutually benefit each other for domain alignment. Extensive experiments on four popular cross-domain benchmarks show that DETR-GA significantly improves cross-domain detection accuracy (e.g., 29.0% → 79.4% mAP on PASCAL VOC → Clipartalldataset) and advances the states of the art.

The task of weakly supervised temporal action localization targets at generating temporal boundaries for actions of interest, meanwhile the action category should also be classified. Pseudo-label-based methods, which serve as an effective solution, have been widely studied recently. However, existing methods generate pseudo labels during training and make predictions during testing under different pipelines or settings, resulting in a gap between training and testing. In this paper, we propose to generate high-quality pseudo labels from the predicted action boundaries. Nevertheless, we note that existing post-processing, like NMS, would lead to information loss, which is insufficient to generate high-quality action boundaries. More importantly, transforming action boundaries into pseudo labels is quite challenging, since the predicted action instances are generally overlapped and have different confidence scores. Besides, the generated pseudo-labels can be fluctuating and inaccurate at the early stage of training. It might repeatedly strengthen the false predictions if there is no mechanism to conduct self-correction. To tackle these issues, we come up with an effective pipeline for learning better pseudo labels. Firstly, we propose a Gaussian weighted fusion module to preserve information of action instances and obtain high-quality action boundaries. Second, we formulate the pseudo-label generation as an optimization problem under the constraints in terms of the confidence scores of action instances. Finally, we introduce the idea of$\Delta$pseudo labels, which enables the model with the ability of self-correction. Our method achieves superior performance to existing methods on two benchmarks, THUMOS14 and ActivityNet1.3, achieving gains of 1.9% on THUMOS14 and 3.7% on ActivityNet1.3 in terms of average mAP. Our code is available at https://github.com/zhou745/GauFuse_WSTAL.git.

Audio-visual navigation is an audio-targeted wayfinding task where a robot agent is entailed to travel a never-before-seen 3D environment towards the sounding source. In this article, we present ORAN, an omnidirectional audiovisual navigator based on cross-task navigation skill transfer. In particular, ORAN sharpens its two basic abilities for a such challenging task, namely wayfinding and audiovisual information gathering. First, ORAN is trained with a confidence-aware cross-task policy distillation (CCPD) strategy. CCPD transfers the fundamental, point-to-point wayfinding skill that is well trained on the large-scale Point-Goal task to ORAN, so as to help ORAN to better master audio-visual navigation with far fewer training samples. To improve the efficiency of knowledge transfer and address the domain gap, CCPD is made to be adaptive to the decision confidence of the teacher policy. Second, ORAN is equipped with an omnidirectional information gathering (OIG) mechanism, i.e., gleaning visual-acoustic observations from different directions before decision-making. As a result, ORAN yields more robust navigation behaviour. Taking CCPD and OIG together, ORAN significantly outperforms previous competitors. After the model ensemble, we got 1st in Soundspaces Challenge 2022, improving SPL and SR by 53% and 35% relatively.

Multi-agent cooperative perception is an increasingly popular topic in the field of autonomous driving, where roadside LiDARs play an essential role. However, how to optimize the placement of roadside LiDARs is a crucial but often overlooked problem. This paper proposes an approach to optimize the placement of roadside LiDARs by selecting optimized positions within the scene for better perception performance. To efficiently obtain the best combination of locations, a greedy algorithm based on perceptual gain is proposed, which selects the location that can maximize the perceptual gain sequentially. We define perceptual gain as the increased perceptual capability when a new LiDAR is placed. To obtain the perception capability, we propose a perception predictor that learns to evaluate LiDAR placement using only a single point cloud frame. A dataset named Roadside-Opt is created using the CARLA simulator to facilitate research on the roadside LiDAR placement problem. Extensive experiments are conducted to demonstrate the effectiveness of our proposed method.

3D object detection from multi-view images has drawn much attention over the past few years. Existing methods mainly establish 3D representations from multi-view images and adopt a dense detection head for object detection, or employ object queries distributed in 3D space to localize objects. In this paper, we design Multi-View 2D Objects guided 3D Object Detector (MV2D), which can lift any 2D object detector to multi-view 3D object detection. Since 2D detections can provide valuable priors for object existence, MV2D exploits 2D detectors to generate object queries conditioned on the rich image semantics. These dynamically generated queries help MV2D to recall objects in the field of view and show a strong capability of localizing 3D objects. For the generated queries, we design a sparse cross attention module to force them to focus on the features of specific objects, which suppresses interference from noises. The evaluation results on the nuScenes dataset demonstrate the dynamic object queries and sparse feature aggregation can promote 3D detection capability. MV2D also exhibits a state-of-the-art performance among existing methods. We hope MV2D can serve as a new baseline for future research. Code is available at https://github.com/tusen-ai/MV2D.

Music is essential when editing videos, but selecting music manually is difficult and time-consuming. Thus, we seek to automatically generate background music tracks given video input. This is a challenging task since it requires music-video datasets, efficient architectures for video-to-music generation, and reasonable metrics, none of which currently exist. To close this gap, we introduce a complete recipe including dataset, benchmark model, and evaluation metric for video background music generation. We present SymMV, a video and symbolic music dataset with various musical annotations. To the best of our knowledge, it is the first video-music dataset with rich musical annotations. We also propose a benchmark video background music generation framework named V-MusProd, which utilizes music priors of chords, melody, and accompaniment along with video-music relations of semantic, color, and motion features. To address the lack of objective metrics for video-music correspondence, we design a retrieval-based metric VMCP built upon a powerful video-music representation learning model. Experiments show that with our dataset, V-MusProd outperforms the state-of-the-art method in both music quality and correspondence with videos. We believe our dataset, benchmark model, and evaluation metric will boost the development of video background music generation. Our dataset and code are available at https://github.com/zhuole1025/SymMV.

Recently, Vehicle-to-Everything (V2X) cooperative perception has attracted increasing attention. Infrastructure sensors play a critical role in this research field; however, how to find the optimal placement of infrastructure sensors is rarely studied. In this paper, we investigate the problem of infrastructure sensor placement and propose a pipeline that can efficiently and effectively find optimal installation positions for infrastructure sensors in a realistic simulated environment. To better simulate and evaluate LiDAR place-ment, we establish a Realistic LiDAR Simulation library that can simulate the unique characteristics of different popular LiDARs and produce high-fidelity LiDAR point clouds in the CARLA simulator. Through simulating point cloud data in different LiDAR placements, we can evaluate the perception accuracy of these placements using multiple detection models. Then, we analyze the correlation between the point cloud distribution and perception accuracy by calculating the density and uniformity of regions of interest. Experiments show that when using the same number and type of LiDAR, the placement scheme optimized by our proposed method improves the average precision by 15%, compared with the conventional placement scheme in the standard lane scene. We also analyze the correlation between perception performance in the region of interest and LiDAR point cloud distribution and validate that density and uniformity can be indicators of performance. Both the RLS Library and related code will be released at https://github.com/PJLab-ADG/LiDARSimLib-and-Placement-Evaluation.

Audio visual segmentation (AVS) aims to segment the sounding objects for each frame of a given video. To distinguish the sounding objects from silent ones, both audio-visual semantic correspondence and temporal interaction are required. The previous method applies multi-frame cross-modal attention to conduct pixel-level interactions between audio features and visual features of multiple frames simultaneously, which is both redundant and implicit. In this paper, we propose an Audio-Queried Transformer architecture, AQFormer, where we define a set of object queries conditioned on audio information and associate each of them to particular sounding objects. Explicit object-level semantic correspondence between audio and visual modalities is established by gathering object information from visual features with predefined audio queries. Besides, an Audio-Bridged Temporal Interaction module is proposed to exchange sounding object-relevant information among multiple frames with the bridge of audio features. Extensive experiments are conducted on two AVS benchmarks to show that our method achieves state-of-the-art performances, especially 7.1% M_J and 7.6% M_F gains on the MS3 setting.

Panoptic narrative grounding (PNG) aims to segment things and stuff objects in an image described by noun phrases of a narrative caption. As a multimodal task, an essential aspect of PNG is the visual-linguistic interaction between image and caption. The previous two-stage method aggregates visual contexts from offline-generated mask proposals to phrase features, which tend to be noisy and fragmentary. The recent one-stage method aggregates only pixel contexts from image features to phrase features, which may incur semantic misalignment due to lacking object priors. To realize more comprehensive visual-linguistic interaction, we propose to enrich phrases with coupled pixel and object contexts by designing a Phrase-Pixel-Object Transformer Decoder (PPO-TD), where both fine-grained part details and coarse-grained entity clues are aggregated to phrase features. In addition, we also propose a Phrase-Object Contrastive Loss (POCL) to pull closer the matched phrase-object pairs and push away unmatched ones for aggregating more precise object contexts from more phrase-relevant object tokens. Extensive experiments on the PNG benchmark show our method achieves new state-of-the-art performance with large margins.

With the prevalence of multimodal learning, camera-LiDAR fusion has gained popularity in 3D object detection. Many fusion approaches have been proposed, falling into two main categories: sparse-only or dense-only, differentiated by their feature representation within the fusion module. We analyze these approaches within a shared taxonomy, identifying two key challenges: (1) Sparse-only methodologies maintain 3D geometric prior but fail to capture the semantic richness from camera data, and (2) Dense-only strategies preserve semantic continuity at the expense of precise geometric information derived from LiDAR. Upon analysis, we deduce that due to their respective architectural designs, some degree of information loss is inevitable. To counteract this loss, we introduce Sparse Dense Fusion (SD-Fusion), an innovative framework combining both sparse and dense fusion modules via the Transformer architecture. The simple yet effective fusion strategy enhances semantic texture and simultaneously leverages spatial structure data. Employing our SD-Fusion strategy, we assemble two popular methods with moderate performance, achieving a 4.3% increase in mAP and a 2.5% rise in NDS, thus ranking first in the nuScenes benchmark. Comprehensive ablation studies validate the effectiveness of our approach and empirically support our findings.

Vehicle-to-Everything (V2X) collaborative perception is crucial for the advancement of autonomous driving. However, achieving high-precision V2X perception requires a significant amount of annotated real-world data, which can always be expensive and hard to acquire. Simulated data have raised much attention since they can be massively produced at an extremely low cost. Nevertheless, the significant domain gap between simulated and real-world data, including differences in sensor type, reflectance patterns, and road surroundings, often leads to poor performance of models trained on simulated data when evaluated on real-world data. In addition, there remains a domain gap between real-world collaborative agents, e.g. different types of sensors may be installed on autonomous vehicles and roadside infrastructures with different extrinsics, further increasing the difficulty of sim2real generalization. To take full advantage of simulated data, we present a new unsupervised sim2real domain adaptation method for V2X collaborative detection named Decoupled Unsupervised Sim2Real Adaptation (DUSA). Our new method decouples the V2X collaborative sim2real domain adaptation problem into two sub-problems: sim2real adaptation and inter-agent adaptation. For sim2real adaptation, we design a Location-adaptive Sim2Real Adapter (LSA) module to adaptively aggregate features from critical locations of the feature map and align the features between simulated data and real-world data via a sim/real discriminator on the aggregated global feature. For inter-agent adaptation, we further devise a Confidence-aware Inter-agent Adapter (CIA) module to align the fine-grained features from heterogeneous agents under the guidance of agent-wise confidence maps. Experiments demonstrate the effectiveness of the proposed DUSA approach on unsupervised sim2real adaptation from the simulated V2XSet dataset to the real-world DAIR-V2X-C dataset.

When hearing music, it is natural for people to dance to its rhythm. Automatic dance generation, however, is a challenging task due to the physical constraints of human motion and rhythmic alignment with target music. Conventional autoregressive methods introduce compounding errors during sampling and struggle to capture the long-term structure of dance sequences. To address these limitations, we present a novel cascaded motion diffusion model, DiffDance, designed for high-resolution, long-form dance generation. This model comprises a music-to-dance diffusion model and a sequence super-resolution diffusion model. To bridge the gap between music and motion for conditional generation, DiffDance employs a pretrained audio representation learning model to extract music embeddings and further align its embedding space to motion via contrastive loss. During training our cascaded diffusion model, we also incorporate multiple geometric losses to constrain the model outputs to be physically plausible and add a dynamic loss weight that adaptively changes over diffusion timesteps to facilitate sample diversity. Through comprehensive experiments performed on the benchmark dataset AIST++, we demonstrate that DiffDance is capable of generating realistic dance sequences that align effectively with the input music. These results are comparable to those achieved by state-of-the-art autoregressive methods.

Traditional 3D segmentation methods can only recognize a fixed range of classes that appear in the training set, which limits their application in real-world scenarios due to the lack of generalization ability. Large-scale visual-language pre-trained models, such as CLIP, have shown their generalization ability in the zero-shot 2D vision tasks, but are still unable to be applied to 3D semantic segmentation directly. In this work, we focus on zero-shot point cloud semantic segmentation and propose a simple yet effective baseline to transfer the visual-linguistic knowledge implied in CLIP to point cloud encoder at both feature and output levels. Both feature-level and output-level alignments are conducted between 2D and 3D encoders for effective knowledge transfer. Concretely, a Multi-granularity Cross-modal Feature Alignment (MCFA) module is proposed to align 2D and 3D features from global semantic and local position perspectives for feature-level alignment. For the output level, per-pixel pseudo labels of unseen classes are extracted using the pre-trained CLIP model as supervision for the 3D segmentation model to mimic the behavior of the CLIP image encoder. Extensive experiments are conducted on two popular benchmarks of point cloud segmentation. Our method outperforms significantly previous state-of-the-art methods under zero-shot setting (+29.2% mIoU on SemanticKITTI and 31.8% mIoU on nuScenes), and further achieves promising results in the annotation-free point cloud semantic segmentation setting, showing its great potential for label-efficient learning.

In this paper, we present a novel training scheme, namely Teach-DETR, to better train DETR-based detectors from versatile types of teacher detectors. We show that the predicted boxes from teacher detectors are effective medium to transfer knowledge of teacher detectors, which could be either RCNN-based or DETR-based detectors, to train a more accurate and robust DETR model. This new training scheme can easily incorporate the predicted boxes from multiple teacher detectors, each of which provides parallel supervisions to the student DETR. Our strategy introduces no additional parameters and adds negligible computational cost to the original detector during training. During inference, Teach-DETR brings zero additional overhead and maintains the merit of requiring no non-maximum suppression. Extensive experiments show that our method leads to consistent improvement for various DETR-based detectors. Specifically, we improve the state-of-the-art detector DINO Zhang et al. 2022 with Swin-Large Liu et al. 2021 backbone, 4-scale feature pyramid and 36-epoch training schedule, from 57.8% to 58.9% in terms of mean average precision on COCO 2017valset.

