Aerial Vision-and-Language Navigation (AVLN) requires Unmanned Aerial Vehicle (UAV) agents to localize targets in large-scale urban environments based on linguistic instructions. While successful navigation demands both global environmental reasoning and local scene comprehension, existing UAV agents typically adopt mono-granularity frameworks that struggle to balance these two aspects. To address this limitation, this work proposes a History-Enhanced Two-Stage Transformer (HETT) framework, which integrates the two aspects through a coarse-to-fine navigation pipeline. Specifically, HETT first predicts coarse-grained target positions by fusing spatial landmarks and historical context, then refines actions via fine-grained visual analysis. In addition, a historical grid map is designed to dynamically aggregate visual features into a structured spatial memory, enhancing comprehensive scene awareness. Additionally, the CityNav dataset annotations are manually refined to enhance data quality. Experiments on the refined CityNav dataset show that HETT delivers significant performance gains, while extensive ablation studies further verify the effectiveness of each component.

Abductive reasoning seeks the likeliest possible explanation for partial observations. Although being frequently employed in human daily reasoning, abduction is rarely explored in computer vision literature. In this article, we propose a new task, Visual Abductive Reasoning (VAR), that underpins the machine intelligence study of abductive reasoning in everyday visual situations. Given an incomplete set of visual events, AI systems are required to not only describe what is observed, but also infer the hypothesis that can best explain the observed premise. We create the first large-scale VAR dataset, which contains a total of 9K examples. We further devise a transformer-based VAR model - Reasonerv2 - for knowledge-driven, causal-and-cascaded reasoning. Reasonerv2 first adopts a contextualized directional position embedding strategy in the encoder, to capture the causal-related temporal structure of the observations, and yield discriminative representations for the premises and hypotheses. Then, Reasonerv2 extracts condensed causal knowledge from external knowledge bases, for reasoning beyond observation. Finally, Reasonerv2 cascades multiple decoders so as to generate and progressively refine the premise and hypothesis sentences. The prediction scores of the sentences are used to guide cross-sentence information flow in the cascaded reasoning procedure. Our VAR benchmarking results show that Reasonerv2 surpasses many famous video-language models, while still being far behind human performance.

Few-Shot Action Recognition (FSAR) is a challenging task that requires recognizing novel action categories with a few labeled videos. Recent works typically apply semantically coarse category names as auxiliary contexts to guide the learning of discriminative visual features. However, such context provided by the action names is too limited to provide sufficient background knowledge for capturing novel spatial and temporal concepts in actions. In this paper, we propose DiST, an innovative Decomposition-incorporation framework for FSAR that makes use of decoupled Spatial and Temporal knowledge provided by large language models to learn expressive multi-granularity prototypes. In the decomposition stage, we decouple vanilla action names into diverse spatio-temporal attribute descriptions (action-related knowledge). Such commonsense knowledge complements semantic contexts from spatial and temporal perspectives. In the incorporation stage, we propose Spatial/Temporal Knowledge Compensators (SKC/TKC) to discover discriminative object-level and frame-level prototypes, respectively. In SKC, object-level prototypes adaptively aggregate important patch tokens under the guidance of spatial knowledge. Moreover, in TKC, frame-level prototypes utilize temporal attributes to assist in inter-frame temporal relation modeling. These learned prototypes thus provide transparency in capturing fine-grained spatial details and diverse temporal patterns. Experimental results show DiST achieves state-of-the-art results on five standard FSAR datasets.

Top-leading solutions for Video Scene Graph Generation (VSGG) typically adopt an offline pipeline. Though demonstrating promising performance, they remain unable to handle real-time video streams and consume large GPU memory. Moreover, these approaches fall short in temporal reasoning, merely aggregating frame-level predictions over a temporal context. In response, we introduce DiffVsgg, an online VSGG solution that frames this task as an iterative scene graph update problem. Drawing inspiration from Latent Diffusion Models (LDMs) which generate images via denoising a latent feature embedding, we unify the decoding of object classification, bounding box regression, and graph generation three tasks using one shared feature embedding. Then, given an embedding containing unified features of object pairs, we conduct a step-wise Denoising on it within LDMs, so as to deliver a clean embedding which clearly indicates the relationships between objects. This embedding then serves as the input to task-specific heads for object classification, scene graph generation, etc. DiffVsgg further facilitates continuous temporal reasoning, where predictions for subsequent frames leverage results of past frames as the conditional inputs of LDMs, to guide the reverse diffusion process for current frames. Extensive experiments on three setups of Action Genome demonstrate the superiority of DiffVsgg.

Navigation instruction generation (NIG), which provides interactive feedback and guidance to humans along a trajectory, is vital for developing embodied agents capable of human-machine communication and collaboration through natural language. Early data-driven methods directly map sequences of past observations to trajectory descriptions on limited datasets, lacking the necessary spatial understanding in complex 3D environments. While recent approaches leverage Large Language Models (LLMs) to improve NIG, they often overlook the global spatial context in navigation, such as the inherent space discretization in maps. Instead of straightforwardly feeding textual descriptions of the map into LLMs, we propose a scene map-based prompt tuning framework for NIG, MAPInstructor, which incorporates map context for parameter-efficient updating of LLMs. MAPInstructor comprises three key components: (i) scene representation encoding, where egocentric observations are projected into 3D voxels for fine-grained scene understanding; (ii) map prompt tuning, which integrates a topological map representation of the entire trajectory into an LLM-based decoder; and (iii) landmark uncertainty assessment, which mitigates hallucinations in landmark predictions, thereby enhancing the reliability and coherence of instruction generation. Extensive experiments on three navigation datasets (i.e., R2R, REVERIE, RxR) confirm the generalization and effectiveness of our algorithm.

This paper aims to reconstruct the scene geometry from multi-view images with strong robustness and high quality. Previous learning-based methods incorporate neural networks into the multi-view stereo matching and have shown impressive reconstruction results. However, due to the reliance on matching across input images, they typically suffer from high GPU memory consumption and tend to fail in sparse view scenarios. To overcome this problem, we develop a new pipeline, named Murre, for multi-view geometry reconstruction of 3D scenes based on SfM-guided monocular depth estimation. For input images, Murre first recovers the SfM point cloud that captures the global scene structure, and then use it to guide a conditional diffusion model to produce multi-view metric depth maps for the final TSDF fusion. By predicting the depth map from a single image, Murre bypasses the multi-view matching step and naturally resolves the issues of previous MVS-based methods. In addition, the diffusion-based model can easily leverage the powerful priors of 2D foundation models, achieving good generalization ability across diverse real-world scenes. To obtain multi-view consistent depth maps, our key design is providing effective guidance on the diffusion model through the SfM point cloud, which is a condensed form of multiview information, highlighting the scene’s salient structure, and can be readily transformed into sparse depth maps to drive the image-space estimation process. We evaluate the reconstruction quality of Murre in various types of real-world datasets including indoor, streetscapes, and aerial scenes, surpassing state-of-the-art MVS-based and implicit neural reconstruction-based methods. The code and supplementary materials are available at https://zju3dv.github.io/murre/.

Compositional zero-shot learning (CZSL) aims to recognize unseen attribute-object compositions by learning the primitive concepts (i.e., attribute and object) from the training set. While recent works achieve impressive results in CZSL by leveraging large vision-language models like CLIP, they ignore the rich semantic relationships between primitive concepts and their compositions. In this work, we propose LogiCzsl, a novel logic-induced learning framework to explicitly model the semantic relationships. Our logic-induced learning framework formulates the relational knowledge constructed from large language models as a set of logic rules, and grounds them onto the training data. Our logic-induced losses are complementary to the widely used CZSL losses, therefore can be employed to inject the semantic information into any existing CZSL methods. Extensive experimental results show that our method brings significant performance improvements across diverse datasets (i.e., CGQA, UT-Zappos50K, MIT-States) with strong CLIP-based methods and settings (i.e., Close World, Open World).

Decoupling from customized parametric templates represents a crucial step toward the creation of fully flexible, animatable articulated models. While existing template-free methods can achieve high-fidelity reconstruction in observed views, they struggle to recover plausible canonical models, resulting in suboptimal animation quality. This limitation stems from overlooking the fundamental ambiguity in canonical reconstruction, where multiple canonical models could explain the same observed views. By revealing the entanglement between the canonical ambiguity and incorrect skinning, we present a self-supervised framework that learns both plausible skinning and accurate canonical geometry using only sparse pose data. Our method, TAGA, uses explicit 3D Gaussians as skinning carriers and characterizes the ambiguity as "Ambiguous Gaussians" with incorrect skinning weights. TAGA then corrects ambiguous Gaussians in the observation space using anomaly detection. With the corrected ones, we enforce cycle consistency constraints on both geometry and skinning to refine the corresponding Gaussians in the canonical space through a new backward method. Compared to existing state-of-the-art template-free methods, TAGA delivers superior visual fidelity for novel views and poses, while significantly improving training and rendering speeds. Experiments on challenging datasets with limited pose variations further demonstrate the robustness and generality of TAGA.

We present UniAlign, a unified model to align an arbitrary number of modalities (e.g., image, text, audio, 3D point cloud, etc.) through one encoder and a single training phase. Existing solutions typically employ distinct encoders for each modality, resulting in increased parameters as the number of modalities grows. In contrast, UniAlign proposes a modality-aware adaptation of the powerful mixture- of-experts (MoE) schema and further integrates it with Low- Rank Adaptation (LoRA), efficiently scaling the encoder to accommodate inputs in diverse modalities while maintaining a fixed computational overhead. Moreover, prior work often requires separate training for each extended modality. This leads to task-specific models and further hinders the communication between modalities. To address this, we propose a soft modality binding strategy that aligns all modalities using unpaired data samples across datasets. Two additional training objectives are introduced to distill knowledge from well-aligned anchor modalities and prior multimodal models, elevating UniAlign into a high performance multimodal foundation model. Experiments on 11 benchmarks across 6 different modalities demonstrate that UniAlign could achieve comparable performance to SOTA approaches, while using merely 7.8M trainable parameters and maintaining an identical model with the same weight across all tasks.

Compositional Zero-Shot Learning (CZSL) aims to recognize unseen combinations of known objects and attributes by leveraging knowledge from previously seen compositions. Traditional approaches primarily focus on disentangling attributes and objects, treating them as independent entities during learning. However, this assumption overlooks the semantic constraints and contextual dependencies inside a composition. For example, certain attributes naturally pair with specific objects (e.g., "striped" applies to "zebra" or "shirts" but not "sky" or "water"), while the same attribute can manifest differently depending on context (e.g., "young" in "young tree" vs. "young dog"). Thus, capturing attribute-object interdependence remains a fundamental yet long-ignored challenge in CZSL. In this paper, we adopt a Conditional Probability Framework (CPF) to explicitly model attribute-object dependencies. We decompose the probability of a composition into two components: the likelihood of an object and the conditional likelihood of its attribute. To enhance object feature learning, we incorporate textual descriptors to highlight semantically relevant image regions. These enhanced object features then guide attribute learning through a cross-attention mechanism, ensuring better contextual alignment. By jointly optimizing object likelihood and conditional attribute likelihood, our method effectively captures compositional dependencies and generalizes well to unseen compositions. Extensive experiments on multiple CZSL benchmarks demonstrate the superiority of our approach. Code is available at here.

DETR introduces a simplified one-stage framework for scene graph generation (SGG) but faces challenges of sparse supervision and false negative samples. The former occurs because each image typically contains fewer than 10 relation annotations, while DETR-based SGG models employ over 100 relation queries. Each ground truth relation is assigned to only one query during training. The latter arises when one ground truth relation may have multiple queries with similar matching scores, leading to suboptimally matched queries being treated as negative samples. To address these, we propose Hydra-SGG, a one-stage SGG method featuring a Hybrid Relation Assignment. This approach combines a One-to-One Relation Assignment with an IoU-based One-to-Many Relation Assignment, increasing positive training samples and mitigating sparse supervision. In addition, we empirically demonstrate that removing self-attention between relation queries leads to duplicate predictions, which actually benefits the proposed One-to-Many Relation Assignment. With this insight, we introduce Hydra Branch, an auxiliary decoder without self-attention layers, to further enhance One-to-Many Relation Assignment by promoting different queries to make the same relation prediction. Hydra-SGG achieves state-of-the-art performance on multiple datasets, including VG150 (16.0 mR@50), Open Images V6 (50.1 weighted score), and GQA (12.7 mR@50). Our code and pre-trained models will be released on Hydra-SGG.

Learning primitive (i.e., attribute and object) concepts from seen compositions is the primary challenge of Compositional Zero-Shot Learning (CZSL). Existing CZSL solutions typically rely on oversimplified data assumptions, e.g., modeling each primitive with a single centroid primitive presentation, ignoring the natural diversities of the attribute (resp. object) when coupled with different objects (resp. attribute). In this work, we develop ClusPro, a robust clustering-based prototype mining framework for CZSL that defines the conceptual boundaries of primitives through a set of diversified prototypes. Specifically, ClusPro conducts within-primitive clustering on the embedding space for automatically discovering and dynamically updating prototypes. To learn high-quality embeddings for discriminative prototype construction, ClusPro repaints a well-structured and independent primitive embedding space, ensuring intra-primitive separation and inter-primitive decorrelation through prototype-based contrastive learning and decorrelation learning. Moreover, ClusPro effectively performs prototype clustering in a non-parametric fashion without the introduction of additional learnable parameters or computational budget during testing. Experiments on three benchmarks demonstrate ClusPro outperforms various top-leading CZSL solutions under both closed-world and open-world settings. Our code is available at CLUSPRO.