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.

Natural language tracking aims to localize the target object referred to by a language description using a sequence of bounding boxes in video frames. Compared with traditional visual single object tracking initialized with only a bounding box (BBox), this task introduces high-level semantic information to reduce the ambiguity of BBox and enhance the ability to retrieve the target in a global manner. Thus, it can yield more accurate and robust tracking results. Previous methods usually adopt off-the-shelf grounding and tracking branches to tackle this task, where feature representations are learned in isolation without benefiting each other. The two branches can associate with each other to discover crucial clues since the language description and the template image provide information from different sources. Therefore, we propose a unified transformer method for natural language tracking named TransNLT, which utilizes isomorphic Transformer structures for grounding and tracking branches where collaborative learning is enabled to construct comprehensive features for the target. In addition, we propose a Selective Feature Gathering (SFG) module which can integrate cross-modal global information of the tracking target from the visual template and language description. Through effective interaction of visual and language information, we can achieve better results than tracking with only a single modality. Extensive experiments on three popular natural language tracking benchmarks show our proposed TransNLT outperforms previous state-of-the-art methods.

Fine-grained face editing, as a special case of image translation task, aims at modifying face attributes according to users' preference. Although generative adversarial networks (GANs) have achieved great success in general image translation tasks, these models cannot be directly applied in the face editing problem. Ideal face editing is challenging as it has two special requirements -- personalization and spatial-awareness. To address these issues, we propose a novel Personalized Spatial-aware Affine Modulation (PSAM) method based on a general GAN structure. The key idea is to modulate the intermediate features in a personalized and spatial-aware manner, which corresponds to the face editing procedure. Specifically, for personalization, we adopt both the face image and the desired attribute as input to generate the modulation tensors. For spatial-aware, we set these tensors to be of the same size as the input image, allowing pixel-wise modulation. Extensive experiments in four fine-grained face editing tasks, i.e., makeup, expression, illumination and aging, demonstrate the effectiveness of the proposed PSAM method. The synthesis results of PSAM can be further boosted by a new transferable training strategy. To facilitate research of face editing, we also construct a new large-scale makeup dataset. The code and dataset are available at http://colalab.org/projects/PSAM.

Model compression is an essential step for large-scale pre-training models toward practical application and deployment on the edge device. However, when conventional compression methods following ‘pre-training then compressing’ two-phase pipeline are applied to Vision-and-Language Pre-training (VLP) models, it will lead to a high calculation and memory overhead. In this work, we break the two-phase pipeline and propose an efficient and effective one-phase VLP model compression mechanism, namedREDUCER, which stands for ‘simultaneously training and compREssing’ VLP model via progressive moDUle replaCing and nEtworkRewiring. Specifically, REDUCER consists of three insightful designs. Firstly, we design a one-phase compression framework to train and compress the VLP model simultaneously to avoid the extra calculation and memory cost caused by an isolated model compression phase in the conventional two-phase pipeline. Secondly, we propose an adaptive progressive module replacing mechanism to compress the model depth free from explicit knowledge distillation losses, relieving the multi-task optimization problems. Thirdly, we integrate pruning techniques into VLP model compression to simultaneously compress the model in width and depth. Overall, we obtain a lightweight VLP model with only one pre-training phase, and it is the first one-phase compression method for VLP models. Extensive experiments have been conducted on representative VLP models,i.e., ClipBERT and VICTOR, and the experimental results show a superior trade-off between performance and efficiency.

Image-based virtual try-on focuses on changing the model's garment item to the target ones and preserving other visual features. To preserve the texture detail of the given in-shop garment, former methods use geometry-based methods (e.g., Thin-plate-spline interpolation) to realize garment warping. However, due to limited degree of freedom, geometry-based methods perform poorly when garment self-occlusion occurs, which is common in daily life. To address this challenge, we propose a novel occlusion-focused virtual try-on system. Compared to previous ones, our system contains three critical submodules, namely, Garment Part Modeling (GPM), a group of Garment Part Generators (GPGs), and Overlap Relation Estimator (ORE). GPM takes the pose landmarks as input, and progressively models the mask of body parts and garments. Based on these masks, GPGs are introduced to generate each garment part. Finally, ORE is proposed to model the overlap relationships between each garment part, and we bind the generated garments under the guidance of overlap relationships predicted by ORE. To make the most of extracted overlap relationships, we proposed an IoU-based hard example mining method for loss terms to handle the sparsity of the self-occlusion samples in the dataset. Furthermore, we introduce part affinity field as pose representation instead of landmark used widely by previous methods and achieve accuracy improvement on try-on layout estimation stage. We evaluate our model on the VITON dataset and found it can outperform previous approaches, especially on samples with garment self-occlusion.

Vision-and-language Navigation (VLN) task requires an embodied agent to navigate to a remote location following a natural language instruction. Previous methods usually adopt a sequence model (e.g., Transformer and LSTM) as the navigator. In such a paradigm, the sequence model predicts action at each step through a maintained navigation state, which is generally represented as a one-dimensional vector. However, the crucial navigation clues (i.e., object-level environment layout) for embodied navigation task is discarded since the maintained vector is essentially unstructured. In this paper, we propose a novel Structured state-Evolution (SEvol) model to effectively maintain the environment layout clues for VLN. Specifically, we utilise the graph-based feature to represent the navigation state instead of the vector-based state. Accordingly, we devise a Reinforced Layout clues Miner (RLM) to mine and detect the most crucial layout graph for long-term navigation via a customised reinforcement learning strategy. Moreover, the Structured Evolving Module (SEM) is proposed to maintain the structured graph-based state during navigation, where the state is gradually evolved to learn the object-level spatial-temporal relationship. The experiments on the R2R and R4R datasets show that the proposed SEvol model improves VLN models' performance by large margins, e.g., +3% absolute SPL accuracy for NvEM and +8% for EnvDrop on the R2R test set.

Referring video object segmentation aims to predict foreground labels for objects referred by natural language expressions in videos. Previous methods either depend on 3D ConvNets or incorporate additional 2D ConvNets as encoders to extract mixed spatial-temporal features. However, these methods suffer from spatial misalignment or false distractors due to delayed and implicit spatial-temporal interaction occurring in the decoding phase. To tackle these limitations, we propose a Language-Bridged Duplex Transfer (LBDT) module which utilizes language as an intermediary bridge to accomplish explicit and adaptive spatial-temporal interaction earlier in the encoding phase. Concretely, cross-modal attention is performed among the temporal encoder, referring words and the spatial encoder to aggregate and transfer language-relevant motion and appearance information. In addition, we also propose a Bilateral Channel Activation (BCA) module in the decoding phase for further denoising and highlighting the spatial-temporal consistent features via channel-wise activation. Extensive experiments show our method achieves new state-of-the-art performances on four popular benchmarks with 6.8% and 6.9% absolute AP gains on A2D Sentences and J-HMDB Sentences respectively, while consuming around 7× less computational overhead11https://github.com/dzh19990407/LBDT.

The task of Human-Object Interaction (HOI) detection could be divided into two core problems, i.e., human-object association and interaction understanding. In this paper, we reveal and address the disadvantages of the conventional query-driven HOI detectors from the two aspects. For the association, previous two-branch methods suffer from complex and costly post-matching, while single-branch methods ignore the features distinction in different tasks. We propose Guided-Embedding Network (GEN) to attain a two-branch pipeline without post-matching. In GEN, we design an instance decoder to detect humans and objects with two independent query sets and a position Guided Embedding (p-GE) to mark the human and object in the same position as a pair. Besides, we design an interaction decoder to classify interactions, where the interaction queries are made of instance Guided Embeddings (i-GE) generated from the outputs of each instance decoder layer. For the interaction understanding, previous methods suffer from long-tailed distribution and zero-shot discovery. This paper proposes Visual-Linguistic Knowledge Transfer (VLKT) training strategy to enhance interaction understanding by transferring knowledge from a visual-linguistic pre-trained model CLIP. In specific, we extract text embeddings for all labels with CLIP to initialize the classifier and adopt a mimic loss to minimize the visual feature distance between GEN and CLIP. As a result, GEN-VLKT outperforms the state of the art by large margins on multiple datasets, e.g., +5.05 mAP on HICO-Det. The source codes are available at https://github.com/YueLiao/gen-vlkt.

3D visual grounding aims to locate the referred target object in 3D point cloud scenes according to a free-form language description. Previous methods mostly follow a two-stage paradigm, i.e., language-irrelevant detection and cross-modal matching, which is limited by the isolated architecture. In such a paradigm, the detector needs to sample keypoints from raw point clouds due to the inherent properties of 3D point clouds (irregular and large-scale), to generate the corresponding object proposal for each keypoint. However, sparse proposals may leave out the target in detection, while dense proposals may confuse the matching model. Moreover, the language-irrelevant detection stage can only sample a small proportion of keypoints on the target, deteriorating the target prediction. In this paper, we propose a 3D Single-Stage Referred Point Progressive Selection (3D-SPS) method, which progressively selects keypoints with the guidance of language and directly locates the target. Specifically, we propose a Description-aware Keypoint Sampling (DKS) module to coarsely focus on the points of language-relevant objects, which are significant clues for grounding. Besides, we devise a Target-oriented Progressive Mining (TPM) module to finely concentrate on the points of the target, which is enabled by progressive intra-modal relation modeling and inter-modal target mining. 3D-SPS bridges the gap between detection and matching in the 3D visual grounding task, localizing the target at a single stage. Experiments demonstrate that 3D-SPS achieves state-of-the-art performance on both ScanRe-fer and Nr3D/Sr3D datasets.

In this paper, we present a novel Distribution-Aware Single-stage (DAS) model for tackling the challenging multi-person 3D pose estimation problem. Different from existing top-down and bottom-up methods, the proposed DAS model simultaneously localizes person positions and their corresponding body joints in the 3D camera space in a one-pass manner. This leads to a simplified pipeline with enhanced efficiency. In addition, DAS learns the true distribution of body joints for the regression of their positions, rather than making a simple Laplacian or Gaussian assumption as previous works. This provides valuable priors for model prediction and thus boosts the regression-based scheme to achieve competitive performance with volumetric-base ones. Moreover, DAS exploits a recur-sive update strategy for progressively approaching to regression target, alleviating the optimization difficulty and further lifting the regression performance. DAS is implemented with a fully Convolutional Neural Network and end-to-end learnable. Comprehensive experiments on benchmarks CMU Panoptic and MuPoTS-3D demonstrate the superior efficiency of the proposed DAS model, specifically 1.5x speedup over previous best model, and its stat-of-the-art accuracy for multi-person 3D pose estimation.

Understanding human and the surrounding context is crucial for the perception of the image and video. It benefits many related applications, such as person search, virtual tryon/makeup, abnormal action detection. In the proposed 4th Person in Context (PIC) workshop, to further promote the progress in the above-mentioned areas, we hold three human-centric perception and cognition challenges including Make-up Temporal Video Grounding (MTVG), Make-up Dense Video Caption (MDVC) and Human-centric Spatio-Temporal Video Grounding (HC-STVG). All the human-centric challenges focus on understanding the human behavior, interactions and relationships in video sequences, which requires understanding both visual and linguistic information, as well as complicated multimodal reasoning. The three sub-problems are complementary and collaboratively contribute to a unified human-centric perception and cognition solution.

Panoptic Narrative Grounding (PNG) is an emerging task whose goal is to segment visual objects of things and stuff categories described by dense narrative captions of a still image. The previous two-stage approach first extracts segmentation region proposals by an off-the-shelf panoptic segmentation model, then conducts coarse region-phrase matching to ground the candidate regions for each noun phrase. However, the two-stage pipeline usually suffers from the performance limitation of low-quality proposals in the first stage and the loss of spatial details caused by region feature pooling, as well as complicated strategies designed for things and stuff categories separately. To alleviate these drawbacks, we propose a one-stage end-to-end Pixel-Phrase Matching Network (PPMN), which directly matches each phrase to its corresponding pixels instead of region proposals and outputs panoptic segmentation by simple combination. Thus, our model can exploit sufficient and finer cross-modal semantic correspondence from the supervision of densely annotated pixel-phrase pairs rather than sparse region-phrase pairs. In addition, we also propose a Language-Compatible Pixel Aggregation (LCPA) module to further enhance the discriminative ability of phrase features through multi-round refinement, which selects the most compatible pixels for each phrase to adaptively aggregate the corresponding visual context. Extensive experiments show that our method achieves new state-of-the-art performance on the PNG benchmark with 4.0 absolute Average Recall gains.

As one of the fundamental functions of autonomous driving system, freespace detection aims at classifying each pixel of the image captured by the camera as drivable or non-drivable. Current works of freespace detection heavily rely on large amount of densely labeled training data for accuracy and robustness, which is time-consuming and laborious to collect and annotate. To the best of our knowledge, we are the first work to explore unsupervised domain adaptation for freespace detection to alleviate the data limitation problem with synthetic data. We develop a cross-modality domain adaptation framework which exploits both RGB images and surface normal maps generated from depth images. A Collaborative Cross Guidance (CCG) module is proposed to leverage the context information of one modality to guide the other modality in a cross manner, thus realizing inter-modality intra-domain complement. To better bridge the domain gap between source domain (synthetic data) and target domain (real-world data), we also propose a Selective Feature Alignment (SFA) module which only aligns the features of consistent foreground area between the two domains, thus realizing inter-domain intra-modality adaptation. Extensive experiments are conducted by adapting three different synthetic datasets to one real-world dataset for freespace detection respectively. Our method performs closely to fully supervised freespace detection methods (93.08% v.s. 97.50% F1 score) and outperforms other general unsupervised domain adaptation methods for semantic segmentation with large margins, which shows the promising potential of domain adaptation for freespace detection.

Vision-language navigation is the task of directing an embodied agent to navigate in 3D scenes with natural language instructions. For the agent, inferring the long-term navigation target from visual-linguistic clues is crucial for reliable path planning, which, however, has rarely been studied before in literature. In this article, we propose a Target-Driven Structured Transformer Planner (TD-STP) for long-horizon goal-guided and room layout-aware navigation. Specifically, we devise an Imaginary Scene Tokenization mechanism for explicit estimation of the long-term target (even located in unexplored environments). In addition, we design a Structured Transformer Planner which elegantly incorporates the explored room layout into a neural attention architecture for structured and global planning. Experimental results demonstrate that our TD-STP substantially improves previous best methods' success rate by 2% and 5% on the test set of R2R and REVERIE benchmarks, respectively. Our code is available at https://github.com/YushengZhao/TD-STP.

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.