Recent advancements in large language models (LLMs) revolutionize the field of intelligent agents, enabling collaborative multi-agent systems capable of tackling complex problems across various domains. However, the potential of conformity within these systems, analogous to phenomena like conformity bias and group-think in human group dynamics, remains largely unexplored, raising concerns about their collective problem-solving capabilities and possible ethical implications. This paper presents a comprehensive study on conformity in LLM-driven multi-agent systems, focusing on three aspects: the existence of conformity, the factors influencing conformity, and potential mitigation strategies. In particular, we introduce BenchForm, a new conformity-oriented benchmark, featuring reasoning-intensive tasks and five distinct interaction protocols designed to probe LLMs’ behavior in collaborative scenarios. Several representative LLMs are evaluated on BenchForm, using metrics such as conformity rate and independence rate to quantify conformity’s impact. Our analysis delves into factors influencing conformity, including interaction time and majority size, and examines how the subject agent rationalize its conforming behavior. Furthermore, we explore two strategies to mitigate conformity effects, i.e., developing enhanced persona and implementing a reflection mechanism. Several interesting findings regarding LLMs’ conformity are derived from empirical results and case studies. We hope that these insights can pave the way for more robust and ethically-aligned collaborative AI systems. Our benchmark and code are available at BenchForm.

Human-Object Interaction Detection (HOI-DET) aims to localize human-object pairs and identify their interactive relationships. To aggregate contextual cues, existing methods typically propagate information across all detected entities via self‑attention mechanisms, or establish message passing between humans and objects with bipartite graphs. However, they primarily focus on pairwise relationships, overlooking that interactions in real-world scenarios often emerge from collective behaviors ($\textit{i}.\textit{e}.$, multiple humans and objects engaging in joint activities). In light of this, we revisit relation modeling from a $\textit{group}$ view and propose GroupHOI, a framework that propagates contextual information in terms of $\textit{geometric proximity}$ and $\textit{semantic similarity}$. To exploit the geometric proximity, humans and objects are grouped into distinct clusters using a learnable proximity estimator based on spatial features derived from bounding boxes. In each group, a soft correspondence is computed via self-attention to aggregate and dispatch contextual cues. To incorporate the semantic similarity, we enhance the vanilla transformer-based interaction decoder with local contextual cues from HO-pair features. Extensive experiments on HICO-DET and V-COCO benchmarks demonstrate the superiority of GroupHOI over the state-of-the-art methods. It also exhibits leading performance on the more challenging Nonverbal Interaction Detection (NVI-DET) task, which involves varied forms of higher-order interactions within groups.

Current 3D gaze estimation methods struggle to generalize across diverse data domains, primarily due to $\textbf{i)}$ $\textit{the scarcity of annotated datasets}$, and $\textbf{ii)}$ $\textit{the insufficient diversity of labeled data}$. In this work, we present OmniGaze, a semi-supervised framework for 3D gaze estimation, which utilizes large-scale unlabeled data collected from diverse and unconstrained real-world environments to mitigate domain bias and generalize gaze estimation in the wild. First, we build a diverse collection of unlabeled facial images, varying in facial appearances, background environments, illumination conditions, head poses, and eye occlusions. In order to leverage unlabeled data spanning a broader distribution, OmniGaze adopts a standard pseudo-labeling strategy and devises a reward model to assess the reliability of pseudo labels. Beyond pseudo labels as 3D direction vectors, the reward model also incorporates visual embeddings extracted by an off-the-shelf visual encoder and semantic cues from gaze perspective generated by prompting a Multimodal Large Language Model to compute confidence scores. Then, these scores are utilized to select high-quality pseudo labels and weight them for loss computation. Extensive experiments demonstrate that OmniGaze achieves state-of-the-art performance on five datasets under both in-domain and cross-domain settings. Furthermore, we also evaluate the efficacy of OmniGaze as a scalable data engine for gaze estimation, which exhibits robust zero-shot generalization on four unseen datasets.

Visual knowledge is a new form of knowledge representation that can encapsulate visual concepts and their relations in a succinct, comprehensive, and interpretable manner, with a deep root in cognitive psychology. As the knowledge of the visual world has been identified as an indispensable component of human cognition and intelligence, visual knowledge is poised to have a pivotal role in establishing machine intelligence. With the recent advance of artificial intelligence (AI) techniques, large AI models (or foundation models) have emerged as a potent tool capable of extracting versatile patterns from broad data as implicit knowledge, and abstracting them into an outrageous amount of numeric parameters. To pave the way for creating visual knowledge empowered AI machines in this coming wave, we present a timely review that investigates the origins and development of visual knowledge in the pre-big-model era, and accentuates the opportunities and unique role of visual knowledge in the big model era.

Vision-language navigation is a task that requires an agent to follow instructions to navigate in environments. It becomes increasingly crucial in the field of embodied AI, with potential applications in autonomous navigation, search and rescue, and human-robot interaction. In this paper, we propose to address a more practical yet challenging counterpart setting - vision-language navigation in continuous environments (VLN-CE). To develop a robust VLN-CE agent, we propose a new navigation framework, ETPNav, which focuses on two critical skills: 1) the capability to abstract environments and generate long-range navigation plans, and 2) the ability of obstacle-avoiding control in continuous environments. ETPNav performs online topological mapping of environments by self-organizing predicted waypoints along a traversed path, without prior environmental experience. It privileges the agent to break down the navigation procedure into high-level planning and low-level control. Concurrently, ETPNav utilizes a transformer-based cross-modal planner to generate navigation plans based on topological maps and instructions. The plan is then performed through an obstacle-avoiding controller that leverages a trial-and-error heuristic to prevent navigation from getting stuck in obstacles. Experimental results demonstrate the effectiveness of the proposed method. ETPNav yields more than 10% and 20% improvements over prior state-of-the-art on R2R-CE and RxR-CE datasets, respectively.

Neural-symbolic computing (NeSy), which pursues the integration of the symbolic and statistical paradigms of cognition, has been an active research area of Artificial Intelligence (AI) for many years. As NeSy shows promise of reconciling the advantages of reasoning and interpretability of symbolic representation and robust learning in neural networks, it may serve as a catalyst for the next generation of AI. In the present paper, we provide a systematic overview of the recent developments and important contributions of NeSy research. First, we introduce study history of this area, covering early work and foundations. We further discuss background concepts and identify key driving factors behind the development of NeSy. Afterward, we categorize recent landmark approaches along several main characteristics that underline this research paradigm, including neural-symbolic integration, knowledge representation, knowledge embedding, and functionality. Next, we briefly discuss the successful application of modern NeSy approaches in several domains. Then, we benchmark several NeSy methods on three representative application tasks. Finally, we identify the open problems together with potential future research directions. This survey is expected to help new researchers enter this rapidly evolving field and accelerate the progress towards data-and knowledge-driven AI.

3D decision-critical tasks urgently require research on explanations to ensure system reliability and transparency. Extensive explanatory research has been conducted on 2D images, but there is a lack in the 3D field. Furthermore, the existing explanations for 3D models are post-hoc and can be misleading, as they separate explanations from the original model. To address these issues, we propose an ad-hoc interpretable classifier for 3D point clouds (i.e., Interpretable3D). As an intuitive case-based classifier, Interpretable3D can provide reliable ad-hoc explanations without any embarrassing nuances. It allows users to understand how queries are embedded within past observations in prototype sets. Interpretable3D has two iterative training steps: 1) updating one prototype with the mean of the embeddings within the same sub-class in Prototype Estimation, and 2) penalizing or rewarding the estimated prototypes in Prototype Optimization. The mean of embeddings has a clear statistical meaning, i.e., class sub-centers. Moreover, we update prototypes with their most similar observations in the last few epochs. Finally, Interpretable3D classifies new samples according to prototypes. We evaluate the performance of Interpretable3D on four popular point cloud models: DGCNN, PointNet2, PointMLP, and PointNeXt. Our Interpretable3D demonstrates comparable or superior performance compared to softmax-based black-box models in the tasks of 3D shape classification and part segmentation. Our code is released at: github.com/FengZicai/Interpretable3D.

Autonomous systems need to process large-scale, sparse, and irregular point clouds with limited compute resources. Consequently, it is essential to develop LiDAR perception methods that are both efficient and effective. Although naive-ly enlarging 3D kernel size can enhance performance, it will also lead to a cubically-increasing overhead. Therefore, it is crucial to develop streamlined 3D large kernel designs that eliminate redundant weights and work effectively with larger kernels. In this paper, we propose an efficient and effective Large Sparse Kernel 3D Neural Network (LSK3DNet) that leverages dynamic pruning to amplify the 3D kernel size. Our method comprises two core components: Spatial-wise Dynamic Sparsity (SDS) and Channel-wise Weight Selection (CWS). SDS dynamically prunes and regrows volumetric weights from the beginning to learn a large sparse 3D kernel. It not only boosts performance but also significantly reduces model size and computational cost. Moreover, CWS selects the most important channels for 3D convolution during training and subsequently prunes the redundant channels to accelerate inference for 3D vision tasks. We demonstrate the effectiveness of LSK3DNet on three benchmark datasets and five tracks compared with classical models and large kernel designs. Notably, LSK3DNet achieves the state-of-the-art performance on SemanticKITTI (i.e., 75.6% on single-scan and 63.4% on multi-scan), with roughly 40% model size re-duction and 60% computing operations reduction compared to the naive large 3D kernel model.

Object detection in remote sensing images (RSIs) often suffers from several increasing challenges, including the large variation in object scales and the diverse-ranging context. Prior methods tried to address these challenges by expanding the spatial receptive field of the backbone, either through large-kernel convolution or dilated convolution. However, the former typically introduces considerable background noise, while the latter risks generating overly sparse feature representations. In this paper, we introduce the Poly Kernel Inception Network (PKINet) to handle the above challenges. PKINet employs multi-scale convolution kernels without dilation to extract object features of varying scales and capture local context. In addition, a Context Anchor Attention (CAA) module is introduced in parallel to capture long-range contextual information. These two components work jointly to advance the performance of PKINet on four challenging remote sensing detection benchmarks, namely DOTA-v1.0, DOTA-v1.5, HRSC2016, and DIOR-R.

We investigate a fundamental aspect of machine vision: the measurement of features, by revisiting clustering, one of the most classic approaches in machine learning and data analysis. Existing visual feature extractors, including ConvNets, ViTs, and MLPs, represent an image as rectangular regions. Though prevalent, such a grid-style paradigm is built upon engineering practice and lacks explicit modeling of data distribution. In this work, we propose feature extraction with clustering (FEC), a conceptually elegant yet surprisingly ad-hoc interpretable neural clustering framework, which views feature extraction as a process of selecting representatives from data and thus automatically captures the underlying data distribution. Given an image, FEC alternates between grouping pixels into individual clusters to abstract representatives and updating the deep features of pixels with current representatives. Such an iterative working mechanism is implemented in the form of several neural layers and the final representatives can be used for downstream tasks. The cluster assignments across layers, which can be viewed and inspected by humans, make the forward process of FEC fully transparent and empower it with promising ad-hoc interpretability. Extensive experiments on various visual recognition models and tasks verify the effectiveness, generality, and interpretability of FEC. We expect this work will provoke a rethink of the current de facto grid-style paradigm.

Prominent solutions for medical image segmentation are typically tailored for automatic or interactive setups, posing challenges in facilitating progress achieved in one task to another. This also necessitates separate models for each task, duplicating both training time and parameters. To address above issues, we introduce S2VNet, a universal framework that leverages Slice-to- Volume propagation to unify auto-matic/interactive segmentation within a single model and one training session. Inspired by clustering-based segmen-tation techniques, S2VNet makes full use of the slice-wise structure of volumetric data by initializing cluster centers from the cluster results of previous slice. This enables knowl-edge acquired from prior slices to assist in the segmentation of the current slice, further efficiently bridging the communication between remote slices using mere 2D networks. Moreover, such a framework readily accommodates inter-active segmentation with no architectural change, simply by initializing centroids from user inputs. S2VNet distin-guishes itselfby swift inference speeds and reduced memory consumption compared to prevailing 3D solutions. It can also handle multi-class interactions with each of them serving to initialize different centroids. Experiments on three benchmarks demonstrate S2VNet surpasses task-specified solutions on both automatic/interactive setups.

Vision-language navigation (VLN) requires an agent to navigate through an 3D environment based on visual ob-servations and natural language instructions. It is clear that the pivotal factor for successful navigation lies in the comprehensive scene understanding. Previous VLN agents employ monocular frameworks to extract 2D features of perspective views directly. Though straightforward, they struggle for capturing 3D geometry and semantics, leading to a partial and incomplete environment representation. To achieve a comprehensive 3D representation with fine- grained details, we introduce a Volumetric Environ-ment Representation (VER), which voxelizes the physical world into structured 3D cells. For each cell, VER aggre-gates multi-view 2D features into such a unified 3D space via 2D-3D sampling. Through coarse-to-fine feature extraction and multi-task learning for VER, our agent predicts 3D occupancy, 3D room layout, and 3D bounding boxes jointly. Based on online collected VERs, our agent per-forms volume state estimation and builds episodic memory for predicting the next step. Experimental results show our environment representations from multi-task learning lead to evident performance gains on VLN. Our model achieves state-of-the-art performance across VLN benchmarks (R2R, REVERIE, and R4R).

Protein representation learning is a challenging task that aims to capture the structure and function of proteins from their amino acid sequences. Previous methods largely ignored the fact that not all amino acids are equally important for protein folding and activity. In this article, we propose a neural clustering framework that can automatically discover the critical components of a protein by considering both its primary and tertiary structure information. Our framework treats a protein as a graph, where each node represents an amino acid and each edge represents a spatial or sequential connection between amino acids. We then apply an iterative clustering strategy to group the nodes into clusters based on their 1D and 3D positions and assign scores to each cluster. We select the highest-scoring clusters and use their medoid nodes for the next iteration of clustering, until we obtain a hierarchical and informative representation of the protein. We evaluate on four protein-related tasks: protein fold classification, enzyme reaction classification, gene ontology term prediction, and enzyme commission number prediction. Experimental results demonstrate that our method achieves state-of-the-art performance.

Reconstructing the viewed images from human brain activity bridges human and computer vision through the Brain-Computer Interface. The inherent variability in brain function between individuals leads existing literature to focus on acquiring separate models for each individual using their respective brain signal data, ignoring commonalities between these data. In this article, we devise Psychometry, an omnifit model for reconstructing images from functional Magnetic Resonance Imaging (fMRI) obtained from different subjects. Psychometry incorporates an omni mixture-of-experts (Omni MoE) module where all the experts work together to capture the inter-subject commonalities, while each expert associated with subject-specific parameters copes with the individual differences. Moreover, Psychometry is equipped with a retrieval-enhanced inference strategy, termed Ecphory, which aims to enhance the learned fMRI representation via retrieving from prestored subject-specific memories. These designs collectively render Psychometry omnifit and efficient, enabling it to capture both inter-subject commonality and individual specificity across subjects. As a result, the enhanced fMRI representations serve as conditional signals to guide a generation model to reconstruct high-quality and realistic images, establishing Psychometry as state-of-the-art in terms of both high-level and low-level metrics.

Bird's eye view (BEV) representation has emerged as a dominant solution for describing 3D space in autonomous driving scenarios. However, objects in the BEV representation typically exhibit small sizes, and the associated point cloud context is inherently sparse, which leads to great challenges for reliable 3D perception. In this paper, we propose IS-Fusion, an innovative multimodal fusion framework that jointly captures the Instance- and Scene-level contextual information. IS-Fusion essentially differs from existing approaches that only focus on the BEV scene-level fusion by explicitly incorporating instance-level multimodal information, thus facilitating the instance-centric tasks like 3D object detection. It comprises a Hierarchical Scene Fusion (HSF) module and an Instance-Guided Fusion (IGF) module. HSF applies Point-to-Grid and Grid-to-Region transformers to capture the multimodal scene context at different granularities. IGF mines instance candidates, explores their relationships, and aggregates the local multimodal context for each instance. These instances then serve as guidance to enhance the scene feature and yield an instance-aware BEV representation. On the challenging nuScenes benchmark, IS-Fusion outperforms all the published multimodal works to date. Code is available at: https://github.com/yinjunbo/IS-Fusion.

As the scale of vision models continues to grow, the emergence of Visual Prompt Tuning (VPT) as a parameter-efficient transfer learning technique has gained attention due to its superior performance compared to traditional full-finetuning. However, the conditions favoring VPT (the "when") and the underlying rationale (the "why") remain unclear. In this paper, we conduct a comprehensive analysis across 19 distinct datasets and tasks. To understand the "when" aspect, we identify the scenarios where VPT proves favorable by two dimensions: task objectives and data distributions. We find that VPT is preferrable when there is 1) a substantial disparity between the original and the downstream task objectives ($e.g.$, transitioning from classification to counting), or 2) a notable similarity in data distributions between the two tasks ($e.g.$, both involve natural images). In exploring the "why" dimension, our results indicate VPT's success cannot be attributed solely to overfitting and optimization considerations. The unique way VPT preserves original features and adds parameters appears to be a pivotal factor. Our study provides insights into VPT's mechanisms, and offers guidance for its optimal utilization.

Recent LLM-driven visual agents mainly focus on solving image-based tasks, which limits their ability to understand dynamic scenes, making it far from real-life applications like guiding students in laboratory experiments and identifying their mistakes. Hence, this paper explores DoraemonGPT, a comprehensive and conceptually elegant system driven by LLMs to understand dynamic scenes. Considering the video modality better reflects the ever-changing nature of real-world scenarios, we exemplify DoraemonGPT as a video agent. Given a video with a question/task, DoraemonGPT begins by converting the input video into a symbolic memory that stores task-related attributes. This structured representation allows for spatial-temporal querying and reasoning by well-designed sub-task tools, resulting in concise intermediate results. Recognizing that LLMs have limited internal knowledge when it comes to specialized domains (e.g., analyzing the scientific principles underlying experiments), we incorporate plug-and-play tools to assess external knowledge and address tasks across different domains. Moreover, a novel LLM-driven planner based on Monte Carlo Tree Search is introduced to explore the large planning space for scheduling various tools. The planner iteratively finds feasible solutions by backpropagating the result’s reward, and multiple solutions can be summarized into an improved final answer. We extensively evaluate DoraemonGPT’s effectiveness on three benchmarks and several in-the-wild scenarios. Project page: https://z-x-yang.github.io/doraemon-gpt.

Current approaches for open-vocabulary scene graph generation (OVSGG) use vision-language models such as CLIP and follow a standard zero-shot pipeline – computing similarity between the query image and the text embeddings for each category (i.e., text classifiers). In this work, we argue that the text classifiers adopted by existing OVSGG methods, i.e., category-/part-level prompts, are scene-agnostic as they remain unchanged across contexts. Using such fixed text classifiers not only struggles to model visual relations with high variance, but also falls short in adapting to distinct contexts. To plug these intrinsic shortcomings, we devise SDSGG, a scene-specific description based OVSGG framework where the weights of text classifiers are adaptively adjusted according to the visual content. In particular, to generate comprehensive and diverse descriptions oriented to the scene, an LLM is asked to play different roles (e.g., biologist and engineer) to analyze and discuss the descriptive features of a given scene from different views. Unlike previous efforts simply treating the generated descriptions as mutually equivalent text classifiers, SDSGG is equipped with an advanced renormalization mechanism to adjust the influence of each text classifier based on its relevance to the presented scene (this is what the term “specific” means). Furthermore, to capture the complicated interplay between subjects and objects, we propose a new lightweight module called mutual visual adapter. It refines CLIP’s ability to recognize relations by learning an interaction-aware semantic space. Extensive experiments on prevalent benchmarks show that SDSGG significantly outperforms top-leading methods.

Prevalent human-object interaction (HOI) detection approaches typically leverage large-scale visual-linguistic models to help recognize events involving humans and objects. Though promising, models trained via contrastive learning on text-image pairs often neglect mid/low-level visual cues and struggle at compositional reasoning. In response, we introduce DIFFUSIONHOI, a new HOI detector shedding light on text-to-image diffusion models. Unlike the aforementioned models, diffusion models excel in discerning mid/low-level visual concepts as generative models, and possess strong compositionality to handle novel concepts expressed in text inputs. Considering diffusion models usually emphasize instance objects, we first devise an inversion-based strategy to learn the expression of relation patterns between humans and objects in embedding space. These learned relation embeddings then serve as textual prompts, to steer diffusion models generate images that depict specific interactions, and extract HOI-relevant cues from images without heavy finetuning. Benefited from above, DIFFUSIONHOI achieves SOTA performance on three datasets under both regular and zero-shot setups.

Vision-language navigation (VLN) requires an agent to execute actions following human instructions. Existing VLN models are optimized through expert demonstrations by supervised behavioural cloning or incorporating manual reward engineering. While straightforward, these efforts overlook the accumulation of errors in the Markov decision process, and struggle to match the distribution of the expert policy. Going beyond this, we propose an Energy-based Navigation Policy (ENP) to model the joint state-action distribution using an energy-based model. At each step, low energy values correspond to the state-action pairs that the expert is most likely to perform, and vice versa. Theoretically, the optimization objective is equivalent to minimizing the forward divergence between the occupancy measure of the expert and ours. Consequently, ENP learns to globally align with the expert policy by maximizing the likelihood of the actions and modeling the dynamics of the navigation states in a collaborative manner. With a variety of VLN architectures, ENP achieves promising performances on R2R, REVERIE, RxR, and R2R-CE, unleashing the power of existing VLN models.

Humans are able to recognize structured relations in observation, allowing us to decompose complex scenes into simpler parts and abstract the visual world at multiple levels. However, such hierarchical reasoning ability of human perception remains largely unexplored in current literature of semantic segmentation. Existing works are often aware of flatten labels and distinguish all the semantic categories exclusively for each pixel. In this work, we instead address hierarchical semantic segmentation (HSS), with the aim of providing a structured, pixel-wise description of visual observation in terms of a class hierarchy. We deviseHssn, a general HSS framework that tackles two critical issues in this task:i)how to efficiently adapt existing hierarchy-agnostic segmentation networks to the HSS setting, andii)how to leverage the class hierarchy to regularize HSS network learning. To addressi),Hssndirectly casts HSS as a pixel-wise multi-label classification task, only bringing minimal architecture change to current segmentation models. To solveii),Hssnfirst explores inherent properties of the hierarchy as a training objective, which enforces segmentation predictions to obey the hierarchy structure. Furthermore, with a set of hierarchy-induced margin constraints,Hssnefficiently reshapes the learned pixel embedding space, so as to generate hierarchy-aware pixel representations and facilitate structured segmentation eventually. Building uponHssn, we further exploit the mutual exclusion relation between semantic labels and strengthen the margin based regularization strategy with more meaningful constrains, leading toHssn+, a more effective framework for HSS. We conduct extensive experiments on six semantic segmentation datasets (i.e., Mapillary Vistas 2.0, Cityscapes, LIP, PASCAL-Person-Part, PASCAL-Part-58, and PASCAL-Part-108), with different class hierarchies, network architectures, and backbones, and the results confirm the generalization and superiority of our algorithms.

This article studies the problem of learning weakly supervised semantic segmentation (WSSS) from image-level supervision only. Current popular solutions leverage object localization maps from classifiers as supervision for semantic segmentation learning, and struggle to make the localization maps capture more complete object content. Rather than previous efforts that primarily focus on intra-image information, we address the value of cross-image semantic relations for comprehensive object pattern mining. To achieve this, two neural co-attentions are incorporated into the classifier to complementarily capture cross-image semantic similarities and differences. In particular, given a pair of training images, one co-attention enforces the classifier to recognize the common semantics from co-attentive objects, while the other one, called contrastive co-attention, drives the classifier to identify the unique semantics from the rest, unshared objects. This helps the classifier discover more object patterns and better ground semantics in image regions. In addition to boosting object pattern learning, the co-attention can leverage context from other related images to improve localization map inference, hence eventually benefiting semantic segmentation learning. More importantly, our algorithm provides a unified framework that handles well different WSSS settings, i.e., learning WSSS with 1) precise image-level supervision only, 2) extra simple single-label data, and 3) extra noisy web data. Without bells and whistles, it sets new state-of-the-arts on all these settings. Moreover, our approach ranked 1st place in the Weakly-Supervised Semantic Segmentation Track of CVPR2020 Learning from Imperfect Data Challenge. The extensive experimental results demonstrate well the efficacy and high utility of our method.

Visual-language navigation (VLN) is a challenging task that requires embodied agents to follow natural language instructions to navigate in previously unseen environments. However, existing literature put most emphasis on interpreting instructions into actions, only delivering “dumb” wayfinding agents which cannot actively use natural language to communicate with humans. In this article, we deviseLana, alanguage-capablenavigationagent which is able to not only execute human-written navigation commands, but also provide route descriptions to humans. This is achieved by simultaneously learning instruction following and generation with only one single model. More specifically, two encoders, respectively for route and language encoding, are built and shared by two decoders, respectively, for action prediction and instruction generation, so as to exploit cross-task knowledge and capture task-specific characteristics. Throughout pretraining and fine-tuning, both instruction following and generation are set as optimization objectives. We further extendLanaby exploiting object semantics during route encoding. This leads toLana+, a more powerful framework that simulates the way humans refer to landmarks for instructions composition and wayfinding. We empirically verify that, compared with recent advanced task-specific solutions,Lanaattains better performances on both instruction following and generation, with nearly half complexity. In addition, endowed with language generation capability,Lanacan explain to humans its behaviors and assist human's wayfinding. Benefiting from landmark information,Lana+exhibits even more impressive performance. This work is expected to foster future efforts towards building more trustworthy and socially-intelligent navigation robots.