In this paper, we address the makeup transfer and removal tasks simultaneously, which aim to transfer the makeup from a reference image to a source image and remove the makeup from the with-makeup image respectively. Existing methods have achieved much advancement in constrained scenarios, but it is still very challenging for them to transfer makeup between images with large pose and expression differences, or handle makeup details like blush on cheeks or highlight on the nose. In addition, they are hardly able to control the degree of makeup during transferring or to transfer a specified part in the input face. These defects limit the application of previous makeup transfer methods to real-world scenarios. In this work, we propose a Pose and expression robust Spatial-aware GAN (abbreviated as PSGAN++). PSGAN++ is capable of performing both detail-preserving makeup transfer and effective makeup removal. For makeup transfer, PSGAN++ uses a Makeup Distill Network (MDNet) to extract makeup information, which is embedded into spatial-aware makeup matrices. We also devise an Attentive Makeup Morphing (AMM) module that specifies how the makeup in the source image is morphed from the reference image, and a makeup detail loss to supervise the model within the selected makeup detail area. On the other hand, for makeup removal, PSGAN++ applies an Identity Distill Network (IDNet) to embed the identity information from with-makeup images into identity matrices. Finally, the obtained makeup/identity matrices are fed to a Style Transfer Network (STNet) that is able to edit the feature maps to achieve makeup transfer or removal. To evaluate the effectiveness of our PSGAN++, we collect a Makeup Transfer In the Wild (MT-Wild) dataset that contains images with diverse poses and expressions and a Makeup Transfer High-Resolution (MT-HR) dataset that contains high-resolution images. Experiments demonstrate that PSGAN++ not only achieves state-of-the-art results with fine makeup details even in cases of large pose/expression differences but also can perform partial or degree-controllable makeup transfer. Both the code and the newly collected datasets will be released at https://github.com/wtjiang98/PSGAN.

In this paper, we target at the Fine-grAined human-Centric Tracklet Segmentation (FACTS) problem, where 12 human parts, e.g., face, pants, left-leg, are segmented. To reduce the heavy and tedious labeling efforts, FACTS requires only one labeled frame per video during training. The small size of human parts and the labeling scarcity makes FACTS very challenging. Considering adjacent frames of videos are continuous and human usually do not change clothes in a short time, we explicitly consider the pixel-level and frame-level context in the proposed Temporal Context segmentation Network (TCNet). On the one hand, optical flow is on-line calculated to propagate the pixel-level segmentation results to neighboring frames. On the other hand, frame-level classification likelihood vectors are also propagated to nearby frames. By fully exploiting the pixel-level and frame-level context, TCNet indirectly uses the large amount of unlabeled frames during training and produces smooth segmentation results during inference. Experimental results on four video datasets show the superiority of TCNet over the state-of-the-arts. The newly annotated datasets can be downloaded via http://liusi-group.com/projects/FACTS for the further studies.

Vision and language understanding techniques have achieved remarkable progress, but currently it is still difficult to well handle problems involving very fine-grained details. For example, when the robot is told to "bring me the book in the girl's left hand", most existing methods would fail if the girl holds one book respectively in her left and right hand. In this work, we introduce a new task named human-centric relation segmentation (HRS), as a fine-grained case of HOI-det. HRS aims to predict the relations between the human and surrounding entities and identify the relation-correlated human parts, which are represented as pixel-level masks. For the above exemplar case, our HRS task produces results in the form of relation triplets 〈girl [left hand], hold, book 〉 and exacts segmentation masks of the book, with which the robot can easily accomplish the grabbing task. Correspondingly, we collect a new Person In Context (PIC) dataset for this new task, which contains 17,122 high-resolution images and densely annotated entity segmentation and relations, including 141 object categories, 23 relation categories and 25 semantic human parts. We also propose a Simultaneous Matching and Segmentation (SMS) framework as a solution to the HRS task. It contains three parallel branches for entity segmentation, subject object matching and human parsing respectively. Specifically, the entity segmentation branch obtains entity masks by dynamically-generated conditional convolutions; the subject object matching branch detects the existence of any relations, links the corresponding subjects and objects by displacement estimation and classifies the interacted human parts; and the human parsing branch generates the pixelwise human part labels. Outputs of the three branches are fused to produce the final HRS results. Extensive experiments on PIC and V-COCO datasets show that the proposed SMS method outperforms baselines with the 36 FPS inference speed. Notably, SMS outperforms the best performing baseline m-KERN with only 17.6 percent time cost. The dataset and code will be released at http://picdataset.com/challenge/index/.

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.

Visual grounding is a task to localize an object described by a sentence in an image. Conventional visual grounding methods extract visual and linguistic features isolatedly and then perform cross-modal interaction in a post-fusion manner. We argue that this post-fusion mechanism does not fully utilize the information in two modalities. Instead, it is more desired to perform cross-modal interaction during the extraction process of the visual and linguistic feature. In this paper, we propose a language-customized visual feature learning mechanism where linguistic information guides the extraction of visual feature from the very beginning. We instantiate the mechanism as a one-stage framework named Progressive Language-customized Visual feature learning (PLV). Our proposed PLV consists of a Progressive Language-customized Visual Encoder (PLVE) and a grounding module. We customize the visual feature with linguistic guidance at each stage of the PLVE by Channel-wise Language-guided Interaction Modules (CLIM). Our proposed PLV outperforms conventional state-of-the-art methods with large margins across five visual grounding datasets without pre-training on object detection datasets, while achieving real-time speed. The source code is available in the supplementary material.

When describing an image, reading text in the visual scene is crucial to understand the key information. Recent work explores the TextCaps task, i.e. image captioning with reading Optical Character Recognition (OCR) tokens, which requires models to read text and cover them in generated captions. Existing approaches fail to generate accurate descriptions because of their (1) poor reading ability; (2) inability to choose the crucial words among all extracted OCR tokens; (3) repetition of words in predicted captions. To this end, we propose a Confidence-aware Non-repetitive Multimodal Transformers (CNMT) to tackle the above challenges. Our CNMT consists of a reading, a reasoning and a generation modules, in which Reading Module employs better OCR systems to enhance text reading ability and a confidence embedding to select the most noteworthy tokens. To address the issue of word redundancy in captions, our Generation Module includes a repetition mask to avoid predicting repeated word in captions. Our model outperforms state-of-the-art models on TextCaps dataset, improving from 81.0 to 93.0 in CIDEr. Our source code is publicly available.

Determining which image regions to concentrate is critical for Human-Object Interaction (HOI) detection. Conventional HOI detectors focus on either detected human and object pairs or pre-defined interaction locations, which limits learning of the effective features. In this paper, we reformulate HOI detection as an adaptive set prediction problem, with this novel formulation, we propose an Adaptive Set-based one-stage framework (AS-Net) with parallel instance and interaction branches. To attain this, we map a trainable interaction query set to an interaction prediction set with transformer. Each query adaptively aggregates the interaction-relevant features from global contexts through multi-head co-attention. Besides, the training process is supervised adaptively by matching each ground-truth with the interaction prediction. Furthermore, we design an effective instance-aware attention module to introduce instructive features from the instance branch into the interaction branch. Our method outperforms previous state-of-the-art methods without any extra human pose and language features on three challenging HOI detection datasets. Especially, we achieve over 31% relative improvement on a large scale HICO-DET dataset. Code is available at https://github.com/yoyomimi/AS-Net.

In recent years, knowledge distillation has been proved to be an effective solution for model compression. This approach can make lightweight student models acquire the knowledge extracted from cumbersome teacher models. However, previous distillation methods of detection have weak generalization for different detection frameworks and rely heavily on ground truth (GT), ignoring the valuable relation information between instances. Thus, we propose a novel distillation method for detection tasks based on discriminative instances without considering the positive or negative distinguished by GT, which is called general instance distillation (GID). Our approach contains a general instance selection module (GISM) to make full use of feature-based, relation-based and response-based knowledge for distillation. Extensive results demonstrate that the student model achieves significant AP improvement and even outperforms the teacher in various detection frame-works. Specifically, RetinaNet with ResNet-50 achieves 39.1% in mAP with GID on COCO dataset, which surpasses the baseline 36.2% by 2.9%, and even better than the ResNet-101 based teacher model with 38.1% AP.

The Remote Embodied Referring Expression (REVERIE) is a recently raised task that requires an agent to navigate to and localise a referred remote object according to a high-level language instruction. Different from related VLN tasks, the key to REVERIE is to conduct goal-oriented exploration instead of strict instruction-following, due to the lack of step-by-step navigation guidance. In this paper, we propose a novel Cross-modality Knowledge Reasoning (CKR) model to address the unique challenges of this task. The CKR, based on a transformer-architecture, learns to generate scene memory tokens and utilise these informative history clues for exploration. Particularly, a Room-and-Object Aware Attention (ROAA) mechanism is devised to explicitly perceive the room- and object-type information from both linguistic and visual observations. Moreover, through incorporating commonsense knowledge, we propose a Knowledge-enabled Entity Relationship Reasoning (KERR) module to learn the internal-external correlations among room- and object-entities for agent to make proper action at each viewpoint. Evaluation on REVERIE benchmark demonstrates the superiority of the CKR model, which significantly boosts SPL and REVERIE-success rate by 64.67% and 46.05%, respectively. Code is available at: https://github.com/alloldman/CKR.

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.

To address the challenging task of instance-aware human part parsing, a new bottom-up regime is proposed to learn category-level human semantic segmentation as well as multi-person pose estimation in a joint and end-to-end manner. It is a compact, efficient and powerful framework that exploits structural information over different human granularities and eases the difficulty of person partitioning. Specifically, a dense-to-sparse projection field, which allows explicitly associating dense human semantics with sparse keypoints, is learnt and progressively improved over the network feature pyramid for robustness. Then, the difficult pixel grouping problem is cast as an easier, multi-person joint assembling task. By formulating joint association as maximum-weight bipartite matching, a differentiable solution is developed to exploit projected gradient descent and Dykstra’s cyclic projection algorithm. This makes our method end-to-end trainable and allows back-propagating the grouping error to directly supervise multi-granularity human representation learning. This is distinguished from current bottom-up human parsers or pose estimators which require sophisticated post-processing or heuristic greedy algorithms. Experiments on three instance-aware human parsing datasets show that our model outperforms other bottom-up alternatives with much more efficient inference.

Editing an image automatically via a linguistic request can significantly save laborious manual work and is friendly to photography novice. In this paper, we focus on the task of language-guided global image editing. Existing works suffer from imbalanced and insufficient data distribution of real-world datasets and thus fail to understand language requests well. To handle this issue, we propose to create a cycle with our image generator by creating a novel model called Editing Description Network (EDNet) which predicts an editing embedding given a pair of images. Given the cycle, we propose several free augmentation strategies to help our model understand various editing requests given the imbalanced dataset. In addition, two other novel ideas are proposed: an Image-Request Attention (IRA) module which allows our method to edit an image spatial-adaptively when the image requires different editing degree at different regions, as well as a new evaluation metric for this task which is more semantic and reasonable than conventional pixel losses (e.g. L1). Extensive experiments on two benchmark datasets demonstrate the effectiveness of our method over existing approaches.

In this work, we address the task of video background music generation. Some previous works achieve effective music generation but are unable to generate melodious music specifically for a given video, and none of them considers the video-music rhythmic consistency. To generate the background music that matches the given video, we first establish the rhythmic relationships between video and background music. In particular, we connect timing, motion speed, and motion saliency from video with beat, simu-note density, and simu-note strength from music, respectively. We then propose CMT, a Controllable Music Transformer that enables the local control of the aforementioned rhythmic features, as well as the global control of the music genre and the used instrument specified by users. Objective and subjective evaluations show that the generated background music has achieved satisfactory compatibility with the input videos, and at the same time, impressive music quality.

Recently proposed fine-grained 3D visual grounding is an essential and challenging task, whose goal is to identify the 3D object referred by a natural language sentence from other distractive objects of the same category. Existing works usually adopt dynamic graph networks to indirectly model the intra/inter-modal interactions, making the model difficult to distinguish the referred object from distractors due to the monolithic representations of visual and linguistic contents. In this work, we exploit Transformer for its natural suitability on permutation-invariant 3D point clouds data and propose a TransRefer3D network to extract entity-and-relation aware multimodal context among objects for more discriminative feature learning. Concretely, we devise an Entity-aware Attention (EA) module and a Relation-aware Attention (RA) module to conduct fine-grained cross-modal feature matching. Facilitated by co-attention operation, our EA module matches visual entity features with linguistic entity features while RA module matches pair-wise visual relation features with linguistic relation features, respectively. We further integrate EA and RA modules into an Entity-and-Relation aware Contextual Block (ERCB) and stack several ERCBs to form our TransRefer3D for hierarchical multimodal context modeling. Extensive experiments on both Nr3D and Sr3D datasets demonstrate that our proposed model significantly outperforms existing approaches by up to 10.6% and claims the new state-of-the-art performance. To the best of our knowledge, this is the first work investigating Transformer architecture for fine-grained 3D visual grounding task.

Two-stage methods have dominated Human-Object Interaction~(HOI) detection for several years. Recently, one-stage HOI detection methods have become popular. In this paper, we aim to explore the essential pros and cons of two-stage and one-stage methods. With this as the goal, we find that conventional two-stage methods mainly suffer from positioning positive interactive human-object pairs, while one-stage methods are challenging to make an appropriate trade-off on multi-task learning, \emph{i.e.}, object detection, and interaction classification. Therefore, a core problem is how to take the essence and discard the dregs from the conventional two types of methods. To this end, we propose a novel one-stage framework with disentangling human-object detection and interaction classification in a cascade manner. In detail, we first design a human-object pair generator based on a state-of-the-art one-stage HOI detector by removing the interaction classification module or head and then design a relatively isolated interaction classifier to classify each human-object pair. Two cascade decoders in our proposed framework can focus on one specific task, detection or interaction classification. In terms of the specific implementation, we adopt a transformer-based HOI detector as our base model. The newly introduced disentangling paradigm outperforms existing methods by a large margin, with a significant relative mAP gain of 9.32% on HICO-Det. The source codes are available at https://github.com/YueLiao/CDN.

In this paper, we are tackling the weakly-supervised referring expression grounding task, for the localization of a referent object in an image according to a query sentence, where the mapping between image regions and queries are not available during the training stage. In traditional methods, an object region that best matches the referring expression is picked out, and then the query sentence is reconstructed from the selected region, where the reconstruction difference serves as the loss for back-propagation. The existing methods, however, conduct both the matching and the reconstruction approximately as they ignore the fact that the matching correctness is unknown. To overcome this limitation, a discriminative triad is designed here as the basis to the solution, through which a query can be converted into one or multiple discriminative triads in a very scalable way. Based on the discriminative triad, we further propose the triad-level matching and reconstruction modules which are lightweight yet effective for the weakly-supervised training, making it three times lighter and faster than the previous state-of-the-art methods. One important merit of our work is its superior performance despite the simple and neat design. Specifically, the proposed method achieves a new state-of-the-art accuracy when evaluated on RefCOCO (39.21 percent), RefCOCO+ (39.18 percent) and RefCOCOg (43.24 percent) datasets, that is 4.17, 4.08 and 7.8 percent higher than the previous one, respectively. The code is available at https://github.com/insomnia94/DTWREG.