This paper delves into the challenges of achieving scalable and effective multi-object modeling for semi-supervised Video Object Segmentation (VOS). Previous VOS methods decode features with a single positive object, limiting the learning of multi-object representation as they must match and segment each target separately under multi-object scenarios. Additionally, earlier techniques catered to specific application objectives and lacked the flexibility to fulfill different speed-accuracy requirements. To address these problems, we present two innovative approaches, Associating Objects with Transformers (AOT) and Associating Objects with Scalable Transformers (AOST). In pursuing effective multi-object modeling, AOT introduces the IDentification (ID) mechanism to allocate each object a unique identity. This approach enables the network to model the associations among all objects simultaneously, thus facilitating the tracking and segmentation of objects in a single network pass. To address the challenge of inflexible deployment, AOST further integrates scalable long short-term transformers that incorporate scalable supervision and layer-wise ID-based attention. This enables online architecture scalability in VOS for the first time and overcomes ID embeddings' representation limitations. Given the absence of a benchmark for VOS involving densely multi-object annotations, we propose a challenging Video Object Segmentation in the Wild (VOSW) benchmark to validate our approaches. We evaluated various AOT and AOST variants using extensive experiments across VOSW and five commonly used VOS benchmarks, including YouTube-VOS 2018 & 2019 Val, DAVIS-2017 Val & Test, and DAVIS-2016. Our approaches surpass the state-of-the-art competitors and display exceptional efficiency and scalability consistently across all six benchmarks. Moreover, we notably achieved the$\mathbf {1^{st}}$position in the 3 rd Large-scale Video Object Segmentation Challenge. Project page:https://github.com/yoxu515/aot-benchmark.

This work studies the problem of image semantic segmentation. Current approaches focus mainly on mining "local" context, i.e., dependencies between pixels within individual images, by specifically-designed, context aggregation modules (e.g., dilated convolution, neural attention) or structure-aware optimization objectives (e.g., IoU-like loss). However, they ignore "global" context of the training data, i.e., rich semantic relations between pixels across different images. Inspired by recent advance in unsupervised contrastive representation learning, we propose a pixel-wise contrastive algorithm, dubbed as PiCo, for semantic segmentation in the fully supervised learning setting. The core idea is to enforce pixel embeddings belonging to a same semantic class to be more similar than embeddings from different classes. It raises a pixel-wise metric learning paradigm for semantic segmentation, by explicitly exploring the structures of labeled pixels, which were rarely studied before. Our training algorithm is compatible with modern segmentation solutions without extra overhead during testing. We experimentally show that, with famous segmentation models (i.e., DeepLabV3, HRNet, OCRNet, SegFormer, Segmenter, MaskFormer) and backbones (i.e., MobileNet, ResNet, HRNet, MiT, ViT), our algorithm brings consistent performance improvements across diverse datasets (i.e., Cityscapes, ADE20 K, PASCAL-Context, COCO-Stuff, CamVid). We expect that this work will encourage our community to rethink the current de facto training paradigm in semantic segmentation.

Deep learning based semantic segmentation solutions have yielded compelling results over the preceding decade. They encompass diverse network architectures (FCN based or attention based), along with various mask decoding schemes (parametric softmax based or pixel-query based). Despite the divergence, they can be grouped within a unified framework by interpreting the softmax weights or query vectors as learnable class prototypes. In light of this prototype view, we reveal inherent limitations within the parametric segmentation regime, and accordingly develop a nonparametric alternative based on non-learnable prototypes. In contrast to previous approaches that entail the learning of a single weight/query vector per class in a fully parametric manner, our approach represents each class as a set of non-learnable prototypes, relying solely upon the mean features of training pixels within that class. The pixel-wise prediction is thus achieved by nonparametric nearest prototype retrieving. This allows our model to directly shape the pixel embedding space by optimizing the arrangement between embedded pixels and anchored prototypes. It is able to accommodate an arbitrary number of classes with a constant number of learnable parameters. Through empirical evaluation with FCN based and Transformer based segmentation models (i.e., HRNet, Swin, SegFormer, Mask2Former) and backbones (i.e., ResNet, HRNet, Swin, MiT), our nonparametric framework shows superior performance on standard segmentation datasets (i.e., ADE20 K, Cityscapes, COCO-Stuff), as well as in large-vocabulary semantic segmentation scenarios. We expect that this study will provoke a rethink of the current de facto semantic segmentation model design.

Currently, the success of image processing relies heavily on large well-annotated datasets. However, collecting and labeling video data are significantly more labor-intensive, posing major challenges for training video algorithms and limiting their practical applications. While label-efficient techniques for image data have advanced, solutions for video data are still emerging. Unlabeled video data, with their inherent structured nature, offer valuable assets for label-efficient learning. Unlike image data, video data naturally captures realistic transformations, providing rich samples for learning. Moreover, from a border perspective, video tasks hold great potential for applications like autonomous driving and video surveillance but present unique challenges due to the need to understand both spatial and temporal aspects. Leveraging label-efficient learning is essential for comprehensively understanding visual content and enabling a wide range of real-world video applications. This Special Issue on “Label-Efficient Learning for Video Data” seeks to advance research in this area, offering new insights and solutions to benefit both researchers and practitioners.

The objective of this paper is self-supervised learning of video object segmentation. We develop a unified framework which simultaneously models cross-frame dense correspondence for locally discriminative feature learning and embeds object-level context for target-mask decoding. As a result, it is able to directly learn to perform mask-guided sequential segmentation from unlabeled videos, in contrast to previous efforts usually relying on an oblique solution - cheaply “copying” labels according to pixel-wise correlations. Concretely, our algorithm alternates between i) clustering video pixels for creating pseudo segmentation labels ex nihilo; and ii) utilizing the pseudo labels to learn mask encoding and decoding for VOS. Unsupervised correspondence learning is further incorporated into this self-taught, mask embedding scheme, so as to ensure the generic nature of the learnt representation and avoid cluster degeneracy. Our algorithm sets state-of-the-arts on two standard benchmarks (i.e., DAVIS17and YouTube-VOS), narrowing the gap between self- and fully-supervised VOS, in terms of both performance and network architecture design.

Recently, visual-language navigation (VLN) - entailing robot agents to follow navigation instructions - has shown great advance. However, existing literature put most emphasis on interpreting instructions into actions, only delivering “dumb” wayfinding agents. In this article, we devise LANA, a language-capable navigation agent which is able to not only execute human-written navigation commands, but also provide route descriptions to humans. This is achieved by simultaneously learning instruction following and generation with only one single model. More specifically, two encoders, respectively for route and language encoding, are built and shared by two decoders, respectively for action prediction and instruction generation, so as to exploit cross-task knowledge and capture task-specific characteristics. Throughout pretraining and fine-tuning, both instruction following and generation are set as optimization objectives. We empirically verify that, compared with recent advanced task-specific solutions, LANA attains better performances on both instruction following and route description, with nearly half complexity. In addition, endowed with language generation capability, Lanacan explain to human its behaviours and assist human's wayfinding. This work is expected to foster future efforts towards building more trustworthy and socially-intelligent navigation robots.

Current top-leading solutions for video object segmentation (VOS) typically follow a matching-based regime: for each query frame, the segmentation mask is inferred according to its correspondence to previously processed and the first annotated frames. They simply exploit the supervisory signals from the groundtruth masks for learning mask prediction only, without posing any constraint on the space-time correspondence matching, which, however, is the fundamental building block of such regime. To alleviate this crucial yet commonly ignored issue, we devise a correspondence-aware training framework, which boosts matching-based VOS solutions by explicitly encouraging robust correspondence matching during network learning. Through comprehensively exploring the intrinsic coherence in videos on pixel and object levels, our algorithm reinforces the standard, fully supervised training of mask segmentation with label-free, contrastive correspondence learning. Without neither requiring extra annotation cost during training, nor causing speed delay during deployment, nor incurring architectural modification, our algorithm provides solid performance gains on four widely used benchmarks, i.e., DAVIS2016&2017, and YouTube-VOS2018&2019, on the top of famous matching-based VOS solutions.

Point cloud analysis (such as 3D segmentation and detection) is a challenging task, because of not only the irregular geometries of many millions of unordered points, but also the great variations caused by depth, viewpoint, occlusion, etc. Current studies put much focus on the adaption of neural networks to the complex geometries of point clouds, but are blind to a fundamental question: how to learn an appropriate point embedding space that is aware of both discriminative semantics and challenging variations? As a response, we propose a clustering based supervised learning scheme for point cloud analysis. Unlike current de-facto, scene-wise training paradigm, our algorithm conducts within-class clustering on the point embedding space for automatically discovering subclass patterns which are latent yet representative across scenes. The mined patterns are, in turn, used to repaint the embedding space, so as to respect the underlying distribution of the entire training dataset and improve the robustness to the variations. Our algorithm is principled and readily pluggable to modern point cloud segmentation networks during training, without extra overhead during testing. With various 3D network architectures (i.e., voxel-based, point-based, Transformer-based, automatically searched), our algorithm shows notable improvements on famous point cloud segmentation datasets (i.e., 2.0-2.6% on single-scan and 2.0-2.2% multi-scan of SemanticKITTI, 1.8-1.9% on S3DIS, in terms of mIoU). Our algorithm also demonstrates utility in 3D detection, showing 2.0-3.4% mAP gains on KITTI.

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.

As the size of transformer-based, models continues to grow, fine-tuning these large-scale pretrained vision models for new tasks has become increasingly parameter-intensive. Parameter-efficient learning has been developed to reduce the number of tunable parameters during fine-tuning. Although these methods show promising results, there is still a significant performance gap compared to full fine-tuning. To address this challenge, we propose an Effective and Efficient Visual Prompt Tuning (E2VPT) approach for large-scale transformer-based model adaptation. Specifically, we introduce a set of learnable key-value prompts and visual prompts into self-attention and input layers, respectively, to improve the effectiveness of model fine-tuning. Moreover, we design a prompt pruning procedure to systematically prune low importance prompts while preserving model performance, which largely enhances the model’s efficiency. Empirical results demonstrate that our approach outperforms several state-of-the-art baselines on two benchmarks, with considerably low parameter usage (e.g., 0.32% of model parameters on VTAB-1k). Our code is available at https://github.com/ChengHan111/E2VPT.

Current high-performance semantic segmentation models are purely data-driven sub-symbolic approaches and blind to the structured nature of the visual world. This is in stark contrast to human cognition which abstracts visual perceptions at multiple levels and conducts symbolic reasoning with such structured abstraction. To fill these fundamental gaps, we devise LogicSeg, a holistic visual semantic parser that integrates neural inductive learning and logic reasoning with both rich data and symbolic knowledge. In particular, the semantic concepts of interest are structured as a hierarchy, from which a set of constraints are derived for describing the symbolic relations and formalized as first-order logic rules. After fuzzy logic-based continuous relaxation, logical formulae are grounded onto data and neural computational graphs, hence enabling logic-induced network training. During inference, logical constraints are packaged into an iterative process and injected into the network in a form of several matrix multiplications, so as to achieve hierarchy-coherent prediction with logic reasoning. These designs together make LogicSeg a general and compact neural-logic machine that is readily integrated into existing segmentation models. Extensive experiments over four datasets with various segmentation models and backbones verify the effectiveness and generality of LogicSeg.We believe this study opens a new avenue for visual semantic parsing.

Recent advances in semi-supervised semantic segmentation have been heavily reliant on pseudo labeling to compensate for limited labeled data, disregarding the valuable relational knowledge among semantic concepts. To bridge this gap, we devise LogicDiag, a brand new neural-logic semi-supervised learning framework. Our key insight is that conflicts within pseudo labels, identified through symbolic knowledge, can serve as strong yet commonly ignored learning signals. LogicDiag resolves such conflicts via reasoning with logic-induced diagnoses, enabling the recovery of (potentially) erroneous pseudo labels, ultimately alleviating the notorious error accumulation problem. We showcase the practical application of LogicDiag in the data-hungry segmentation scenario, where we formalize the structured abstraction of semantic concepts as a set of logic rules. Extensive experiments on three standard semi-supervised semantic segmentation benchmarks demonstrate the effectiveness and generality of LogicDiag. Moreover, LogicDiag highlights the promising opportunities arising from the systematic integration of symbolic reasoning into the prevalent statistical, neural learning approaches.

Vision-language navigation (VLN), which entails an agent to navigate 3D environments following human instructions, has shown great advances. However, current agents are built upon panoramic observations, which hinders their ability to perceive 3D scene geometry and easily leads to ambiguous selection of panoramic view. To address these limitations, we present a BEV Scene Graph (BSG), which leverages multi-step BEV representations to encode scene layouts and geometric cues of indoor environment under the supervision of 3D detection. During navigation, BSG builds a local BEV representation at each step and maintains a BEV-based global scene map, which stores and organizes all the online collected local BEV representations according to their topological relations. Based on BSG, the agent predicts a local BEV grid-level decision score and a global graph-level decision score, combined with a subview selection score on panoramic views, for more accurate action prediction. Our approach significantly outperforms state-of-the-art methods on REVERIE, R2R, and R4R, showing the potential of BEV perception in VLN.

VLN-CE is a recently released embodied task, where AI agents need to navigate a freely traversable environment to reach a distant target location, given language instructions. It poses great challenges due to the huge space of possible strategies. Driven by the belief that the ability to anticipate the consequences of future actions is crucial for the emergence of intelligent and interpretable planning behavior, we propose Dreamwalker — a world model based VLN-CE agent. The world model is built to summarize the visual, topological, and dynamic properties of the complicated continuous environment into a discrete, structured, and compact representation. Dreamwalker can simulate and evaluate possible plans entirely in such internal abstract world, before executing costly actions. As opposed to existing model-free VLN-CE agents simply making greedy decisions in the real world, which easily results in shortsighted behaviors, Dreamwalker is able to make strategic planning through large amounts of "mental experiments." Moreover, the imagined future scenarios reflect our agent’s intention, making its decision-making process more transparent. Extensive experiments and ablation studies on VLN-CE dataset confirm the effectiveness of the proposed approach and outline fruitful directions for future work.