The goal of referring image segmentation is to identify the object matched with an input natural language expression. Previous methods only support English descriptions, whereas Chinese is also broadly used around the world, which limits the potential application of this task. Therefore, we propose to extend existing datasets with Chinese descriptions and preprocessing tools for training and evaluating bilingual referring segmentation models. In addition, previous methods also lack the ability to collaboratively learn channel-wise and spatial-wise cross-modal attention to well align visual and linguistic modalities. To tackle these limitations, we propose a Linguistic Excitation module to excite image channels guided by language information and a Linguistic Aggregation module to aggregate multimodal information based on image-language relationships. Since different levels of features from the visual backbone encode rich visual information, we also propose a Cross-Level Attentive Fusion module to fuse multilevel features gated by language information. Extensive experiments on four English and Chinese benchmarks show that our bilingual referring image segmentation model outperforms previous methods.

Scene graph generation has received increasing attention in recent years. Enhancing the predicate representations is an important entry point to this task. There are various methods to fully investigate the context of representation enhancement. In this brief, we analyze the decisive factors that can significantly affect the relation detection results. Our analysis shows that spatial correlations between objects, focused regions of objects, and global hints related to the relations have strong influences in relation prediction and contradiction elimination. Based on our analysis, we propose a hierarchical context network (HCNet) to generate a scene graph. HCNet consists of three contexts, including interaction context, depression context, and global context, which integrates information from pair, object, and graph levels. The experiments show that our method outperforms the state-of-the-art methods on the Visual Genome (VG) data set.

Representation learning on a knowledge graph (KG) is to embed entities and relations of a KG into low-dimensional continuous vector spaces. Early KG embedding methods only pay attention to structured information encoded in triples, which would cause limited performance due to the structure sparseness of KGs. Some recent attempts consider paths information to expand the structure of KGs but lack explainability in the process of obtaining the path representations. In this paper, we propose a novel Rule and Path-based Joint Embedding (RPJE) scheme, which takes full advantage of the explainability and accuracy of logic rules, the generalization of KG embedding as well as the supplementary semantic structure of paths. Specifically, logic rules of different lengths (the number of relations in rule body) in the form of Horn clauses are first mined from the KG and elaborately encoded for representation learning. Then, the rules of length 2 are applied to compose paths accurately while the rules of length 1 are explicitly employed to create semantic associations among relations and constrain relation embeddings. Moreover, the confidence level of each rule is also considered in optimization to guarantee the availability of applying the rule to representation learning. Extensive experimental results illustrate that RPJE outperforms other state-of-the-art baselines on KG completion task, which also demonstrate the superiority of utilizing logic rules as well as paths for improving the accuracy and explainability of representation learning.

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.

Neural Architecture Search (NAS) that aims to automate the procedure of architecture design has achieved promising results in many computer vision fields. In this paper, we propose an AdversarialNAS method specially tailored for Generative Adversarial Networks (GANs) to search for a superior generative model on the task of unconditional image generation. The AdversarialNAS is the first method that can search the architectures of generator and discriminator simultaneously in a differentiable manner. During searching, the designed adversarial search algorithm does not need to comput any extra metric to evaluate the performance of the searched architecture, and the search paradigm considers the relevance between the two network architectures and improves their mutual balance. Therefore, AdversarialNAS is very efficient and only takes 1 GPU day to search for a superior generative model in the proposed large search space. Experiments demonstrate the effectiveness and superiority of our method. The discovered generative model sets a new state-of-the-art FID score of 10.87 and highly competitive Inception Score of 8.74 on CIFAR-10. Its transferability is also proven by setting new state-of-the-art FID score of 26.98 and Inception score of 9.63 on STL-10. Code is at: https://github.com/chengaopro/AdversarialNAS.

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.

In this paper, we address the makeup transfer task, which aims to transfer the makeup from a reference image to a source image. Existing methods have achieved promising progress in constrained scenarios, but transferring between images with large pose and expression differences is still challenging. Besides, they cannot realize customizable transfer that allows a controllable shade of makeup or specifies the part to transfer, which limits their applications. To address these issues, we propose Pose and expression robust Spatial-aware GAN (PSGAN). It first utilizes Makeup Distill Network to disentangle the makeup of the reference image as two spatial-aware makeup matrices. Then, Attentive Makeup Morphing module is introduced to specify how the makeup of a pixel in the source image is morphed from the reference image. With the makeup matrices and the source image, Makeup Apply Network is used to perform makeup transfer. Our PSGAN not only achieves state-of-the-art results even when large pose and expression differences exist but also is able to perform partial and shade-controllable makeup transfer. Both the code and a newly collected dataset containing facial images with various poses and expressions will be available at https://github.com/wtjiang98/PSGAN.

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.

We propose a single-stage Human-Object Interaction (HOI) detection method that has outperformed all existing methods on HICO-DET dataset at 37 fps on a single Titan XP GPU. It is the first real-time HOI detection method. Conventional HOI detection methods are composed of two stages, i.e., human-object proposals generation, and proposals classification. Their effectiveness and efficiency are limited by the sequential and separate architecture. In this paper, we propose a Parallel Point Detection and Matching (PPDM) HOI detection framework. In PPDM, an HOI is defined as a point triplet. Human and object points are the center of the detection boxes, and the interaction point is the midpoint of the human and object points. PPDM contains two parallel branches, namely point detection branch and point matching branch. The point detection branch predicts three points. Simultaneously, the point matching branch predicts two displacements from the interaction point to its corresponding human and object points. The human point and the object point originated from the same interaction point are considered as matched pairs. In our novel parallel architecture, the interaction points implicitly provide context and regularization for human and object detection. The isolated detection boxes unlikely to form meaningful HOI triplets are suppressed, which increases the precision of HOI detection. Moreover, the matching between human and object detection boxes is only applied around limited numbers of filtered candidate interaction points, which saves much computational cost. Additionally, we build a new application-oriented database named as HOI-A, which serves as a good supplement to the existing datasets.

Compared with the widely studied Human-Object Interaction DE-Tection (HOI-DET), no effort has been devoted to its inverse problem, i.e. to generate an HOI scene image according to the given relationship triplet , to our best knowledge. We term this new task "Human-Object Interaction Image Generation" (HOI-IG). HOI-IG is a research-worthy task with great application prospects, such as online shopping, film production and interactive entertainment. In this work, we introduce an Interact-GAN to solve this challenging task. Our method is composed of two stages: (1) manipulating the posture of a given human image conditioned on a predicate. (2) merging the transformed human image and object image to one realistic scene image while satisfying the ir expected relative position and ratio. Besides, to address the large spatial misalignment issue caused by fusing two images content with reasonable spatial layout, we propose a Relation-based Spatial Transformer Network (RSTN) to adaptively process the images conditioned on their interaction. Extensive experiments on two challenging datasets demonstrate the effectiveness and superiority of our approach. We advocate for the image generation community to draw more attention to the new Human-Object Interaction Image Generation problem. To facilitate future research, our project will be released at: http://colalab.org/projects/InteractGAN.

Customizable makeup transfer, which aims to transfer the makeup from an arbitrary reference face to a source face, is widely demanded in many applications such as short video platforms and online meeting applications. However, existing methods are neither user-friendly nor sufficiently fast. In this demo, we present the first fast makeup transfer system named as Fast Pose and expression robust Spatial-Aware GAN (FPSGAN). With a novel Attentive Makeup Morphing (AMM) module, FPSGAN is robust to face pose and expression. Moreover, it can achieve shade-controllable and partial makeup, improving the system's user-friendliness. In addition, FPSGAN is light-weighted and fast. To sum up, FPSGAN is the first fast customizable makeup transfer system to enable users to beautify themselves as they like.

Video relation detection problem refers to the detection of the relationship between different objects in videos, such as spatial relationship and action relationship. In this paper, we present video relation detection with trajectory-aware multi-modal features to solve this task. Considering the complexity of doing visual relation detection in videos, we decompose this task into three sub-tasks: object detection, trajectory proposal and relation prediction. We use the state-of-the-art object detection method to ensure the accuracy of object trajectory detection and multi-modal feature representation to help the prediction of relation between objects. Our method won the first place on the video relation detection task of Video Relation Understanding Grand Challenge in ACM Multimedia 2020 with 11.74% mAP, which surpasses other methods by a large margin.

Phrase grounding aims to localize the objects described by phrases in a natural language specification. Previous works model the interaction of inputs from text modality and visual modality only in the intra-modal global level and consequently lacks the ability to capture the precise and complete context information. In this paper, we propose a novel Cross-Modal Omni Interaction network (COI Net) composed of a neighboring interaction module, a global interaction module, a cross-modal interaction module and a multilevel alignment module. Our approach formulates the complex spatial and semantic relationship among image regions and phrases through multi-level multi-modal interaction. We capture the local relationship using the interaction among neighboring regions and then collect the global context through the interaction among all regions using a transformer encoder. We further use a co-attention module to apply the interaction between two modalities to gather the cross-modal context for all image regions and phrases. In addition to the omni interaction modeling, we also leverage a straightforward yet effective multilevel alignment regularization to formulate the dependencies among all grounding decisions. We extensively validate the effectiveness of our model. Experiments show that our approach outperforms existing state-of-the-art methods by large margins on two popular datasets in terms of accuracy: 6.15% on Flickr30K Entities (71.36% increased to 77.51%) and 21.25% on ReferItGame (44.91% increased to 66.16%). The code of our implementation is available at https://github.com/yiranyyu/Phrase-Grounding.

Learning to capture dependencies between spatial positions is essential to many visual tasks, especially the dense labeling problems like scene parsing. Existing methods can effectively capture long-range dependencies with self-attention mechanism while short ones by local convolution. However, there is still much gap between long-range and short-range dependencies, which largely reduces the models' flexibility in application to diverse spatial scales and relationships in complicated natural scene images. To fill such a gap, we develop a Middle-Range (MR) branch to capture middle-range dependencies by restricting self-attention into local patches. Also, we observe that the spatial regions which have large correlations with others can be emphasized to exploit long-range dependencies more accurately, and thus propose a Reweighed Long-Range (RLR) branch. Based on the proposed MR and RLR branches, we build an Omni-Range Dependencies Network (ORDNet) which can effectively capture short-, middle- and long-range dependencies. Our ORDNet is able to extract more comprehensive context information and well adapt to complex spatial variance in scene images. Extensive experiments show that our proposed ORDNet outperforms previous state-of-the-art methods on three scene parsing benchmarks including PASCAL Context, COCO Stuff and ADE20K, demonstrating the superiority of capturing omni-range dependencies in deep models for scene parsing task.

Semantic segmentation is an important computer vision task, which aims to allocate a semantic label to each pixel in an image. When training a segmentation model, it is common to fine-tune a classification network pre-trained on a large-scale dataset. However, as an intrinsic property of the classification model, invariance to spatial perturbation resulting from the lose of detail-sensitivity prevents segmentation networks from achieving high performance. The use of standard poolings is one of the key factors for this invariance. The most common standard poolings are max and average pooling. Max pooling can increase both the invariance to spatial perturbations and the non-linearity of the networks. Average pooling, on the other hand, is sensitive to spatial perturbations, but is a linear function. For semantic segmentation, we prefer both the preservation of detailed cues within a local feature region and non-linearity that increases a network's functional complexity. In this work, we propose a polynomial pooling (P-pooling) function that finds an intermediate form between max and average pooling to provide an optimally balanced and self-adjusted pooling strategy for semantic segmentation. The P-pooling is differentiable and can be applied into a variety of pre-trained networks. Extensive studies on the PASCAL VOC, Cityscapes and ADE20k datasets demonstrate the superiority of P-pooling over other poolings. Experiments on various network architectures and state-of-the-art training strategies also show that models with P-pooling layers consistently outperform those directly fine-tuned using pre-trained classification models.

RGB-Infrared (IR) person re-identification is an important and challenging task due to large cross-modality variations between RGB and IR images. Most conventional approaches aim to bridge the cross-modality gap with feature alignment by feature representation learning. Different from existing methods, in this paper, we propose a novel and end-to-end Alignment Generative Adversarial Network (AlignGAN) for the RGB-IR RE-ID task. The proposed model enjoys several merits. First, it can exploit pixel alignment and feature alignment jointly. To the best of our knowledge, this is the first work to model the two alignment strategies jointly for the RGB-IR RE-ID problem. Second, the proposed model consists of a pixel generator, a feature generator and a joint discriminator. By playing a min-max game among the three components, our model is able to not only alleviate the cross-modality and intra-modality variations, but also learn identity-consistent features. Extensive experimental results on two standard benchmarks demonstrate that the proposed model performs favourably against state-of-the-art methods. Especially, on SYSU-MM01 dataset, our model can achieve an absolute gain of 15.4% and 12.9% in terms of Rank-1 and mAP.

Noticeable progress has been witnessed in general object detection, semantic segmentation and instance segmentation, while parsing a group of people is still a challenging task for human-centric visual understanding due to severe occlusion and various poses. In this paper, we present a new large-scale dataset named “GPS (Group People Segmentation)” to boost academical study and technology development. GPS contains 14000 elaborately annotated images with 20 fine-grained semantic category labels related to human, divided into two sub-datasets corresponding to indoor and outdoor scenes involving various poses, occlusion and background. We further propose a novel GPSNet for group people segmentation. GPSNet consists of a new “Adjusted RoI Align” module to adjust position of detected person and align RoI features, such that the network does not need to fit various positions of each person. A fusion of global and local features is also employed to refine parsing results. Compared with baseline methods, GPSNet achieves the best performance on GPS Dataset.

Image retrieval in complicated scene is a challenging task that requires the comprehensive understanding of an image. In this paper, we propose a scene graph based image retrieval framework that combines the scene graph generation with image retrieval and fine tuning the searching results via a dialogue mechanism. Specifically, we proposed an image retrieval oriented scene graph generation model that takes an image and a text describing the image as inputs. The additional text input is used to control the generated scene graph. It provides information for a newly introduced attributes head to better predict the attributes and helps constructing an adjacency matrix at the same time. Graph Convolutional Network is further used to gather information among nodes for precise relation estimation. Moreover, modification on the scene graph can be done by changing the text. Our proposed approach achieves the state-of-the-art performances in both scene graph based image retrieval and scene graph generation in the Visual Genome dataset.