Location determination finds wide applications in daily life. Instead of existing efforts devoted to localizing tourist photos captured by perspective cameras, in this article, we focus on devising person positioning solutions using overhead fisheye cameras. Such solutions are advantageous in large field of view (FOV), low cost, anti-occlusion, and unaggressive work mode (without the necessity of cameras carried by persons). However, related studies are quite scarce, due to the paucity of data. To stimulate research in this exciting area, we present LOAF, the first large-scale overhead fisheye dataset for person detection and localization. LOAF is built with many essential features, e.g., i) the data cover abundant diversities in scenes, human pose, density, and location; ii) it contains currently the largest number of annotated pedestrian, i.e., 457K bounding boxes with groundtruth location information; iii) the body-boxes are labeled as radius-aligned so as to fully address the positioning challenge. To approach localization, we build a fisheye person detection network, which exploits the fisheye distortions by a rotation-equivariant training strategy and predict radius-aligned human boxes end-to-end. Then, the actual locations of the detected persons are calculated by a numerical solution on the fisheye model and camera altitude data. Extensive experiments on LOAF validate the superiority of our fisheye detector w.r.t. previous methods, and show that our whole fisheye positioning solution is able to locate all persons in FOV with an accuracy of0.5 m, within 0.1 s.

We present CLUSTSEG, a general, transformer-based framework that tackles different image segmentation tasks ($i.e.,$ superpixel, semantic, instance, and panoptic) through a unified, neural clustering scheme. Regarding queries as cluster centers, CLUSTSEG is innovative in two aspects: 1) cluster centers are initialized in heterogeneous ways so as to pointedly address task-specific demands ($e.g.,$ instance- or category-level distinctiveness), yet without modifying the architecture; and 2) pixel-cluster assignment, formalized in a cross-attention fashion, is alternated with cluster center update, yet without learning additional parameters. These innovations closely link CLUSTSEG to EM clustering and make it a transparent and powerful framework that yields superior results across the above segmentation tasks.

The interaction decoder utilized in prevalent Transformer-based HOI detectors typically accepts pre-composed human-object pairs as inputs. Though achieving remarkable performance, such a paradigm lacks feasibility and cannot explore novel combinations over entities during decoding. We present LogicHOI, a new HOI detector that leverages neural-logic reasoning and Transformer to infer feasible interactions between. entities. Specifically, we modify. self-attention mechanism in the vanilla Transformer, enabling it to reason over the ⟨ human, action, object ⟩ triplet and constitute novel interactions. Meanwhile, such a reasoning process is guided by two crucial properties for understanding HOI: affordances (the potential actions an object can facilitate) and proxemics (the spatial relations between humans and objects). We formulate these two properties in first-order logic and ground them into continuous space to constrain the learning process of our approach, leading to improved performance and zero-shot generalization capabilities. We evaluate L OGIC HOI on V-COCO and HICO-DET under both normal and zero-shot setups, achieving significant improvements over existing methods.

This paper presents ClusterFormer, a universal vision model that is based on the Clustering paradigm with TransFormer. It comprises two novel designs: 1) recurrent cross-attention clustering, which reformulates the cross-attention mechanism in Transformer and enables recursive updates of cluster centers to facilitate strong representation learning; and 2) feature dispatching, which uses the updated cluster centers to redistribute image features through similarity-based metrics, resulting in a transparent pipeline. This elegant design streamlines an explainable and transferable workflow, capable of tackling heterogeneous vision tasks (i.e., image classification, object detection, and image segmentation) with varying levels of clustering granularity (i.e., image-, box-, and pixel-level). Empirical results demonstrate that ClusterFormer outperforms various well-known specialized architectures, achieving 83.41% top-1 acc. over ImageNet-1K for image classification, 54.2% and 47.0% mAP over MS COCO for object detection and instance segmentation, 52.4% mIoU over ADE20K for semantic segmentation, and 55.8% PQ over COCO Panoptic for panoptic segmentation. This work aims to initiate a paradigm shift in universal visual understanding and to benefit the broader field.

The past decade has witnessed remarkable achievements in computer vision, owing to the fast development of deep learning. With the advancement of computing power and deep learning algorithms, we can process and apply millions or even hundreds of millions of large-scale data to train robust and advanced deep learning models. In spite of the impressive success, current deep learning methods tend to rely on massive annotated training data and lack the capability of learning from limited exemplars. However, constructing a million-scale annotated dataset like ImageNet is time-consuming, labour-intensive and even infeasible in many applications. In certain fields, very limited annotated examples can be gathered due to various reasons such as privacy or ethical issues. Consequently, one of the pressing challenges in computer vision is to develop approaches that are capable of learning from limited annotated data. The purpose of this Special Issue is to collect high-quality articles on learning from limited annotations for computer vision tasks (e.g. image classification, object detection, semantic segmentation, instance segmentation and many others), publish new ideas, theories, solutions and insights on this topic and showcase their applications. In this Special Issue we received 29 papers, all of which underwent peer review. Of the 29 originally submitted papers, 9 have been accepted. The nine accepted papers can be clustered into two main categories: theoretical and applications. The papers that fall into the first category are by Liu et al., Li et al. and He et al. The second category of papers offers a direct solution to various computer vision tasks. These papers are by Ma et al., Wu et al., Rao et al., Sun et al., Hou et al. and Gong et al. A brief presentation of each of the papers in this Special Issue follows. Liu et al. present a Gaussianisation prototypical classifier (GPC) for few-shot classification which mainly focuses on solving the issue of prototype bias. GPC consists of handling the features with the Gaussianisation operation and estimating a reliable prototype using the maximum a posteriori method using base class features as prior information. The proposed method is simple yet effective, which does not use any extra labelled data or knowledge. Moreover, it's also a one-step prototype rectification method, which does not resort any complex continuous optimisation. The ablation study shows that GPC can benefit from features pretrained only with CE loss or jointly trained with self-supervised loss. The results demonstrate that the proposed method outperforms related work and other state-of-the-art methods. Li et al. present a novel hyperspectral unmixing method named ‘Global centralised and Structured discriminative Nonnegative Matrix Factorisation (GSNMF)’. The proposed GSNMF offers several distinct advantages over the traditional unmixing techniques. Constructed on the foundation of the manifold regularisation techniques, GSNMF captures the intrinsic structural information by using the local affinity and distant repulsion constraints concurrently. With the structured discriminative information, local affinity constraint ensures that similar elements share similar estimated abundances, while the distant repulsion constraint ensures that dissimilar elements have different abundances. All experiments and analyses have demonstrated that the proposed GSNMF exhibits a remarkable performance compared to the other methods. He et al. present a taxonomy of existing algorithms in the task of makeup transfer. Evaluation methods are proposed, existing methods are analysed and existing datasets are reviewed. Finally the current problems in the field of makeup transfer are discussed, and the trend of future research is analysed. Ma et al. present a dense transformer framework for person re-identification tasks. This paper introduces densely connected class tokens to connect any two layers implicitly. The framework, Denseformer, outperforms other vision transformer models on four widely used benchmarks, namely Market-1501, DukeMTMC-reID, MSMT17 and Occluded-Duke datasets with only a small amount of extra calculation cost. According to the visualisation results, the proposed Denseformer pays more attention to the main parts of human bodies, obtaining discriminative global features. The Denseformer is a general improvement on ViT and works well on other tasks that use ViT as a backbone according to the promising results. Wu et al. present a new homology-continuous-based makeup transformation method, which can be roughly divided into two network branches: the age compensation branch and the makeup transformation branch. Specifically, in the age compensation branch, based on the same source continuity the authors designed a new encoding module which can map the face vector into the corresponding high-dimensional vector space and realise the compensation for age by adjusting the vector direction. In the makeup transformation branch, this work designed a multi-style encoder to handle different types of makeup, such as Chinese Japanese Korean makeup etc. In addition, the proposed network structure is a two-pass encoder-decoder architecture which has good parallelism and can achieve better results with training and inference on GPU. Rao et al. present a novel end-to-end architecture for point completion by using a stack-style folding network called the SSFN. Due to the fact that the output shape code cannot completely represent semantically, they propose a Stack-Style Folding module that transforms the bottleneck output into the style code analogous to StyleGAN. Experiments on ShapeNet and KITTI datasets indicate that the proposed SSFN architecture achieves a decent visual quality and metric performance. Sun et al. present a method for a zero-shot temporal event localisation (ZSTEL) that leverage large-scale video and language models, for example, CLIP. They solve the two key problems for ZSTEL: (1) how to find the relevant region where the event is likely to occur, (2) how to determine event duration after the relevant region is found. They propose the query-guided optimisation for local frame relevance. Relying on the query-to-frame relationship, this method can find the most relevant local frame region where the event is most likely to occur, guided by a constructed objective. The experimental results on the two standard benchmark datasets, Charades-STA and ActivityCaptions have shown the effectiveness of the proposed approach. Hou et al. present a cutting-edge few-shot detection method for logo images. To avoid the misclassification between the base and novel classes, they add an extra classification head. They also apply the convolutional layer into regression heads to improve the accuracy of location by using the limited training data. Considering the characteristics of logo images, they add balanced feature pyramid with Deformable RoI Pooling and unfreeze region proposal network in the fine-tuning stage. The extensive comparative experimentation and ablation studies illustrate the advantage of the proposed method and the effectiveness of every component in the model. Gong et al. present a method for object detection with a long-tail distribution that includes a dual-balanced network and balanced classification loss. This work investigates how the long-tailed distribution impacts the sub-networks in the general two-stage object detection framework Faster-RCNN and finds that unbalanced proposal sampling and unbalanced classification logic deteriorate the performance of the model in terms of AP. They propose the balanced region proposal network and balanced the classification network to address the above issues. Experiments on the LVIS-v0.5 dataset demonstrate that the framework improves the performance of AP without sacrificing too much from the performance of head categories in long-tail distribution. All of the papers selected for this Special Issue show that the field of learning from limited annotations for computer vision tasks is steadily moving forward. The possibility of a weakly supervised learning paradigm will remain a source of inspiration for new techniques in the years to come. Firstly, we wish to express our thanks to Ph.D. students at Nanjing University of Science and Technology for their continuous assistance throughout this process. Also, we wish to express our gratitude to all the contributors who submitted novel scientific results in this special issue and to the anonymous reviewers, whose expert work allowed the realisation of this endeavor. We aspire that this effort should contribute to the further development of DL and increase the concern of the scientific and technological community in the respective area. Last, we should not omit to express our appreciation to the journal's Editors-in-Chief and the Editorial Office for their support throughout this venture. Data sharing is not applicable to this article as no new data were created or analysed in this study. Yazhou Yao is a professor at the School of Computer Science and Engineering and Nanjing University of Science and Technology. With the support of the China Scholarship Council, he received his Ph.D. degree in Computer Science, University of Technology Sydney, Australia at 2018. From July 2018 to July 2019, he worked as a Research Scientist at the Inception Institute of Artificial Intelligence, Abu Dhabi, UAE. His research interests include multimedia processing and machine learning. Wenguan Wang is currently a ZJU100 Young Professor at Zhejiang University. He received his Ph.D. degree from Beijing Institute of Technology in 2018. From 2016 to 2018, he was a joint Ph.D. candidate at the University of California, Los Angeles. From 2018 to 2019, he was a senior scientist at the Inception Institute of Artificial Intelligence, UAE. From 2020 to 2022, he worked as a postdoc researcher at ETH Zurich, Switzerland. After that, he worked as a lecturer and ARC DECRA Fellow at the University of Technology Sydney. His current research interests include computer vision, image processing and deep learning. Qiang Wu received the BEng and MEng degrees in electronic engineering from the Harbin Institute of Technology, Harbin, China, in 1996 and 1998, respectively, and the Ph.D. degree in computing science from the University of Technology Sydney, Sydney, Australia, in 2004. He is currently an Associate Professor and a Core Member of the Global Big Data Technologies Centre, University of Technology Sydney. He has published more than 70 refereed papers, including those published in prestigious journals and top international conferences. His major research interests include computer vision, image processing, pattern recognition, machine learning and multimedia processing. He has served as the chair and/or a Programme Committee Member for a number of international conferences. Dongfang Liu is an Assistant Professor in the Department of Computer Engineering at the Rochester Institute of Technology (RIT). He earned his Ph.D. degree from Purdue University. Dr. Dongfang Liu's research focus on embodied AI and creates general AI solutions to address significant societal challenges. His ongoing work consists of: (1) developing attention-guided perception models that behave like a human's perpetual capacity; and (2) developing structured and human-centred recognition systems that comprehend the surrounding visual world. His publication portfolio includes papers from major conferences in the artificial intelligence and robotics fields, such as CVPR, ECCV, ICCV, ICLR, NIPS, ICML, AAAI, IJCAI, ACL, EMNLP, WWW, WACV, IROS etc. He currently serves on the senior programme committee for AAAI and IJCAI and as an associate editor for IEEE Transactions on Circuits and Systems for Video Technology (TCSVT). Jin Zheng received the BS and MS degrees from Liaoning Technical University, in 2001 and 2004, respectively, and the Ph.D. degree from the School of Computer Science and Engineering, Beihang University, in 2009. She joined the School of Computer Science and Engineering, Beihang University, in 2009. In 2014, she visited Harvard University, MA, USA, as a Visiting Scholar for 1 year. Her current research interests include object detection, tracking and recognition, among other similar interests.

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.

We explore the task of language-guided video segmentation (LVS). Previous algorithms mostly adopt 3D CNNs to learn video representation, struggling to capture long-term context and easily suffering from visual-linguistic misalignment. In light of this, we present Locater (local-global context aware Transformer), which augments the Transformer architecture with a finite memory so as to query the entire video with the language expression in an efficient manner. The memory is designed to involve two components - one for persistently preserving global video content, and one for dynamically gathering local temporal context and segmentation history. Based on the memorized local-global context and the particular content of each frame, Locater holistically and flexibly comprehends the expression as an adaptive query vector for each frame. The vector is used to query the corresponding frame for mask generation. The memory also allows Locater to process videos with linear time complexity and constant size memory, while Transformer-style self-attention computation scales quadratically with sequence length. To thoroughly examine the visual grounding capability of LVS models, we contribute a new LVS dataset, A2D-S +, which is built upon A2D-S dataset but poses increased challenges in disambiguating among similar objects. Experiments on three LVS datasets and our A2D-S + show that Locater outperforms previous state-of-the-arts. Further, we won the 1st place in the Referring Video Object Segmentation Track of the 3rd Large-scale Video Object Segmentation Challenge, where Locater served as the foundation for the winning solution.

Video segmentation-partitioning video frames into multiple segments or objects-plays a critical role in a broad range of practical applications, from enhancing visual effects in movie, to understanding scenes in autonomous driving, to creating virtual background in video conferencing. Recently, with the renaissance of connectionism in computer vision, there has been an influx of deep learning based approaches for video segmentation that have delivered compelling performance. In this survey, we comprehensively review two basic lines of research - generic object segmentation (of unknown categories) in videos, and video semantic segmentation - by introducing their respective task settings, background concepts, perceived need, development history, and main challenges. We also offer a detailed overview of representative literature on both methods and datasets. We further benchmark the reviewed methods on several well-known datasets. Finally, we point out open issues in this field, and suggest opportunities for further research. We also provide a public website to continuously track developments in this fast advancing field: https://github.com/tfzhou/VS-Survey.

In this work, we study the challenging problem of instance-aware human body part parsing. We introduce a new bottom-up regime which achieves the task through learning category-level human semantic segmentation as well as multi-person pose estimation in a joint and end-to-end manner. The output 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, we develop two novel algorithms based on projected gradient descent and unbalanced optimal transport, respectively, to solve the matching problem differentiablly. These algorithms make our method end-to-end trainable and allow back-propagating the grouping error to directly supervise multi-granularity human representation learning. This is significantly distinguished from current bottom-up human parsers or pose estimators which require sophisticated post-processing or heuristic greedy algorithms. Extensive experiments on three instance-aware human parsing datasets (i.e., MHP-v2, DensePose-COCO, PASCAL-Person-Part) demonstrate that our approach outperforms most existing human parsers with much more efficient inference. Our code is available at https://github.com/tfzhou/MG-HumanParsing.

Humans are able to recognize structured relations in observation, allowing us to decompose complex scenes into simpler parts and abstract the visual world in multiple levels. However, such hierarchical reasoning ability of human perception remains largely unexplored in current literature of semantic segmentation. Existing work is often aware of flatten labels and predicts target classes exclusively for each pixel. In this paper, we instead address hierarchical semantic segmentation (HSS), which aims at structured, pixel-wise description of visual observation in terms of a class hierarchy. We devise HSSN, a general HSS framework that tackles two critical issues in this task: i) how to efficiently adapt existing hierarchy-agnostic segmentation networks to the HSS setting, and ii) how to leverage the hierarchy information to regularize HSS network learning. To address i), HSSN directly casts HSS as a pixel-wise multi-label classification task, only bringing minimal architecture change to current segmentation models. To solve ii), HSSN first explores inherent properties of the hierarchy as a training objective, which enforces segmentation predictions to obey the hierarchy structure. Further, with hierarchy-induced margin constraints, HSSNreshapes the pixel embedding space, so as to generate well-structured pixel representations and improve segmentation eventually. We conduct experiments on four semantic segmentation datasets (i.e., Mapillary Vistas 2.0, City-scapes, LIP, and PASCAL-Person-Part), with different class hierarchies, segmentation network architectures and backbones, showing the generalization and superiority of HSSN.

Our target is to learn visual correspondence from unlabeled videos. We develop Liir, a locality-aware inter-and intra-video reconstruction method that fills in three missing pieces, i.e., instance discrimination, location awareness, and spatial compactness, of self-supervised correspondence learning puzzle. First, instead of most existing efforts focusing on intra-video self-supervision only, we exploit cross-video affinities as extra negative samples within a unified, inter-and intra-video reconstruction scheme. This enables instance discriminative representation learning by contrasting desired intra-video pixel association against negative inter-video correspondence. Second, we merge position information into correspondence matching, and design a position shifting strategy to remove the side-effect of position encoding during inter-video affinity computation, making our Liir location-sensitive. Third, to make full use of the spatial continuity nature of video data, we impose a compactness-based constraint on correspondence matching, yielding more sparse and reliable solutions. The learned representation surpasses self-supervised state-of-the-arts on label propagation tasks including objects, semantic parts, and keypoints.

Abductive reasoning seeks the likeliest possible explanation for partial observations. Although abduction is frequently employed in human daily reasoning, it is rarely explored in computer vision literature. In this paper, we propose a new task and dataset, Visual Abductive Reasoning (VAR), for examining abductive reasoning ability of machine intelligence in everyday visual situations. Given an incomplete set of visual events, AI systems are required to not only describe what is observed, but also infer the hypothesis that can best explain the visual premise. Based on our large-scale VAR dataset, we devise a strong baseline model, REASONER (causal-and-cascaded reasoning Transformer). First, to capture the causal structure of the observations, a contextualized directional position embedding strategy is adopted in the encoder, that yields discriminative represen-tations for the premise and hypothesis. Then, multiple de-coders are cascaded to generate and progressively refine the premise and hypothesis sentences. The prediction scores of the sentences are used to guide cross-sentence information flow in the cascaded reasoning procedure. Our VAR bench-marking results show that REASONER surpasses many famous video-language models, while still being far behind human performance. This work is expected to foster future efforts in the reasoning-beyond-observation paradigm.

Since the rise of vision-language navigation (VLN), great progress has been made in instruction following - building a follower to navigate environments under the guidance of instructions. However, far less attention has been paid to the inverse task: instruction generation - learning a speaker to generate grounded descriptions for navigation routes. Existing VLN methods train a speaker independently and often treat it as a data augmentation tool to strengthen the follower, while ignoring rich cross-task relations. Here we describe an approach that learns the two tasks simultaneously and exploits their intrinsic correlations to boost the training of each: the follower judges whether the speaker-created instruction explains the original navigation route correctly, and vice versa. Without the need of aligned instruction-path pairs, such cycle-consistent learning scheme is complementary to task-specific training targets defined on labeled data, and can also be applied over unlabeled paths (sampled without paired instructions). Another agent, called creator is added to generate counterfactual environments. It greatly changes current scenes yet leaves novel items - which are vital for the execution of original instructions - unchanged. Thus more informative training scenes are synthesized and the three agents compose a powerful VLN learning system. Extensive experiments on a standard benchmark show that our approach improves the performance of various follower models and produces accurate navigation instructions.

Prevalent semantic segmentation solutions, despite their different network designs (FCN based or attention based) and mask decoding strategies (parametric softmax based or pixel-query based), can be placed in one category, by considering the softmax weights or query vectors as learnable class prototypes. In light of this prototype view, this study uncovers several limitations of such parametric segmentation regime, and proposes a nonparametric alternative based on non-learnable prototypes. Instead of prior methods learning a single weight/query vector for each class in a fully parametric manner, our model represents each class as a set of non-learnable prototypes, relying solely on the mean fea-tures of several training pixels within that class. The dense prediction is thus achieved by nonparametric nearest prototype retrieving. This allows our model to directly shape the pixel embedding space, by optimizing the arrangement between embedded pixels and anchored prototypes. It is able to handle arbitrary number of classes with a constant amount of learnable parameters. We empirically show that, with FCN based and attention based segmentation models (i.e., HR-Net, Swin, SegFormer) and backbones (i.e., ResNet, HRNet, Swin, MiT), our nonparametric framework yields compel-ling results over several datasets (i.e., ADE20K, Cityscapes, COCO-Stuff), and performs well in the large-vocabulary situation. We expect this work will provoke a rethink of the current de facto semantic segmentation model design.

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.

Prevalent semantic segmentation solutions are, in essence, a dense discriminative classifier of p(class|pixel feature). Though straightforward, this de facto paradigm neglects the underlying data distribution p(pixel feature|class), and struggles to identify out-of-distribution data. Going beyond this, we propose GMMSeg, a new family of segmentation models that rely on a dense generative classifier for the joint distribution p(pixel feature,class). For each class, GMMSeg builds Gaussian Mixture Models (GMMs) via Expectation-Maximization (EM), so as to capture class-conditional densities. Meanwhile, the deep dense representation is end-to-end trained in a discriminative manner, i.e., maximizing p(class|pixel feature). This endows GMMSeg with the strengths of both generative and discriminative models. With a variety of segmentation architectures and backbones, GMMSeg outperforms the discriminative counterparts on three closed-set datasets. More impressively, without any modification, GMMSeg even performs well on open-world datasets. We believe this work brings fundamental insights into the related fields.

With the emergence of varied visual navigation tasks (e.g., image-/object-/audio-goal and vision-language navigation) that specify the target in different ways, the community has made appealing advances in training specialized agents capable of handling individual navigation tasks well. Given plenty of embodied navigation tasks and task-specific solutions, we address a more fundamental question: can we learn a single powerful agent that masters not one but multiple navigation tasks concurrently? First, we propose VXN, a large-scale 3D dataset that instantiates~four classic navigation tasks in standardized, continuous, and audiovisual-rich environments. Second, we propose Vienna, a versatile embodied navigation agent that simultaneously learns to perform the four navigation tasks with one model. Building upon a full-attentive architecture, Vienna formulates various navigation tasks as a unified, parse-and-query procedure: the target description, augmented with four task embeddings, is comprehensively interpreted into a set of diversified goal vectors, which are refined as the navigation progresses, and used as queries to retrieve supportive context from episodic history for decision making. This enables the reuse of knowledge across navigation tasks with varying input domains/modalities. We empirically demonstrate that, compared with learning each visual navigation task individually, our multitask agent achieves comparable or even better performance with reduced complexity.

Prevalent state-of-the-art instance segmentation methods fall into a query-based scheme, in which instance masks are derived by querying the image feature using a set of instance-aware embeddings. In this work, we devise a new training framework that boosts query-based models through discriminative query embedding learning. It explores two essential properties, namely dataset-level uniqueness and transformation equivariance, of the relation between queries and instances. First, our algorithm uses the queries to retrieve the corresponding instances from the whole training dataset, instead of only searching within individual scenes. As querying instances across scenes is more challenging, the segmenters are forced to learn more discriminative queries for effective instance separation. Second, our algorithm encourages both image (instance) representations and queries to be equivariant against geometric transformations, leading to more robust, instance-query matching. On top of four famous, query-based models (i.e., CondInst, SOLOv2, SOTR, and Mask2Former), our training algorithm provides significant performance gains (e.g., +1.6 – 3.2 AP) on COCO dataset. In addition, our algorithm promotes the performance of SOLOv2 by 2.7 AP, on LVISv1 dataset.

In this article, we model a set of pixelwise object segmentation tasks - automatic video segmentation (AVS), image co-segmentation (ICS) and few-shot semantic segmentation (FSS) - in a unified view of segmenting objects from relational visual data. To this end, we propose an attentive graph neural network (AGNN) that addresses these tasks in a holistic fashion, by formulating them as a process of iterative information fusion over data graphs. It builds a fully-connected graph to efficiently represent visual data as nodes and relations between data instances as edges. The underlying relations are described by a differentiable attention mechanism, which thoroughly examines fine-grained semantic similarities between all the possible location pairs in two data instances. Through parametric message passing, AGNN is able to capture knowledge from the relational visual data, enabling more accurate object discovery and segmentation. Experiments show that AGNN can automatically highlight primary foreground objects from video sequences (i.e., automatic video segmentation), and extract common objects from noisy collections of semantically related images (i.e., image co-segmentation). AGNN can even generalize segment new categories with little annotated data (i.e., few-shot semantic segmentation). Taken together, our results demonstrate that AGNN provides a powerful tool that is applicable to a wide range of pixel-wise object pattern understanding tasks with relational visual data. Our algorithm implementations have been made publicly available at https://github.com/carrierlxk/AGNN.

We introduce a novel network, called CO-attention siamese network (COSNet), to address the zero-shot video object segmentation task in a holistic fashion. We exploit the inherent correlation among video frames and incorporate a global co-attention mechanism to further improve the state-of-the-art deep learning based solutions that primarily focus on learning discriminative foreground representations over appearance and motion in short-term temporal segments. The co-attention layers in COSNet provide efficient and competent stages for capturing global correlations and scene context by jointly computing and appending co-attention responses into a joint feature space. COSNet is a unified and end-to-end trainable framework where different co-attention variants can be derived for capturing diverse properties of the learned joint feature space. We train COSNet with pairs (or groups) of video frames, and this naturally augments training data and allows increased learning capacity. During the segmentation stage, the co-attention model encodes useful information by processing multiple reference frames together, which is leveraged to infer the frequently reappearing and salient foreground objects better. Our extensive experiments over three large benchmarks demonstrate that COSNet outperforms the current alternatives by a large margin. Our implementations are available at https://github.com/carrierlxk/COSNet.