Similarity-preserving hashing is a widely used method for nearest neighbor search in large-scale image retrieval tasks. Considerable research has been conducted on deep-network-based hashing approaches to improve the performance. However, the binary codes generated from deep networks may be not uniformly distributed over the Hamming space, which will greatly increase the retrieval time. To this end, we propose a deep-network-based multi-index hashing (MIH) for retrieval efficiency. We first introduce the MIH mechanism into the proposed deep architecture, which divides the binary codes into multiple substrings. Each substring corresponds to one hash table. Then, we add the two balanced constraints to obtain more uniformly distributed binary codes: 1) balanced substrings, where the Hamming distances of each substring are equal for any two binary codes and 2) balanced hash buckets, where the sizes of each bucket are equal. Extensive evaluations on several benchmark image retrieval data sets show that the learned balanced binary codes bring dramatic speedups and achieve comparable performance over the existing baselines.

This paper presents an intelligent system named Magic-wall, which enables visualization of the effect of room decoration automatically. Concretely, given an image of the indoor scene and a preferred color, the Magic-wall can automatically locate the wall regions in the image and smoothly replace the existing wall with the required one. The key idea of the proposed Magic-wall is to leverage visual semantics to guide the entire process of color substitution, including wall segmentation and replacement. To strengthen the reality of visualization, we make the following contributions. First, we propose an edge-aware fully convolutional neural network (Edge-aware-FCN) for indoor semantic scene parsing, in which a novel edge-prior branch is introduced to identify the boundary of different semantic regions better. To further polish the details between the wall and other semantic regions, we leverage the output of Edge-aware-FCN as the prior knowledge, concatenating with the image to form a new input for the Enhanced-Net. In such a case, the Enhanced-Net is able to capture more semantic-aware information from the input and polish some ambiguous regions. Finally, to naturally replace the color of the original walls, a simple yet effective color space conversion method is proposed for replacement with brightness reserved. We build a new indoor scene dataset upon ADE20K for training and testing, which includes six semantic labels. Extensive experimental evaluations and visualizations well demonstrate that the proposed Magic-wall is effective and can automatically generate a set of visually pleasing results.

In this paper, we propose a design scheme for deep learning networks in face parsing task with promising accuracy and real-time inference speed. By analyzing the differences between general image parsing task and face parsing task, we first revisit the structure of traditional FCN and make improvements to adapt to the unique properties of face parsing task. Especially, the concept of Normalized Receptive Field is proposed to give more insights on designing the network. Then a novel loss function called Statistical Contextual Loss is introduced, which integrates richer contextual information and regularizes features during training. For further model acceleration, we propose a semi-supervised distillation scheme that effectively transfers the learned knowledge to a lighter network. Extensive experiments on LFW and Helen dataset demonstrate the significant superiority of the new design scheme on both efficacy and efficiency.

Product display in e-commerce commonly uses static images or videos. In this paper, we design a novel video composition system “RotateView” which displays real-world products videos on the mobile phone in an interactive and 3D-like way. The system estimates the rotation direction of products using optical flow, segments products using an improved version of online adaptive video object segmentation, and adjusts motion and color for composition. The rotation direction estimation methods are evaluated on a video dataset of 1500 rotated videos that are uploaded by sellers, and on our collected real-world video object segmentation (RVOS) dataset. On our RVOS dataset, experimental results show an improvement in segmentation over the state of the art. Moreover, the proposed algorithms for motion and color adjustment are evaluated using extensive user studies. The RVOS dataset can be downloaded viahttps://realvos.github.io/for further studies and code will be made available.

Human parsing has been extensively studied recently due to its wide applications in many important scenarios. Mainstream fashion parsing models (i.e., parsers) focus on parsing the high-resolution and clean images. However, directly applying the parsers trained on benchmarks of high-quality samples to a particular application scenario in the wild, e.g., a canteen, airport or workplace, often gives non-satisfactory performance due to domain shift. In this paper, we explore a new and challenging cross-domain human parsing problem: taking the benchmark dataset with extensive pixel-wise labeling as the source domain, how to obtain a satisfactory parser on a new target domain without requiring any additional manual labeling? To this end, we propose a novel and efficient cross-domain human parsing model to bridge the cross-domain differences in terms of visual appearance and environment conditions and fully exploit commonalities across domains. Our proposed model explicitly learns a feature compensation network, which is specialized for mitigating the cross-domain differences. A discriminative feature adversarial network is introduced to supervise the feature compensation to effectively reduces the discrepancy between feature distributions of two domains. Besides, our proposed model also introduces a structured label adversarial network to guide the parsing results of the target domain to follow the high-order relationships of the structured labels shared across domains. The proposed framework is end-to-end trainable, practical and scalable in real applications. Extensive experiments are conducted where LIP dataset is the source domain and 4 different datasets including surveillance videos, movies and runway shows without any annotations, are evaluated as target domains. The results consistently confirm data efficiency and performance advantages of the proposed method for the challenging cross-domain human parsing problem.

Softmax loss is arguably one of the most popular losses to train CNN models for image classification. However, recent works have exposed its limitation on feature discriminability. This paper casts a new viewpoint on the weakness of softmax loss. On the one hand, the CNN features learned using the softmax loss are often inadequately discriminative. We hence introduce a soft-margin softmax function to explicitly encourage the discrmination between different classes. On the other hand, the learned classifier of softmax loss is weak. We propose to assemble multiple these weak classifiers to a strong one, inspired by the recognition that the diversity among weak classifiers is critical to a good ensemble. To achieve the diversity, we adopt the Hilbert-Schmidt Independence Criterion (HSIC). Considering these two aspects in one framework, we design a novel loss, named as Ensemble Soft-Margin Softmax (EM-Softmax). Extensive experiments on benchmark datasets are conducted to show the superiority of our design over the baseline softmax loss and several state-of-the-art alternatives.

Facial makeup transfer aims to translate the makeup style from a given reference makeup face image to another non-makeup one while preserving face identity. Such an instance-level transfer problem is more challenging than conventional domain-level transfer tasks, especially when paired data is unavailable. Makeup style is also different from global styles (e.g., paintings) in that it consists of several local styles/cosmetics, including eye shadow, lipstick, foundation, and so on. Extracting and transferring such local and delicate makeup information is infeasible for existing style transfer methods. We address the issue by incorporating both global domain-level loss and local instance-level loss in an dual input/output Generative Adversarial Network, called BeautyGAN. Specifically, the domain-level transfer is ensured by discriminators that distinguish generated images from domains' real samples. The instance-level loss is calculated by pixel-level histogram loss on separate local facial regions. We further introduce perceptual loss and cycle consistency loss to generate high quality faces and preserve identity. The overall objective function enables the network to learn translation on instance-level through unsupervised adversarial learning. We also build up a new makeup dataset that consists of 3834 high-resolution face images. Extensive experiments show that BeautyGAN could generate visually pleasant makeup faces and accurate transferring results. Data and code are available at http://liusi-group.com/projects/BeautyGAN.

This article summarizes the corresponding half-day tutorial at ACM Multimedia 2018. This tutorial reviews recent progresses for pixel-level understanding with structured deep learning, including 1) human-centric analysis: human parsing and pose estimation; 2) part-based analysis: object part and face parsing; 3) weakly-supervised analysis: object localization and semantic segmentation; 4) depth estimation: stereo matching.

In this paper, we introduce a novel approach to automatically regulate receptive fields in deep image parsing networks. Unlike previous work which placed much importance on obtaining better receptive fields using manually selected dilated convolutional kernels, our approach uses two affine transformation layers in the network's backbone and operates on feature maps. Feature maps are inflated or shrunk by the new layer, thereby changing the receptive fields in the following layers. By use of end-to-end training, the whole framework is data-driven, without laborious manual intervention. The proposed method is generic across datasets and different tasks. We have conducted extensive experiments on both general image parsing tasks, and face parsing tasks as concrete examples, to demonstrate the method's superior ability to regulate over manual designs.

This paper presents a robust joint discriminative appearance model-based tracking method using online random forests and mid-level feature (superpixels). To achieve superpixel-wise discriminative ability, we propose a joint appearance model that consists of two random forest-based models, i.e., the background-target discriminative model (BTM) and the distractor-target discriminative model (DTM). More specifically, the BTM effectively learns discriminative information between the target object and the background. In contrast, the DTM is used to suppress distracting superpixels, which significantly improves the tracker's robustness and alleviates the drifting problem. A novel online random forest regression algorithm is proposed to build the two models. The BTM and DTM are linearly combined into a joint model to compute a confidence map. Tracking results are estimated using the confidence map, in which the position and scale of the target are estimated orderly. Furthermore, we design a model updating strategy to adapt the appearance changes over time by discarding degraded trees of the BTM and DTM and initializing new trees as replacements. We test the proposed tracking method on two large tracking benchmarks, the CVPR2013 tracking benchmark and VOT2014 tracking challenge. Experimental results show that the tracker runs at real-time speed and achieves favorable tracking performance compared with the state-of-the-art methods. The results also suggest that the DTM improves tracking performance significantly and plays an important role in robust tracking.

Image retargeting has been applied to display images of any size via devices with various resolutions (e.g., cell phone, TV monitors). To fit an image with the target resolution, certain unimportant regions need to be deleted or distorted and the key problem is to determine the importance of each pixel. Existing methods predict pixel-wise importance in a bottom-up manner via eye fixation estimation or saliency detection. In contrast, the proposed algorithm estimates the pixel-wise importance based on a top-down criterion where the target image maintains the semantic meaning of the original image. To this end, several semantic components corresponding to foreground objects, action contexts, and background regions are extracted. The semantic component maps are integrated by a classification guided fusion network. Specifically, the deep network classifies the original image as object or scene-oriented, and fuses the semantic component maps according to classification results. The network output, referred to as the semantic collage with the same size as the original image, is then fed into any existing optimization method to generate the target image. Extensive experiments are carried out on the RetargetMe dataset and S-Retarget database developed in this work. Experimental results demonstrate the merits of the proposed algorithm over the state-of-the-art image retargeting methods.

In this paper, we propose a novel correlation particle filter (CPF) for robust visual tracking. Instead of a simple combination of a correlation filter and a particle filter, we exploit and complement the strength of each one. Compared with existing tracking methods based on correlation filters and particle filters, the proposed tracker has four major advantages: 1) it is robust to partial and total occlusions, and can recover from lost tracks by maintaining multiple hypotheses; 2) it can effectively handle large-scale variation via a particle sampling strategy; 3) it can efficiently maintain multiple modes in the posterior density using fewer particles than conventional particle filters, resulting in low computational cost; and 4) it can shepherd the sampled particles toward the modes of the target state distribution using a mixture of correlation filters, resulting in robust tracking performance. Extensive experimental results on challenging benchmark data sets demonstrate that the proposed CPF tracking algorithm performs favorably against the state-of-the-art methods.

Surveillance video parsing, which segments the video frames into several labels, e.g., face, pants, left-leg, has wide applications [41, 8]. However, pixel-wisely annotating all frames is tedious and inefficient. In this paper, we develop a Single frame Video Parsing (SVP) method which requires only one labeled frame per video in training stage. To parse one particular frame, the video segment preceding the frame is jointly considered. SVP (i) roughly parses the frames within the video segment, (ii) estimates the optical flow between frames and (iii) fuses the rough parsing results warped by optical flow to produce the refined parsing result. The three components of SVP, namely frame parsing, optical flow estimation and temporal fusion are integrated in an end-to-end manner. Experimental results on two surveillance video datasets show the superiority of SVP over state-of-the-arts. The collected video parsing datasets can be downloaded via http://liusi-group.com/projects/SVP for the further studies.

In this paper, we introduce a novel approach to regulate receptive field in deep image parsing network automatically. Unlike previous works which have stressed much importance on obtaining better receptive fields using manually selected dilated convolutional kernels, our approach uses two affine transformation layers in the networks backbone and operates on feature maps. Feature maps will be inflated/shrinked by the new layer and therefore receptive fields in following layers are changed accordingly. By end-to-end training, the whole framework is data-driven without laborious manual intervention. The proposed method is generic across dataset and different tasks. We conduct extensive experiments on both general parsing task and face parsing task as concrete examples to demonstrate the methods superior regulation ability over manual designs.

Face aging, which renders aging faces for an input face, has attracted extensive attention in the multimedia research. Recently, several conditional Generative Adversarial Nets (GANs) based methods have achieved great success. They can generate images fitting the real face distributions conditioned on each individual age group. However, these methods fail to capture the transition patterns, e.g., the gradual shape and texture changes between adjacent age groups. In this paper, we propose a novel Contextual Generative Adversarial Nets (C-GANs) to specifically take it into consideration. The C-GANs consists of a conditional transformation network and two discriminative networks. The conditional transformation network imitates the aging procedure with several specially designed residual blocks. The age discriminative network guides the synthesized face to fit the real conditional distribution. The transition pattern discriminative network is novel, aiming to distinguish the real transition patterns with the fake ones. It serves as an extra regularization term for the conditional transformation network, ensuring the generated image pairs to fit the corresponding real transition pattern distribution. Experimental results demonstrate the proposed framework produces appealing results by comparing with the state-of-the-art and ground truth. We also observe performance gain for cross-age face verification.

This work focuses on Magic-wall, an automatic system for visualizing the effect of room decoration. Given an image of the indoor scene and a preferred color, the Magic-wall can automatically locate the wall regions in the image and smoothly replace the existing color with the required one. The key idea of the proposed Magic-wall is to leverage visual semantics to guide the entire process of color substitution including wall segmentation and color replacement. We propose an edge-aware fully convolutional neural network (FCN) for indoor semantic scene parsing, in which a novel edge-prior branch is introduced to better identify the boundary of different semantic regions. To accurately localize the wall regions, we adapt a semantic-dependent optimized strategy, which pays more attention to those pixels belonging to the wall by adapting larger optimization weights compared with those from other semantic regions. Finally, to naturally replace the color of original walls, a simple yet effective color space conversion method is proposed for replacement with brightness reservation. We build a new indoor scene dataset upon ADE20K for training and testing, which includes 6 semantic labels. Extensive experimental evaluations and visualizations well demonstrate that the proposed Magic-wall is effective and can automatically generate a set of visually pleasing results.

Face aging, also known as age progression, is attracting more and more research interests. It has plenty of applications in various domains including cross-age face recognition, finding lost children, and entertainments. In recent years, face aging has witnessed various breakthroughs and a number of face aging models have been proposed. Face aging, however, is still a very challenging task in practice for various reasons. First, faces may have many different expressions and lighting conditions, which pose great challenges to modeling the aging patterns. Besides, the training data are usually very limited and the face images for the same person only cover a narrow range of ages.