It is quite laborious and costly to manually label LiDAR point cloud data for training high-quality 3D object detectors. This work proposes a weakly supervised framework which allows learning 3D detection from a few weakly annotated examples. This is achieved by a two-stage architecture design. Stage-1 learns to generate cylindrical object proposals under inaccurate and inexact supervision, obtained by our proposed BEV center-click annotation strategy, where only the horizontal object centers are click-annotated in bird's view scenes. Stage-2 learns to predict cuboids and confidence scores in a coarse-to-fine, cascade manner, under incomplete supervision, i.e., only a small portion of object cuboids are precisely annotated. With KITTI dataset, using only 500 weakly annotated scenes and 534 precisely labeled vehicle instances, our method achieves 86-97 percent the performance of current top-leading, fully supervised detectors (which require 3,712 exhaustively annotated scenes with 15,654 instances). More importantly, with our elaborately designed network architecture, our trained model can be applied as a 3D object annotator, supporting both automatic and active (human-in-the-loop) working modes. The annotations generated by our model can be used to train 3D object detectors, achieving over 95 percent of their original performance (with manually labeled training data). Our experiments also show our model's potential in boosting performance when given more training data. The above designs make our approach highly practical and open-up opportunities for learning 3D detection at reduced annotation cost.

As an essential problem in computer vision, salient object detection (SOD) has attracted an increasing amount of research attention over the years. Recent advances in SOD are predominantly led by deep learning-based solutions (named deep SOD). To enable in-depth understanding of deep SOD, in this paper, we provide a comprehensive survey covering various aspects, ranging from algorithm taxonomy to unsolved issues. In particular, we first review deep SOD algorithms from different perspectives, including network architecture, level of supervision, learning paradigm, and object-/instance-level detection. Following that, we summarize and analyze existing SOD datasets and evaluation metrics. Then, we benchmark a large group of representative SOD models, and provide detailed analyses of the comparison results. Moreover, we study the performance of SOD algorithms under different attribute settings, which has not been thoroughly explored previously, by constructing a novel SOD dataset with rich attribute annotations covering various salient object types, challenging factors, and scene categories. We further analyze, for the first time in the field, the robustness of SOD models to random input perturbations and adversarial attacks. We also look into the generalization and difficulty of existing SOD datasets. Finally, we discuss several open issues of SOD and outline future research directions. All the saliency prediction maps, our constructed dataset with annotations, and codes for evaluation are publicly available at https://github.com/wenguanwang/SODsurvey.

Modeling the human structure is central for human parsing that extracts pixel-wise semantic information from images. We start with analyzing three types of inference processes over the hierarchical structure of human bodies: direct inference (directly predicting human semantic parts using image information), bottom-up inference (assembling knowledge from constituent parts), and top-down inference (leveraging context from parent nodes). We then formulate the problem as a compositional neural information fusion (CNIF) framework, which assembles the information from the three inference processes in a conditional manner, i.e., considering the confidence of the sources. Based on CNIF, we further present a part-relation-aware human parser (PRHP), which precisely describes three kinds of human part relations, i.e., decomposition, composition, and dependency, by three distinct relation networks. Expressive relation information can be captured by imposing the parameters in the relation networks to satisfy specific geometric characteristics of different relations. By assimilating generic message-passing networks with their edge-typed, convolutional counterparts, PRHP performs iterative reasoning over the human body hierarchy. With these efforts, PRHP provides a more general and powerful form of CNIF, and lays the foundation for more sophisticated and flexible human relation patterns of reasoning. Experiments on five datasets demonstrate that our two human parsers outperform the state-of-the-arts in all cases.

3D data that contains rich geometry information of objects and scenes is valuable for understanding 3D physical world. With the recent emergence of large-scale 3D datasets, it becomes increasingly crucial to have a powerful 3D generative model for 3D shape synthesis and analysis. This paper proposes a deep 3D energy-based model to represent volumetric shapes. The maximum likelihood training of the model follows an "analysis by synthesis" scheme. The benefits of the proposed model are six-fold: first, unlike GANs and VAEs, the model training does not rely on any auxiliary models; second, the model can synthesize realistic 3D shapes by Markov chain Monte Carlo (MCMC); third, the conditional model can be applied to 3D object recovery and super resolution; fourth, the model can serve as a building block in a multi-grid modeling and sampling framework for high resolution 3D shape synthesis; fifth, the model can be used to train a 3D generator via MCMC teaching; sixth, the unsupervisedly trained model provides a powerful feature extractor for 3D data, which is useful for 3D object classification. Experiments demonstrate that the proposed model can generate high-quality 3D shape patterns and can be useful for a wide variety of 3D shape analysis.

In this paper, we propose a pose grammar to tackle the problem of 3D human pose estimation from a monocular RGB image. Our model takes estimated 2D pose as the input and learns a generalized 2D-3D mapping function to leverage into 3D pose. The proposed model consists of a base network which efficiently captures pose-aligned features and a hierarchy of Bi-directional RNNs (BRNNs) on the top to explicitly incorporate a set of knowledge regarding human body configuration (i.e., kinematics, symmetry, motor coordination). The proposed model thus enforces high-level constraints over human poses. In learning, we develop a data augmentation algorithm to further improve model robustness against appearance variations and cross-view generalization ability. We validate our method on public 3D human pose benchmarks and propose a new evaluation protocol working on cross-view setting to verify the generalization capability of different methods. We empirically observe that most state-of-the-art methods encounter difficulty under such setting while our method can well handle such challenges.

This paper addresses the task of detecting and recognizing human-object interactions (HOI) in images. Considering the intrinsic complexity and structural nature of the task, we introduce a cascaded parsing network (CP-HOI) for a multi-stage, structured HOI understanding. At each cascade stage, an instance detection module progressively refines HOI proposals and feeds them into a structured interaction reasoning module. Each of the two modules is also connected to its predecessor in the previous stage, enabling efficient cross-stage information propagation. The structured interaction reasoning module is built upon a graph parsing neural network (GPNN), which efficiently models potential HOI structures as graphs and mines rich context for comprehensive relation understanding. In particular, GPNN infers a parse graph that i) interprets meaningful HOI structures by a learnable adjacency matrix, and ii) predicts action (edge) labels. Within an end-to-end, message-passing framework, GPNN blends learning and inference, iteratively parsing HOI structures and reasoning HOI representations (i.e., instance and relation features). Further beyond relation detection at a bounding-box level, we make our framework flexible to perform fine-grained pixel-wise relation segmentation; this provides a new glimpse into better relation modeling. A preliminary version of our CP-HOI model reached 1stplace in the ICCV2019 Person in Context Challenge, on both relation detection and segmentation. In addition, our CP-HOI shows promising results on two popular HOI recognition benchmarks,i.e., V-COCO and HICO-DET.

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.

Recently, numerous algorithms have been developed to tackle the problem of vision-language navigation (VLN), i.e., entailing an agent to navigate 3D environments through following linguistic instructions. However, current VLN agents simply store their past experiences/observations as latent states in recurrent networks, failing to capture environment layouts and make long-term planning. To address these limitations, we propose a crucial architecture, called Structured Scene Memory (SSM). It is compartmentalized enough to accurately memorize the percepts during navigation. It also serves as a structured scene representation, which captures and disentangles visual and geometric cues in the environment. SSM has a collect-read controller that adaptively collects information for supporting current decision making and mimics iterative algorithms for long-range reasoning. As SSM provides a complete action space, i.e., all the navigable places on the map, a frontier-exploration based navigation decision making strategy is introduced to enable efficient and global planning. Experiment results on two VLN datasets (i.e., R2R and R4R) show that our method achieves state-of-the-art performance on several metrics.

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.

On existing public benchmarks, face forgery detection techniques have achieved great success. However, when used in multi-person videos, which often contain many people active in the scene with only a small subset having been manipulated, their performance remains far from being satisfactory. To take face forgery detection to a new level, we construct a novel large-scale dataset, called FFIW10K, which comprises 10,000 high-quality forgery videos, with an average of three human faces in each frame. The manipulation procedure is fully automatic, controlled by a domain-adversarial quality assessment network, making our dataset highly scalable with low human cost. In addition, we propose a novel algorithm to tackle the task of multi-person face forgery detection. Supervised by only video-level label, the algorithm explores multiple instance learning and learns to automatically attend to tampered faces. Our algorithm outperforms representative approaches for both forgery classification and localization on FFIW10K, and also shows high generalization ability on existing benchmarks. We hope that our dataset and study will help the community to explore this new field in more depth.

Current semantic segmentation methods focus only on mining "local" context, i.e., dependencies between pixels within individual images, by context-aggregation modules (e.g., dilated convolution, neural attention) or structure-aware optimization criteria (e.g., IoU-like loss). However, they ignore "global" context of the training data, i.e., rich semantic relations between pixels across different images. Inspired by recent advance in unsupervised contrastive representation learning, we propose a pixel-wise contrastive algorithm for semantic segmentation in the fully supervised setting. The core idea is to enforce pixel embeddings belonging to a same semantic class to be more similar than embeddings from different classes. It raises a pixel-wise metric learning paradigm for semantic segmentation, by explicitly exploring the structures of labeled pixels, which were rarely explored before. Our method can be effortlessly incorporated into existing segmentation frameworks without extra overhead during testing. We experimentally show that, with famous segmentation models (i.e., DeepLabV3, HRNet, OCR) and backbones (i.e., ResNet, HRNet), our method brings performance improvements across diverse datasets (i.e., Cityscapes, PASCAL-Context, COCO-Stuff, CamVid). We expect this work will encourage our community to rethink the current de facto training paradigm in semantic segmentation.

Hyperparameters are numerical pre-sets whose values are assigned prior to the commencement of a learning process. Selecting appropriate hyperparameters is often critical for achieving satisfactory performance in many vision problems, such as deep learning-based visual object tracking. However, it is often difficult to determine their optimal values, especially if they are specific to each video input. Most hyperparameter optimization algorithms tend to search a generic range and are imposed blindly on all sequences. In this paper, we propose a novel dynamical hyperparameter optimization method that adaptively optimizes hyperparameters for a given sequence using an action-prediction network leveraged on continuous deep Q-learning. Since the observation space for object tracking is significantly more complex than those in traditional control problems, existing continuous deep Q-learning algorithms cannot be directly applied. To overcome this challenge, we introduce an efficient heuristic strategy to handle high dimensional state space, while also accelerating the convergence behavior. The proposed algorithm is applied to improve two representative trackers, a Siamese-based one and a correlation-filter-based one, to evaluate its generalizability. Their superior performances on several popular benchmarks are clearly demonstrated. Our source code is available at https://github.com/shenjianbing/dqltracking.

) with dynamic eye-tracking data in the unsupervised video object segmentation (UVOS) setting. For the first time, we quantitatively verified the high consistency of visual attention behavior among human observers, and found strong correlation between human attention and explicit primary object judgments during dynamic, task-driven viewing. Such novel observations provide an in-depth insight of the underlying rationale behind video object pattens. Inspired by these findings, we decouple UVOS into two sub-tasks: UVOS-driven Dynamic Visual Attention Prediction (DVAP) in spatiotemporal domain, and Attention-Guided Object Segmentation (AGOS) in spatial domain. Our UVOS solution enjoys three major advantages: 1) modular training without using expensive video segmentation annotations, instead, using more affordable dynamic fixation data to train the initial video attention module and using existing fixation-segmentation paired static/image data to train the subsequent segmentation module; 2) comprehensive foreground understanding through multi-source learning; and 3) additional interpretability from the biologically-inspired and assessable attention. Experiments on four popular benchmarks show that, even without using expensive video object mask annotations, our model achieves compelling performance compared with state-of-the-arts and enjoys fast processing speed (10 fps on a single GPU). Our collected eye-tracking data and algorithm implementations have been made publicly available at https://github.com/wenguanwang/AGS.

Predicting where people look in static scenes, a.k.a visual saliency, has received significant research interest recently. However, relatively less effort has been spent in understanding and modeling visual attention over dynamic scenes. This work makes three contributions to video saliency research. First, we introduce a new benchmark, called DHF1K (Dynamic Human Fixation 1K), for predicting fixations during dynamic scene free-viewing, which is a long-time need in this field. DHF1K consists of 1K high-quality elaborately-selected video sequences annotated by 17 observers using an eye tracker device. The videos span a wide range of scenes, motions, object types and backgrounds. Second, we propose a novel video saliency model, called ACLNet (Attentive CNN-LSTM Network), that augments the CNN-LSTM architecture with a supervised attention mechanism to enable fast end-to-end saliency learning. The attention mechanism explicitly encodes static saliency information, thus allowing LSTM to focus on learning a more flexible temporal saliency representation across successive frames. Such a design fully leverages existing large-scale static fixation datasets, avoids overfitting, and significantly improves training efficiency and testing performance. Third, we perform an extensive evaluation of the state-of-the-art saliency models on three datasets : DHF1K, Hollywood-2, and UCF sports. An attribute-based analysis of previous saliency models and cross-dataset generalization are also presented. Experimental results over more than 1.2K testing videos containing 400K frames demonstrate that ACLNet outperforms other contenders and has a fast processing speed (40 fps using a single GPU). Our code and all the results are available at https://github.com/wenguanwang/DHF1K.