In this demo, we present a real-time surveillance video parsing (RSVP) system to parse surveillance videos. Surveillance video parsing, which aims to segment the video frames into several labels, e.g., face, pants, left-legs, has wide applications, especially in security filed. However, it is very tedious and time-consuming to annotate all the frames in a video. We design a RSVP system to parse the surveillance videos in real-time. The RSVP system requires only one labeled frame in training stage. The RSVP system jointly considers the segmentation of preceding frames when parsing one particular frame within the video. The RSVP system is proved to be effective and efficient in real applications.

Image matting plays an important role in image and video editing. However, the formulation of image matting is inherently ill-posed. Traditional methods usually employ interaction to deal with the image matting problem with trimaps and strokes, and cannot run on the mobile phone in real-time. In this paper, we propose a real-time automatic deep matting approach for mobile devices. By leveraging the densely connected blocks and the dilated convolution, a light full convolutional network is designed to predict a coarse binary mask for portrait image. And a feathering block, which is edge-preserving and matting adaptive, is further developed to learn the guided filter and transform the binary mask into alpha matte. Finally, an automatic portrait animation system based on fast deep matting is built on mobile devices, which does not need any interaction and can realize real-time matting with 15 fps. The experiments show that the proposed approach achieves comparable results with the state-of-the-art matting solvers.

Retrieving objects from large image collection is challenging due to the so-called background-interference, i.e., matching between query object and reference images is usually confused by cluttered background, especially when objects are small. In this paper, we propose an object retrieval technique addressing this problem by partitioning the images. Specifically, several object proposals are partitioned from the images by jointly optimizing their objectness and coverage. The proposal set with maximum objectness score and minimum redundancy is obtained. Therefore,the interference of cluttered background is greatly reduced. Next, the objects are retrieved based on the partitioned proposals, separately and independently to the background. Our method is featured by the fine partitioning, which not only removes interferences from background, but also significantly reduces the number of objects to index. In this way, the effectiveness and efficiency are both achieved, which better suits big data retrieval. Subsequently, feature coding on partitioned objects generates much meaningful representation, and object level connectivity also introduces novel clues into the reranking. Extensive experiments on three popular object retrieval benchmark datasets (Oxford Buildings, Paris, Holiday) show the effectiveness of our method in retrieving small objects out of big data.

Adult image and video recognition is an important and challenging problem in the real world. Low-level feature cues do not produce good enough information, especially when the dataset is very large and has various data distributions. This issue raises a serious problem for conventional approaches. In this article, we tackle this problem by proposing a deep multicontext network with fine-to-coarse strategy for adult image and video recognition. We employ a deep convolution networks to model fusion features of sensitive objects in images. Global contexts and local contexts are both taken into consideration and are jointly modeled in a unified multicontext deep learning framework. To make the model more discriminative for diverse target objects, we investigate a novel hierarchical method, and a task-specific fine-to-coarse strategy is designed to make the multicontext modeling more suitable for adult object recognition. Furthermore, some recently proposed deep models are investigated. Our approach is extensively evaluated on four different datasets. One dataset is used for ablation experiments, whereas others are used for generalization experiments. Results show significant and consistent improvements over the state-of-the-art methods.

In this study, we present a weakly supervised approach that discovers the discriminative structures of sketch images, given pairs of sketch images and web images. In contrast to traditional approaches that use global appearance features or relay on keypoint features, our aim is to automatically learn the shared latent structures that exist between sketch images and real images, even when there are significant appearance differences across its relevant real images. To accomplish this, we propose a deep convolutional neural network, named SketchNet. We firstly develop a triplet composed of sketch, positive and negative real image as the input of our neural network. To discover the coherent visual structures between the sketch and its positive pairs, we introduce the softmax as the loss function. Then a ranking mechanism is introduced to make the positive pairs obtain a higher score comparing over negative ones to achieve robust representation. Finally, we formalize above-mentioned constrains into the unified objective function, and create an ensemble feature representation to describe the sketch images. Experiments on the TUBerlin sketch benchmark demonstrate the effectiveness of our model and show that deep feature representation brings substantial improvements over other state-of-the-art methods on sketch classification.

In this paper, we propose a novel structural correlation filter (SCF) model for robust visual tracking. The proposed SCF model takes part-based tracking strategies into account in a correlation filter tracker, and exploits circular shifts of all parts for their motion modeling to preserve target object structure. Compared with existing correlation filter trackers, our proposed tracker has several advantages: (1) Due to the part strategy, the learned structural correlation filters are less sensitive to partial occlusion, and have computational efficiency and robustness. (2) The learned filters are able to not only distinguish the parts from the background as the traditional correlation filters, but also exploit the intrinsic relationship among local parts via spatial constraints to preserve object structure. (3) The learned correlation filters not only make most parts share similar motion, but also tolerate outlier parts that have different motion. Both qualitative and quantitative evaluations on challenging benchmark image sequences demonstrate that the proposed SCF tracking algorithm performs favorably against several state-of-the-art methods.

In this demo, we present a Beauty eMakeup System to automatically recommend the most suitable makeup for a female and synthesis the makeup on her face. Given a before-makeup face, her most suitable makeup is determined automatically. Then, both the before-makeup and the reference faces are fed into the proposed Deep Transfer Network to generate the after-makeup face. Our end-to-end makeup transfer network have several nice properties including: (1) with complete functions: including foundation, lip gloss, and eye shadow transfer; (2) cosmetic specific: different cosmetics are transferred in different manners; (3) localized: different cosmetics are applied on different facial regions; (4) producing naturally looking results without obvious artifacts; (5) controllable makeup lightness: various results from light makeup to heavy makeup can be generated. Extensive experimental evaluations and analysis on testing images well demonstrate the effectiveness of the proposed system.

In this paper, we formulate particle filter-based object tracking as an exclusive sparse learning problem that exploits contextual information. To achieve this goal, we propose the context-aware exclusive sparse tracker (CEST) to model particle appearances as linear combinations of dictionary templates that are updated dynamically. Learning the representation of each particle is formulated as an exclusive sparse representation problem, where the overall dictionary is composed of multiple group dictionaries that can contain contextual information. With context, CEST is less prone to tracker drift. Interestingly, we show that the popular L1 tracker is a special case of our CEST formulation. The proposed learning problem is efficiently solved using an accelerated proximal gradient method that yields a sequence of closed form updates. To make the tracker much faster, we reduce the number of learning problems to be solved by using the dual problem to quickly and systematically rank and prune particles in each frame. We test our CEST tracker on challenging benchmark sequences that involve heavy occlusion, drastic illumination changes, and large pose variations. Experimental results show that CEST consistently outperforms state-of-the-art trackers.

In this paper, we focus on how to boost the multi-view clustering by exploring the complementary information among multi-view features. A multi-view clustering framework, called Diversity-induced Multi-view Subspace Clustering (DiMSC), is proposed for this task. In our method, we extend the existing subspace clustering into the multi-view domain, and utilize the Hilbert Schmidt Independence Criterion (HSIC) as a diversity term to explore the complementarity of multi-view representations, which could be solved efficiently by using the alternating minimizing optimization. Compared to other multi-view clustering methods, the enhanced complementarity reduces the redundancy between the multi-view representations, and improves the accuracy of the clustering results. Experiments on both image and video face clustering well demonstrate that the proposed method outperforms the state-of-the-art methods.

Both parametric and non-parametric approaches have demonstrated encouraging performances in the human parsing task, namely segmenting a human image into several semantic regions (e.g., hat, bag, left arm, face). In this work, we aim to develop a new solution with the advantages of both methodologies, namely supervision from annotated data and the flexibility to use newly annotated (possibly uncommon) images, and present a quasi-parametric human parsing model. Under the classic K Nearest Neighbor (KNN)-based nonparametric framework, the parametric Matching Convolutional Neural Network (M-CNN) is proposed to predict the matching confidence and displacements of the best matched region in the testing image for a particular semantic region in one KNN image. Given a testing image, we first retrieve its KNN images from the annotated/manually-parsed human image corpus. Then each semantic region in each KNN image is matched with confidence to the testing image using M-CNN, and the matched regions from all KNN images are further fused, followed by a superpixel smoothing procedure to obtain the ultimate human parsing result. The M-CNN differs from the classic CNN [12] in that the tailored cross image matching filters are introduced to characterize the matching between the testing image and the semantic region of a KNN image. The cross image matching filters are defined at different convolutional layers, each aiming to capture a particular range of displacements. Comprehensive evaluations over a large dataset with 7,700 annotated human images well demonstrate the significant performance gain from the quasi-parametric model over the state-of-the-arts [29, 30], for the human parsing task.

Sparse representation has been applied to visual tracking by finding the best target candidate with minimal reconstruction error by use of target templates. However, most sparse representation based trackers only consider holistic or local representations and do not make full use of the intrinsic structure among and inside target candidates, thereby making the representation less effective when similar objects appear or under occlusion. In this paper, we propose a novel Structural Sparse Tracking (SST) algorithm, which not only exploits the intrinsic relationship among target candidates and their local patches to learn their sparse representations jointly, but also preserves the spatial layout structure among the local patches inside each target candidate. We show that our SST algorithm accommodates most existing sparse trackers with the respective merits. Both qualitative and quantitative evaluations on challenging benchmark image sequences demonstrate that the proposed SST algorithm performs favorably against several state-of-the-art methods.

Intuitive observations show that a baby may inherently possess the capability of recognizing a new visual concept (e.g., chair, dog) by learning from only very few positive instances taught by parent(s) or others, and this recognition capability can be gradually further improved by exploring and/or interacting with the real instances in the physical world. Inspired by these observations, we propose a computational model for weakly-supervised object detection, based on prior knowledge modelling, exemplar learning and learning with video contexts. The prior knowledge is modeled with a pre-trained Convolutional Neural Network (CNN). When very few instances of a new concept are given, an initial concept detector is built by exemplar learning over the deep features the pre-trained CNN. The well-designed tracking solution is then used to discover more diverse instances from the massive online weakly labeled videos. Once a positive instance is detected/identified with high score in each video, more instances possibly from different view-angles and/or different distances are tracked and accumulated. Then the concept detector can be fine-tuned based on these new instances. This process can be repeated again and again till we obtain a very mature concept detector. Extensive experiments on Pascal VOC-07/10/12 object detection datasets [9] well demonstrate the effectiveness of our framework. It can beat the state-of-the-art full-training based performances by learning from very few samples for each object category, along with about 20,000 weakly labeled videos.

In this work, we address the human parsing task with a novel Contextualized Convolutional Neural Network (Co-CNN) architecture, which well integrates the cross-layer context, global image-level context, within-super-pixel context and cross-super-pixel neighborhood context into a unified network. Given an input human image, Co-CNN produces the pixel-wise categorization in an end-to-end way. First, the cross-layer context is captured by our basic local-to-global-to-local structure, which hierarchically combines the global semantic structure and the local fine details within the cross-layers. Second, the global image-level label prediction is used as an auxiliary objective in the intermediate layer of the Co-CNN, and its outputs are further used for guiding the feature learning in subsequent convolutional layers to leverage the global image-level context. Finally, to further utilize the local super-pixel contexts, the within-super-pixel smoothing and cross-super-pixel neighbourhood voting are formulated as natural sub-components of the Co-CNN to achieve the local label consistency in both training and testing process. Comprehensive evaluations on two public datasets well demonstrate the significant superiority of our Co-CNN architecture over other state-of-the-arts for human parsing. In particular, the F-1 score on the large dataset [15] reaches 76.95% by Co-CNN, significantly higher than 62.81% and 64.38% by the state-of-the-art algorithms, M-CNN [21] and ATR [15], respectively.

In this paper, we explore the problem of multiview subspace clustering. We introduce a low-rank tensor constraint to explore the complementary information from multiple views and, accordingly, establish a novel method called Low-rank Tensor constrained Multiview Subspace Clustering (LT-MSC). Our method regards the subspace representation matrices of different views as a tensor, which captures dexterously the high order correlations underlying multiview data. Then the tensor is equipped with a low-rank constraint, which models elegantly the cross information among different views, reduces effectually the redundancy of the learned subspace representations, and improves the accuracy of clustering as well. The inference process of the affinity matrix for clustering is formulated as a tensor nuclear norm minimization problem, constrained with an additional L2,1-norm regularizer and some linear equalities. The minimization problem is convex and thus can be solved efficiently by an Augmented Lagrangian Alternating Direction Minimization (AL-ADM) method. Extensive experimental results on four benchmark datasets show the effectiveness of our proposed LT-MSC method.

This article summarizes the corresponding half-day tutorial at ACM Multimedia 2015. This tutorial reviews recent progresses in human-centric images and videos analysis: 1) fashion analysis: parsing, attribute prediction and retrieval; 2) action analysis: discriminative feature selection, pooling and fusion; 3) person verification: cross-domain person verification via learning a generalized similarity measure, and bit-scalable deep hashing with regularized similarity learning.

People counting in extremely dense crowds is an important step for video surveillance and anomaly warning. The problem becomes especially more challenging due to the lack of training samples, severe occlusions, cluttered scenes and variation of perspective. Existing methods either resort to auxiliary human and face detectors or surrogate by estimating the density of crowds. Most of them rely on hand-crafted features, such as SIFT, HOG etc, and thus are prone to fail when density grows or the training sample is scarce. In this paper we propose an end-to-end deep convolutional neural networks (CNN) regression model for counting people of images in extremely dense crowds. Our method has following characteristics. Firstly, it is a deep model built on CNN to automatically learn effective features for counting. Besides, to weaken influence of background like buildings and trees, we purposely enrich the training data with expanded negative samples whose ground truth counting is set as zero. With these negative samples, the robustness can be enhanced. Extensive experimental results show that our method achieves superior performance than the state-of-the-arts in term of the mean and variance of absolute difference.

In this work, the human parsing task, namely decomposing a human image into semantic fashion/body regions, is formulated as an active template regression (ATR) problem, where the normalized mask of each fashion/body item is expressed as the linear combination of the learned mask templates, and then morphed to a more precise mask with the active shape parameters, including position, scale and visibility of each semantic region. The mask template coefficients and the active shape parameters together can generate the human parsing results, and are thus called the structure outputs for human parsing. The deep Convolutional Neural Network (CNN) is utilized to build the end-to-end relation between the input human image and the structure outputs for human parsing. More specifically, the structure outputs are predicted by two separate networks. The first CNN network is with max-pooling, and designed to predict the template coefficients for each label mask, while the second CNN network is without max-pooling to preserve sensitivity to label mask position and accurately predict the active shape parameters. For a new image, the structure outputs of the two networks are fused to generate the probability of each label for each pixel, and super-pixel smoothing is finally used to refine the human parsing result. Comprehensive evaluations on a large dataset well demonstrate the significant superiority of the ATR framework over other state-of-the-arts for human parsing. In particular, the F1-score reaches 64.38 percent by our ATR framework, significantly higher than 44.76 percent based on the state-of-the-art algorithm [28].

Person reidentification across nonoverlapping camera views is a rather challenging task. Due to the difficulties in obtaining identifiable faces, clothing appearance becomes the main cue for identification purposes. In this paper, we present a comprehensive study on clothing attributes assisted person reidentification. First, the body parts and their local features are extracted for alleviating the pose-misalignment issue. A latent support vector machine (LSVM)-based person reidentification approach is proposed to describe the relations among the low-level part features, middle-level clothing attributes, and high-level reidentification labels of person pairs. Motivated by the uncertainties of clothing attributes, we treat them as real-value variables instead of using them as discrete variables. Moreover, a large-scale real-world dataset with 10 camera views and about 200 subjects is collected and thoroughly annotated for this paper. The extensive experiments on this dataset show: 1) part features are more effective than features extracted from the holistic human bounding boxes; 2) the clothing attributes embedded in the LSVM model may further boost reidentification performance compared with support vector machine without clothing attributes; and 3) treating clothing attributes as real-value variables is more effective than using them as discrete variables in person reidentification.

Most existing methods on weakly supervised image annotation rely on jointly unsupervised feature representation, the components of which are not directly correlated with specific labels. In practical cases, however, there is a big gap between the training and the testing data, say the label combination of the testing data is not always consistent with that of the training. To bridge the gap, this paper presents a semantic label embedding dictionary representation that not only achieves the discriminative feature representation for each label in the image, but also mines the semantic relevance between co-occurrence labels for context information. More specifically, to enhance the discriminative representation of labels, the training data is first divided into a set of overlapped groups by graph shift based on the exclusive label graph. Afterward, given a group of exclusive labels, we try to learn multiple label-specific dictionaries to explicitly decorrelate the feature representation of each label. A joint optimization approach is proposed according to the Fisher discrimination criterion for seeking its solution. Then, to discover the context information hidden in the co-occurrence labels, we explore the semantic relationship between visual words in dictionaries and labels in a multitask learning way with respect to the reconstruction coefficients of the training data. In the annotation stage, with the discriminative dictionaries and exclusive label groups as well as a group sparsity constraint, the reconstruction coefficients of a test image can be easily obtained. Finally, we introduce a label propagation scheme to compute the score of each label for the test image based on its reconstruction coefficients. Experimental results on three challenging data sets demonstrate that our proposed method leads to significant performance gains over existing methods.

In this paper, we propose a novel semi- supervised learning strategy to address human parsing. Existing human parsing datasets are relatively small due to the required tedious human labeling. We present a general, affordable and scalable solution, which harnesses the rich contexts in those easily available web videos to boost any existing human parser. First, we crawl a large number of unlabeled videos from the web. Then for each video, the cross-frame contexts are utilized for human pose co- estimation , and then video co-parsing to obtain satisfactory human parsing results for all frames. More specifically, SIFT flow and super-pixel matching are used to build correspondences across different frames, and these correspondences then contextualize the pose estimation and human parsing in individual frames. Finally these parsed video frames are used as the reference corpus for the non-parametric human parsing component of the whole solution. To further improve the accuracy of video co-parsing, we propose an active learning method to incorporate human guidance, where the labelers are required to assess the accuracies of the pose estimation results of certain selected video frames. Then we take reliable frames as the seed frames to guide the video pose co-estimation. Our human parsing framework can then easily incorporate the human feedback to train a better fashion parser. Extensive experiments on two benchmark fashion datasets as well as a newly collected challenging Fashion Icon dataset well demonstrate the encouraging performance gain from our general pipeline for human parsing.

In this paper, we explore how to utilize the video context to facilitate fashion parsing. Instead of annotating a large amount of fashion images, we present a general, affordable and scalable solution, which harnesses the rich contexts in easily available fashion videos to boost any existing fashion parser. First, we crawl a large unlabelled fashion video corpus with fashion frames. Then for each fashion video, the cross-frame contexts are utilized for human pose co-estimation, and then video co-parsing to obtain satisfactory fashion parsing results for all frames. More specifically, Sift Flow and super-pixel matching are used to build correspondences across frames, and these correspondences then con- textualize the pose estimations and fashion parsing in individual frames. Finally, these parsed video frames are used as the reference corpus for the non-parametric fashion parsing component of the whole solution. Extensive experiments on two benchmark fashion datasets as well as a newly collected challenging Fashion Icon (FI) dataset demonstrate the encouraging performance gain from our general pipeline for fashion parsing.

In this article, by taking a popular game, the Find-the-Difference (FiDi) game, as a concrete example, we explore how state-of-the-art image processing techniques can assist in developing a personalized, automatic, and dynamic game. Unlike the traditional FiDi game, where image pairs (source image and target image) with five different patches are manually produced by professional game developers, the proposed Personalized FiDi (P-FiDi) electronic game can be played in a fully automatic Snap & Play mode.Snapmeans that players first take photos with their digital cameras. The newly captured photos are used as source images and fed into the P-FiDi system to autogenerate the counterpart target images for users toplay. Four steps are adopted to autogenerate target images: enhancing the visual quality of source images, extracting some changeable patches from the source image, selecting the most suitable combination of changeable patches and difference styles for the image, and generating the differences on the target image with state-of-the-art image processing techniques. In addition, the P-FiDi game can be easily redesigned for the im-game advertising. Extensive experiments show that the P-FiDi electronic game is satisfying in terms of player experience, seamless advertisement, and technical feasibility.

In this paper, we propose a novel text-art system: input a source picture and some keywords introducing the information about the picture, and the output is the so-called PicWords in the form of the source picture composed of the introduction keywords. Different from traditional text-graphics which are created by highly skilled artists and involve a huge amount of tedious manual work, PicWords is an automatic non-photorealistic rendering (NPR) packing system. Given a source picture, we first generate its silhouette, which is a binary image containing a Yang part and a Yin part. Yang part is for keywords placing while the Yin part can be ignored. Next, the Yang part is further over-segmented into small patches, each of which serves as a container for one keyword. To make sure that more important keywords are put into more salient and larger image patches, we rank both the patches and keywords and construct a correspondence between the patch list and keyword list. Then, mean value coordinates method is used for the keyword-patch warping. Finally, certain post-processing techniques are adopted to improve the aesthetics of PicWords. Extensive experimental results well demonstrate the effectiveness of the proposed PicWords system.

In this paper we address the problem of automatically parsing the fashion images with weak supervision from the user-generated color-category tags such as “red jeans” and “white T-shirt”. This problem is very challenging due to the large diversity of fashion items and the absence of pixel-level tags, which make the traditional fully supervised algorithms inapplicable. To solve the problem, we propose to combine the human pose estimation module, the MRF-based color and category inference module and the (super)pixel-level category classifier learning module to generate multiple well-performing category classifiers, which can be directly applied to parse the fashion items in the images. Besides, all the training images are parsed with color-category labels and the human poses of the images are estimated during the model learning phase in this work. We also construct a new fashion image dataset called Colorful-Fashion, in which all 2,682 images are labeled with pixel-level color-category labels. Extensive experiments on this dataset clearly show the effectiveness of the proposed method for the weakly supervised fashion parsing task.

Taking the shoe as a concrete example, we present an innovative product retrieval system that leverages object detection and retrieval techniques to support a brand-new online shopping experience in this article. The system, called Circle & Search, enables users to naturally indicate any preferred product by simply circling the product in images as the visual query, and then returns visually and semantically similar products to the users. The system is characterized by introducing attributes in both the detection and retrieval of the shoe. Specifically, we first develop an attribute-aware part-based shoe detection model. By maintaining the consistency between shoe parts and attributes, this shoe detector has the ability to model high-order relations between parts and thus the detection performance can be enhanced. Meanwhile, the attributes of this detected shoe can also be predicted as the semantic relations between parts. Based on the result of shoe detection, the system ranks all the shoes in the repository using an attribute refinement retrieval model that takes advantage of query-specific information and attribute correlation to provide an accurate and robust shoe retrieval. To evaluate this retrieval system, we build a large dataset with 17,151 shoe images, in which each shoe is annotated with 10 shoe attributes e.g., heel height, heel shape, sole shape, etc.). According to the experimental result and the user study, our Circle & Search system achieves promising shoe retrieval performance and thus significantly improves the users' online shopping experience.

Beauty e-Experts, a fully automatic system for makeover recommendation and synthesis, is developed in this work. The makeover recommendation and synthesis system simultaneously considers many kinds of makeover items on hairstyle and makeup. Given a user-provided frontal face image with short/bound hair and no/light makeup, the Beauty e-Experts system not only recommends the most suitable hairdo and makeup, but also synthesizes the virtual hairdo and makeup effects. To acquire enough knowledge for beauty modeling, we built the Beauty e-Experts Database, which contains 1,505 female photos with a variety of attributes annotated with different discrete values. We organize these attributes into two different categories, beauty attributes and beauty-related attributes. Beauty attributes refer to those values that are changeable during the makeover process and thus need to be recommended by the system. Beauty-related attributes are those values that cannot be changed during the makeup process but can help the system to perform recommendation. Based on this Beauty e-Experts Dataset, two problems are addressed for the Beauty e-Experts system: what to recommend and how to wear it, which describes a similar process of selecting hairstyle and cosmetics in daily life. For the what-to-recommend problem, we propose a multiple tree-structured supergraph model to explore the complex relationships among high-level beauty attributes, mid-level beauty-related attributes, and low-level image features. Based on this model, the most compatible beauty attributes for a given facial image can be efficiently inferred. For the how-to-wear-it problem, an effective and efficient facial image synthesis module is designed to seamlessly synthesize the recommended makeovers into the user facial image. We have conducted extensive experiments on testing images of various conditions to evaluate and analyze the proposed system. The experimental results well demonstrate the effectiveness and efficiency of the proposed system.

Recently, studies on sketch, such as sketch retrieval and sketch classification, have received more attention in the computer vision community. One of its most fundamental and essential problems is how to more effectively describe a sketch image. Many existing descriptors, such as shape context, have achieved great success. In this paper, we propose a new descriptor, namely Symmetric-aware Flip Invariant Sketch Histogram (SYM-FISH) to refine the shape context feature. Its extraction process includes three steps. First the Flip Invariant Sketch Histogram (FISH) descriptor is extracted on the input image, which is a flip-invariant version of the shape context feature. Then we explore the symmetry character of the image by calculating the kurtosis coefficient. Finally, the SYM-FISH is generated by constructing a symmetry table. The new SYM-FISH descriptor supplements the original shape context by encoding the symmetric information, which is a pervasive characteristic of natural scene and objects. We evaluate the efficacy of the novel descriptor in two applications, i.e., sketch retrieval and sketch classification. Extensive experiments on three datasets well demonstrate the effectiveness and robustness of the proposed SYM-FISH descriptor.

In this paper, we propose a low-rank sparse coding (LRSC) method that exploits local structure information among features in an image for the purpose of image-level classification. LRSC represents densely sampled SIFT descriptors, in a spatial neighborhood, collectively as low-rank, sparse linear combinations of code words. As such, it casts the feature coding problem as a low-rank matrix learning problem, which is different from previous methods that encode features independently. This LRSC has a number of attractive properties. (1) It encourages sparsity in feature codes, locality in codebook construction, and low-rankness for spatial consistency. (2) LRSC encodes local features jointly by considering their low-rank structure information, and is computationally attractive. We evaluate the LRSC by comparing its performance on a set of challenging benchmarks with that of 7 popular coding and other state-of-the-art methods. Our experiments show that by representing local features jointly, LRSC not only outperforms the state-of-the-art in classification accuracy but also improves the time complexity of methods that use a similar sparse linear representation model for feature coding.

In this demo, we propose the puppetry eHeritage, including a creator module and a manipulator module, to preserve the precious traditional heritage Chinese shadow puppetry. The creator module accepts a frontal face image and a profile face image of the user as input, and automatically generates the corresponding puppet, which looks like the original person and meanwhile preserves typical characteristics of traditional Chinese shadow puppetry. The manipulator module can accept the script provided by the user as input and automatically generate the motion sequences. For better visual effects, we propose the sparsity optimization over simplexes formulation.

To preserve the precious traditional heritage Chinese shadow puppetry, we propose the puppetry eHeritage, including a creator module and a manipulator module. The creator module accepts a frontal view face image and a profile face image of the user as input, and automatically generates the corresponding puppet, which looks like the original person and meanwhile has some typical characteristics of traditional Chinese shadow puppetry. In order to create the puppet, we first extract the central profile curve and warp the reference puppet eye and eyebrow to the shape of the frontal view eye and eyebrow. Then we transfer the puppet texture to the real face area. The manipulator module can accept the script provided by the user as input and automatically generate the motion sequences. Technically, we first learn atomic motions from a set of shadow puppetry videos. A scripting system converts the user's input to atomic motions, and finally synthesizes the animation based on the atomic motion instances. For better visual effects, we propose the sparsity optimization over simplexes formulation to automatically assemble weighted instances of different atomic actions into a smooth shadow puppetry animation sequence. We evaluate the performance of the creator module and the manipulator module sequentially. Extensive experimental results on the creation of puppetry characters and puppetry plays well demonstrate the effectiveness of the proposed system.

In this demo, we present Beauty e-Experts, a fully automatic system for hairstyle and facial makeup recommendation and synthesis. Given a user-provided frontal facial image with short/bound hair and no/light makeup, the Beauty e-Experts system can not only recommend the most suitable hairstyle and makeup, but also show the synthesis effects. Two problems are considered for the Beauty e-Experts system: what to recommend and how to wear, which describe a similar process of selecting and applying hairstyle and cosmetics in our daily life. For the what-to-recommend problem, we propose a multiple tree-structured super-graphs model to explore the complex relationships among the beauty attributes, beauty-related attributes and image features, and then based on this model, the most suitable beauty attributes for a given facial image can be efficiently inferred. For the how-to-wear problem, a facial image synthesis module is designed to seamlessly blend the recommended hairstyle and makeup into the user facial image. Extensive experimental evaluations and analysis on testing images well demonstrate the effectiveness of the proposed system.

Beauty e-Experts, a fully automatic system for hairstyle and facial makeup recommendation and synthesis, is developed in this work. Given a user-provided frontal face image with short/bound hair and no/light makeup, the Beauty e-Experts system can not only recommend the most suitable hairdo and makeup, but also show the synthetic effects. To obtain enough knowledge for beauty modeling, we build the Beauty e-Experts Database, which contains 1,505 attractive female photos with a variety of beauty attributes and beauty-related attributes annotated. Based on this Beauty e-Experts Dataset, two problems are considered for the Beauty e-Experts system: what to recommend and how to wear, which describe a similar process of selecting hairstyle and cosmetics in our daily life. For the what-to-recommend problem, we propose a multiple tree-structured super-graphs model to explore the complex relationships among the high-level beauty attributes, mid-level beauty-related attributes and low-level image features, and then based on this model, the most compatible beauty attributes for a given facial image can be efficiently inferred. For the how-to-wear problem, an effective and efficient facial image synthesis module is designed to seamlessly synthesize the recommended hairstyle and makeup into the user facial image. Extensive experimental evaluations and analysis on testing images of various conditions well demonstrate the effectiveness of the proposed system.

Automated visual surveillance systems are attracting extensive interest due to public security. In this paper, we attempt to mine semantic context information including object-specific context information and scene-specific context information (learned from object-specific context information) to build an intelligent system with robust object detection, tracking, and classification and abnormal event detection. By means of object-specific context information, a cotrained classifier, which takes advantage of the multiview information of objects and reduces the number of labeling training samples, is learned to classify objects into pedestrians or vehicles with high object classification performance. For each kind of object, we learn its corresponding semantic scene-specific context information: motion pattern, width distribution, paths, and entry/exist points. Based on this information, it is efficient to improve object detection and tracking and abnormal event detection. Experimental results demonstrate the effectiveness of our semantic context features for multiple real-world traffic scenes.

Decrypting the secret of beauty or attractiveness has been the pursuit of artists and philosophers for centuries. To date, the computational model for attractiveness estimation has been actively explored in computer vision and multimedia community, yet with the focus mainly on facial features. In this article, we conduct a comprehensive study on female attractiveness conveyed by single/multiple modalities of cues, that is, face, dressing and/or voice, and aim to discover how different modalities individually and collectively affect the human sense of beauty. To extensively investigate the problem, we collect the Multi-Modality Beauty (M2B) dataset, which is annotated with attractiveness levels converted from manualk-wise ratings and semantic attributes of different modalities. Inspired by the common consensus that middle-level attribute prediction can assist higher-level computer vision tasks, we manually labeled many attributes for each modality. Next, a tri-layer Dual-supervised Feature-Attribute-Task (DFAT) network is proposed to jointly learn the attribute model and attractiveness model of single/multiple modalities. To remedy possible loss of information caused by incomplete manual attributes, we also propose a novel Latent Dual-supervised Feature-Attribute-Task (LDFAT) network, where latent attributes are combined with manual attributes to contribute to the final attractiveness estimation. The extensive experimental evaluations on the collected M2B dataset well demonstrate the effectiveness of the proposed DFAT and LDFAT networks for female attractiveness prediction.

In this paper, we address a practical problem of cross-scenario clothing retrieval - given a daily human photo captured in general environment, e.g., on street, finding similar clothing in online shops, where the photos are captured more professionally and with clean background. There are large discrepancies between daily photo scenario and online shopping scenario. We first propose to alleviate the human pose discrepancy by locating 30 human parts detected by a well trained human detector. Then, founded on part features, we propose a two-step calculation to obtain more reliable one-to-many similarities between the query daily photo and online shopping photos: 1) the within-scenario one-to-many similarities between a query daily photo and the auxiliary set are derived by direct sparse reconstruction; and 2) by a cross-scenario many-to-many similarity transfer matrix inferred offline from an extra auxiliary set and the online shopping set, the reliable cross-scenario one-to-many similarities between the query daily photo and all online shopping photos are obtained. We collect a large online shopping dataset and a daily photo dataset, both of which are thoroughly labeled with 15 clothing attributes via Mechanic Turk. The extensive experimental evaluations on the collected datasets well demonstrate the effectiveness of the proposed framework for cross-scenario clothing retrieval.

In this paper, we formulate object tracking in a particle filter framework as a multi-task sparse learning problem, which we denote as Multi-Task Tracking (MTT). Since we model particles as linear combinations of dictionary templates that are updated dynamically, learning the representation of each particle is considered a single task in MTT. By employing popular sparsity-inducing ℓp, qmixed norms (p ∈ {2, ∞} and q = 1), we regularize the representation problem to enforce joint sparsity and learn the particle representations together. As compared to previous methods that handle particles independently, our results demonstrate that mining the interdependencies between particles improves tracking performance and overall computational complexity. Interestingly, we show that the popular L1tracker [15] is a special case of our MTT formulation (denoted as the L11tracker) when p = q = 1. The learning problem can be efficiently solved using an Accelerated Proximal Gradient (APG) method that yields a sequence of closed form updates. As such, MTT is computationally attractive. We test our proposed approach on challenging sequences involving heavy occlusion, drastic illumination changes, and large pose variations. Experimental results show that MTT methods consistently outperform state-of-the-art trackers.

This paper proposes an algorithm of data subcarrier designing to apply the tone reservation(TR) peak-to-average power ratio (PAPR) reduction algorithm in OFDM-based wireless communication systems and overcome the high computational cost issue. Different from the existing works, the proposed algorithm focuses on designing data subcarriers, controlling both the iteration times and the number of subcarriers. The new algorithm exhibits similar performance as the traditional TR algorithm with lower computational complexity and the ability to control the number of used subcarriers. Simulation results show that the proposed algorithm can significantly reduce the PAPR by only 2 or 3 iterations.

In this paper, we aim at a practical system, magic closet, for automatic occasion-oriented clothing recommendation. Given a user-input occasion, e.g., wedding, shopping or dating, magic closet intelligently suggests the most suitable clothing from the user's own clothing photo album, or automatically pairs the user-specified reference clothing (upper-body or lower-body) with the most suitable one from online shops.

In this demo, we present a practical system, magic closet, for automatic occasion-oriented clothing pairing. Given a user-input occasion, e.g., wedding or shopping, the magic closet intelligently and automatically pairs the user-specified reference clothing (upper-body or lower-body) with the most suitable one from online shops. Two key criteria are explicitly considered for the magic closet system. One criterion is to wear properly, e.g., compared to suit pants, it is more decent to wear a cocktail dress for a banquet occasion. The other criterion is to wear aesthetically, e.g., a red T-shirt matches better white pants than green pants. To narrow the semantic gap between the low-level visual features and the high-level occasion categories, we propose to adopt middle-level clothing attributes (e.g., clothing category, color, pattern) as a bridge. More specifically, the clothing attributes are treated as latent variables in our proposed latent Support Vector Machine (SVM) based recommendation model. The wearing properly criterion is described through a feature-occasion potential and an attribute-occasion potential, while the wearing aesthetically criterion is expressed by an attribute-attribute potential.

We address a cross-scenario clothing retrieval problem- given a daily human photo captured in general environment, e.g., on street, finding similar clothing in online shops, where the photos are captured more professionally and with clean background. There are large discrepancies between daily photo scenario and online shopping scenario. We first propose to alleviate the human pose discrepancy by locating 30 human parts detected by a well trained human detector. Then, founded on part features, we propose a two-step calculation to obtain more reliable one-to-many similarities between the query daily photo and online shopping photos: 1) the within-scenario one-to-many similarities between a query daily photo and an extra auxiliary set are derived by direct sparse reconstruction; 2) by a cross-scenario many-to-many similarity transfer matrix inferred offline from the auxiliary set and the online shopping set, the reliable cross-scenario one-to-many similarities between the query daily photo and all online shopping photos are obtained.

Discovering the secret of beauty has been the pursuit of artists and philosophers for centuries. Nowadays, the computational model for beauty estimation has been actively explored in computer science community, yet with the focus mainly on facial features. In this work, we perform a comprehensive study of female attractiveness conveyed by single/multiple modalities of cues, i.e., face, dressing and/or voice, and aim to uncover how different modalities individually and collectively affect the human sense of beauty. To this end, we collect the first Multi-Modality Beauty (M2B) dataset in the world for female attractiveness study, which is thoroughly annotated with attractiveness levels converted from manual k-wise ratings and semantic attributes of different modalities. A novel Dual-supervised Feature-Attribute-Task (DFAT) network is proposed to jointly learn the beauty estimation models of single/multiple modalities as well as the attribute estimation models. The DFAT network differentiates itself by its supervision in both attribute and task layers. Several interesting beauty-sense observations over single/multiple modalities are reported, and the extensive experimental evaluations on the collected M2B dataset well demonstrate the effectiveness of the proposed DFAT network for female attractiveness estimation.

In this work, we propose a weakly supervised graph propagation method to automatically assign the annotated labels at image level to those contextually derived semantic regions. The graph is constructed with the over-segmented patches of the image collection as nodes. Image-level labels are imposed on the graph as weak supervision information over subgraphs, each of which corresponds to all patches of one image, and the contextual information across different images at patch level are then mined to assist the process of label propagation from images to their descendent regions. The ultimate optimization problem is efficiently solved by Convex Concave Programming (CCCP). Extensive experiments on four benchmark datasets clearly demonstrate the effectiveness of our proposed method for the task of collective image parsing. Two extensions including image annotation and concept map based image retrieval demonstrate the proposed image parsing algorithm can effectively aid other vision tasks.

Learning-based video annotation is essential for video analysis and understanding, and many various approaches have been proposed to avoid the intensive labor costs of purely manual annotation. However, there lacks a generic framework due to several difficulties, such as dependence of domain knowledge, insufficiency of training data, no precise localization and in efficacy for large-scale video dataset. In this paper, we propose a novel approach based on semi-supervised learning by means of information from the Internet for interesting event annotation in videos. Concretely, a Fast Graph-based Semi-Supervised Multiple Instance Learning (FGSSMIL) algorithm, which aims to simultaneously tackle these difficulties in a generic framework for various video domains (e.g., sports, news, and movies), is proposed to jointly explore small-scale expert labeled videos and large-scale unlabeled videos to train the models. The expert labeled videos are obtained from the analysis and alignment of well-structured video related text (e.g., movie scripts, web-casting text, close caption). The unlabeled data are obtained by querying related events from the video search engine (e.g., YouTube, Google) in order to give more distributive information for event modeling. Two critical issues of FGSSMIL are: (1) how to calculate the weight assignment for a graph construction, where the weight of an edge specifies the similarity between two data points. To tackle this problem, we propose a novel Multiple Instance Learning Induced Similarity (MILIS) measure by learning instance sensitive classifiers; (2) how to solve the algorithm efficiently for large-scale dataset through an optimization approach. To address this issue, Concave-Convex Procedure (CCCP) and nonnegative multiplicative updating rule are adopted. We perform the extensive experiments in three popular video domains: movies, sports, and news. The results compared with the state-of-the-arts are promising and demonstrate the effectiveness and efficiency of our proposed approach.

In this paper, we propose a novel method to select the most informativesubset of features, which has little redundancy andvery strong discriminating power. Our proposed approach automaticallydetermines the optimal number of features and selectsthe best subset accordingly by maximizing the averagepairwise informativeness, thus has obvious advantage overtraditional filter methods. By relaxing the essential combinatorialoptimization problem into the standard quadratic programmingproblem, the most informative feature subset canbe obtained efficiently, and a strategy to dynamically computethe redundancy between feature pairs further greatly acceleratesour method through avoiding unnecessary computationsof mutual information. As shown by the extensive experiments,the proposed method can successfully select the mostinformative subset of features, and the obtained classificationresults significantly outperform the state-of-the-art results onmost test datasets.

According to the year 2010 report of the Entertainment Software Association [5], 42% of USA heads of households reported playing games on mobile devices, rising quickly from the 20% in 2002 and bringing huge market for mobile games. In this paper, by taking the popular game, Find-the-Difference (FiDi), as a concrete example, we explore new mobile game design principles and techniques for enhancing player's gaming experience in personalized, automatic, and dynamic aspects. Unlike traditional FiDi game, where image pairs (source image vs. target image) with M different patches are manually produced by game developer and players may feel boring or cheat after practicing all image pairs, our proposed Personalized FiDi (P-FiDi) mobile game may be played under a new Snap & Play mode. The player may first take photos with one s mobile device (or select from one's own albums). Then, these photos serve as source images, and the P-FiDi system automatically generates the counterpart target images by sequential operations of aesthetic image quality enhancement, image patch and differentiating style joint selection, music adaptation, dynamic difficulty level determination, and ultimate automatic image editing with a rich set of popular differentiating styles used in traditional FiDi game. Finally, the player enjoys the unique gaming with one's own (instant) photos and music, and the freedom to have new gaming image pairs any time. The user studies show that the P-FiDi mobile game is satisfying in terms of player experience.

Human action recognition and annotation is an active research topic in computer vision. How to model various actions, varying with time resolution, visual appearance, and others, is a challenging task. In this paper, we propose a boosted exemplar learning (BEL) approach to model various actions in a weakly supervised manner, i.e., only action bag-level labels are provided but action instance level ones are not. The proposed BEL method can be summarized as three steps. First, for each action category, amount of class-specific candidate exemplars are learned through an optimization formulation considering their discrimination and co-occurrence. Second, each action bag is described as a set of similarities between its instances and candidate exemplars. Instead of simply using a heuristic distance measure, the similarities are decided by the exemplar-based classifiers through the multiple instance learning, in which a positive (or negative) video or image set is deemed as a positive (or negative) action bag and those frames similar to the given exemplar in Euclidean Space as action instances. Third, we formulate the selection of the most discriminative exemplars into a boosted feature selection framework and simultaneously obtain an action bag-based detector. Experimental results on two publicly available datasets: the KTH dataset and Weizmann dataset, demonstrate the validity and effectiveness of the proposed approach for action recognition. We also apply BEL to learn representations of actions by using images collected from the Web and use this knowledge to automatically annotate action in YouTube videos. Results are very impressive, which proves that the proposed algorithm is also practical in unconstraint environments.

Event detection is essential for the extensively studied video analysis and understanding area. Although various approaches have been proposed for event detection, there is a lack of a generic event detection framework that can be applied to various video domains (e.g. sports, news, movies, surveillance). In this paper, we present a generic event detection approach based on semi-supervised learning and Internet vision. Concretely, a Graph-based Semi-Supervised Multiple Instance Learning (GSSMIL) algorithm is proposed to jointly explore small-scale expert labeled videos and large-scale unlabeled videos to train the event models to detect video event boundaries. The expert labeled videos are obtained from the analysis and alignment of well-structured video related text (e.g. movie scripts, web-casting text, close caption). The unlabeled data are obtained by querying related events from the video search engine (e.g. YouTube) in order to give more distributive information for event modeling. A critical issue of GSSMIL in constructing a graph is the weight assignment, where the weight of an edge specifies the similarity between two data points. To tackle this problem, we propose a novel Multiple Instance Learning Induced Similarity (MILIS) measure by learning instance sensitive classifiers. We perform the thorough experiments in three popular video domains: movies, sports and news. The results compared with the state-of-the-arts are promising and demonstrate our proposed approach is performance-effective.