We propose a new method for video object segmentation (VOS) that addresses object pattern learning from unlabeled videos, unlike most existing methods which rely heavily on extensive annotated data. We introduce a unified unsupervised/weakly supervised learning framework, called MuG, that comprehensively captures intrinsic properties of VOS at multiple granularities. Our approach can help advance understanding of visual patterns in VOS and significantly reduce annotation burden. With a carefully-designed architecture and strong representation learning ability, our learned model can be applied to diverse VOS settings, including object-level zero-shot VOS, instance-level zero-shot VOS, and one-shot VOS. Experiments demonstrate promising performance in these settings, as well as the potential of MuG in leveraging unlabeled data to further improve the segmentation accuracy.

Human parsing is for pixel-wise human semantic understanding. As human bodies are underlying hierarchically structured, how to model human structures is the central theme in this task. Focusing on this, we seek to simultaneously exploit the representational capacity of deep graph networks and the hierarchical human structures. In particular, we provide following two contributions. First, three kinds of part relations, i.e., decomposition, composition, and dependency, are, for the first time, completely and precisely described by three distinct relation networks. This is in stark contrast to previous parsers, which only focus on a portion of the relations and adopt a type-agnostic relation modeling strategy. More expressive relation information can be captured by explicitly imposing the parameters in the relation networks to satisfy the specific characteristics of different relations. Second, previous parsers largely ignore the need for an approximation algorithm over the loopy human hierarchy, while we instead address an iterative reasoning process, by assimilating generic message-passing networks with their edge-typed, convolutional counterparts. With these efforts, our parser lays the foundation for more sophisticated and flexible human relation patterns of reasoning. Comprehensive experiments on five datasets demonstrate that our parser sets a new state-of-the-art on each.

Current popular online multi-object tracking (MOT) solutions apply single object trackers (SOTs) to capture object motions, while often requiring an extra affinity network to associate objects, especially for the occluded ones. This brings extra computational overhead due to repetitive feature extraction for SOT and affinity computation. Meanwhile, the model size of the sophisticated affinity network is usually non-trivial. In this paper, we propose a novel MOT framework that unifies object motion and affinity model into a single network, named UMA, in order to learn a compact feature that is discriminative for both object motion and affinity measure. In particular, UMA integrates single object tracking and metric learning into a unified triplet network by means of multi-task learning. Such design brings advantages of improved computation efficiency, low memory requirement and simplified training procedure. In addition, we equip our model with a task-specific attention module, which is used to boost task-aware feature learning. The proposed UMA can be easily trained end-to-end, and is elegant - requiring only one training stage. Experimental results show that it achieves promising performance on several MOT Challenge benchmarks.

Rapid progress has been witnessed for human-object interaction (HOI) recognition, but most existing models are confined to single-stage reasoning pipelines. Considering the intrinsic complexity of the task, we introduce a cascade architecture for a multi-stage, coarse-to-fine HOI understanding. At each stage, an instance localization network progressively refines HOI proposals and feeds them into an interaction recognition network. Each of the two networks is also connected to its predecessor at the previous stage, enabling cross-stage information propagation. The interaction recognition network has two crucial parts: a relation ranking module for high-quality HOI proposal selection and a triple-stream classifier for relation prediction. With our carefully-designed human-centric relation features, these two modules work collaboratively towards effective interaction understanding. Further beyond relation detection on a bounding-box level, we make ourframework flexible to perform fine-grained pixel-wise relation segmentation; this provides a new glimpse into better relation modeling. Our approach reached the 1st place in the ICCV2019 Person in Context Challenge, on both relation detection and segmentation tasks. It also shows promising results on V-COCO.

Previous research in visual saliency has been focused on two major types of models namely fixation prediction and salient object detection. The relationship between the two, however, has been less explored. In this work, we propose to employ the former model type to identify salient objects. We build a novel Attentive Saliency Network (ASNet)11.Available at: https://github.com/wenguanwang/ASNet. that learns to detect salient objects from fixations. The fixation map, derived at the upper network layers, mimics human visual attention mechanisms and captures a high-level understanding of the scene from a global view. Salient object detection is then viewed as fine-grained object-level saliency segmentation and is progressively optimized with the guidance of the fixation map in a top-down manner. ASNet is based on a hierarchy of convLSTMs that offers an efficient recurrent mechanism to sequentially refine the saliency features over multiple steps. Several loss functions, derived from existing saliency evaluation metrics, are incorporated to further boost the performance. Extensive experiments on several challenging datasets show that our ASNet outperforms existing methods and is capable of generating accurate segmentation maps with the help of the computed fixation prior. Our work offers a deeper insight into the mechanisms of attention and narrows the gap between salient object detection and fixation prediction.

In this paper, we propose a computationally efficient and consistently accurate spatiotemporal salient object detection method to identify the most noticeable object in a video sequence. Intuitively, the underlying motion in a video is a more stable saliency indicator than the apparent color cues that often contain significant variations and complex structures. Based on this observation, we build an efficient and accurate spatiotemporal saliency detection method that uses motion information as a leverage to locate the most dynamic regions in a video sequence. We first analyze the optical flow field to obtain foreground priors, and then incorporate spatial saliency features such as appearance contrasts and compactness measures, into a multi-cue integration framework to combine various saliency cues and achieve temporal consistency. Rigorous experiments on the challenging SegTrackV1, SegTrackV2, and FBMS datasets demonstrate that our method generates comparable or superior performance to state-of-the-art methods while running almost 100× faster at only 0.08 sec/frame. Promising performance and rapid speed imply that the proposed spatiotemporal saliency method can be easily involved in various vision applications.

This paper proposes a novel residual attentive learning network architecture for predicting dynamic eye-fixation maps. The proposed model emphasizes two essential issues, i.e, effective spatiotemporal feature integration and multi-scale saliency learning. For the first problem, appearance and motion streams are tightly coupled via dense residual cross connections, which integrate appearance information with multi-layer, comprehensive motion features in a residual and dense way. Beyond traditional two-stream models learning appearance and motion features separately, such design allows early, multi-path information exchange between different domains, leading to a unified and powerful spatiotemporal learning architecture. For the second one, we propose a composite attention mechanism that learns multi-scale local attentions and global attention priors end-to-end. It is used for enhancing the fused spatiotemporal features via emphasizing important features in multi-scales. A lightweight convolutional Gated Recurrent Unit (convGRU), which is flexible for small training data situation, is used for long-term temporal characteristics modeling. Extensive experiments over four benchmark datasets clearly demonstrate the advantage of the proposed video saliency model over other competitors and the effectiveness of each component of our network. Our code and all the results will be available at https://github.com/ashleylqx/STRA-Net.

Neural Machine Translation (NMT) optimized by Maximum Likelihood Estimation (MLE) lacks the guarantee of translation adequacy.To alleviate this problem, we propose an NMT approach that heightens the adequacy in machine translation by transferring the semantic knowledge learned from bilingual sentence alignment.Specifically, we first design a discriminator that learns to estimate sentence aligning score over translation candidates, and then the learned semantic knowledge is transfered to the NMT model under an adversarial learning framework.We also propose a gated self-attention based encoder for sentence embedding.Furthermore, an N -pair training loss is introduced in our framework to aid the discriminator in better capturing lexical evidence in translation candidates.Experimental results show that our proposed method outperforms baseline NMT models on Chinese-to-English and English-to-German translation tasks.Further analysis also indicates the detailed semantic knowledge transfered from the discriminator to the NMT model.

The last decade has witnessed a growing interest in video salient object detection (VSOD). However, the research community long-term lacked a well-established VSOD dataset representative of real dynamic scenes with high-quality annotations. To address this issue, we elaborately collected a visual-attention-consistent Densely Annotated VSOD (DAVSOD) dataset, which contains 226 videos with 23,938 frames that cover diverse realistic-scenes, objects, instances and motions. With corresponding real human eye-fixation data, we obtain precise ground-truths. This is the first work that explicitly emphasizes the challenge of saliency shift, i.e., the video salient object(s) may dynamically change. To further contribute the community a complete benchmark, we systematically assess 17 representative VSOD algorithms over seven existing VSOD datasets and our DAVSOD with totally ~84K frames (largest-scale). Utilizing three famous metrics, we then present a comprehensive and insightful performance analysis. Furthermore, we propose a baseline model. It is equipped with a saliency shift- aware convLSTM, which can efficiently capture video saliency dynamics through learning human attention-shift behavior. Extensive experiments open up promising future directions for model development and comparison.

We introduce a novel network, called as CO-attention Siamese Network (COSNet), to address the unsupervised video object segmentation task from a holistic view. We emphasize the importance of inherent correlation among video frames and incorporate a global co-attention mechanism to improve further the state-of-the-art deep learning based solutions that primarily focus on learning discriminative foreground representations over appearance and motion in short-term temporal segments. The co-attention layers in our network provide efficient and competent stages for capturing global correlations and scene context by jointly computing and appending co-attention responses into a joint feature space. We train COSNet with pairs of video frames, which naturally augments training data and allows increased learning capacity. During the segmentation stage, the co-attention model encodes useful information by processing multiple reference frames together, which is leveraged to infer the frequently reappearing and salient foreground objects better. We propose a unified and end-to-end trainable framework where different co-attention variants can be derived for mining the rich context within videos. Our extensive experiments over three large benchmarks manifest that COSNet outperforms the current alternatives by a large margin. We will publicly release our implementation and models.

This paper presents a salient object detection method that integrates both top-down and bottom-up saliency inference in an iterative and cooperative manner. The top-down process is used for coarse-to-fine saliency estimation, where high-level saliency is gradually integrated with finer lower-layer features to obtain a fine-grained result. The bottom-up process infers the high-level, but rough saliency through gradually using upper-layer, semantically-richer features. These two processes are alternatively performed, where the bottom-up process uses the fine-grained saliency obtained from the top-down process to yield enhanced high-level saliency estimate, and the top-down process, in turn, is further benefited from the improved high-level information. The network layers in the bottom-up/top-down processes are equipped with recurrent mechanisms for layer-wise, step-by-step optimization. Thus, saliency information is effectively encouraged to flow in a bottom-up, top-down and intra-layer manner. We show that most other saliency models based on fully convolutional networks (FCNs) are essentially variants of our model. Extensive experiments on several famous benchmarks clearly demonstrate the superior performance, good generalization, and powerful learning ability of our proposed saliency inference framework.

This paper conducts a systematic study on the role of visual attention in Unsupervised Video Object Segmentation (UVOS) tasks. By elaborately annotating three popular video segmentation datasets (DAVIS, Youtube-Objects and SegTrack V2) with dynamic eye-tracking data in the UVOS setting, for the first time, we quantitatively verified the high consistency of visual attention behavior among human observers, and found strong correlation between human attention and explicit primary object judgements during dynamic, task-driven viewing. Such novel observations provide an in-depth insight into the underlying rationale behind UVOS. Inspired by these findings, we decouple UVOS into two sub-tasks: UVOS-driven Dynamic Visual Attention Prediction (DVAP) in spatiotemporal domain, and Attention-Guided Object Segmentation (AGOS) in spatial domain. Our UVOS solution enjoys three major merits: 1) modular training without using expensive video segmentation annotations, instead, using more affordable dynamic fixation data to train the initial video attention module and using existing fixation-segmentation paired static/image data to train the subsequent segmentation module; 2) comprehensive foreground understanding through multi-source learning; and 3) additional interpretability from the biologically-inspired and assessable attention. Experiments on popular benchmarks show that, even without using expensive video object mask annotations, our model achieves compelling performance in comparison with state-of-the-arts.

This paper presents a new method for detecting salient objects in images using convolutional neural networks (CNNs). The proposed network, named PAGE-Net, offers two key contributions. The first is the exploitation of an essential pyramid attention structure for salient object detection. This enables the network to concentrate more on salient regions while considering multi-scale saliency information. Such a stacked attention design provides a powerful tool to efficiently improve the representation ability of the corresponding network layer with an enlarged receptive field. The second contribution lies in the emphasis on the importance of salient edges. Salient edge information offers a strong cue to better segment salient objects and refine object boundaries. To this end, our model is equipped with a salient edge detection module, which is learned for precise salient boundary estimation. This encourages better edge-preserving salient object segmentation. Exhaustive experiments confirm that the proposed pyramid attention and salient edges are effective for salient object detection. We show that our deep saliency model outperforms state-of-the-art approaches for several benchmarks with a fast processing speed (25fps on one GPU).

We propose a novel model to address the task of Visual Dialog which exhibits complex dialog structures. To obtain a reasonable answer based on the current question and the dialog history, the underlying semantic dependencies between dialog entities are essential. In this paper, we explicitly formalize this task as inference in a graphical model with partially observed nodes and unknown graph structures (relations in dialog). The given dialog entities are viewed as the observed nodes. The answer to a given question is represented by a node with missing value. We first introduce an Expectation Maximization algorithm to infer both the underlying dialog structures and the missing node values (desired answers). Based on this, we proceed to propose a differentiable graph neural network (GNN) solution that approximates this process. Experiment results on the VisDial and VisDial-Q datasets show that our model outperforms comparative methods. It is also observed that our method can infer the underlying dialog structure for better dialog reasoning.

This paper addresses a new problem of understanding human gaze communication in social videos from both atomic-level and event-level, which is significant for studying human social interactions. To tackle this novel and challenging problem, we contribute a large-scale video dataset, VACATION, which covers diverse daily social scenes and gaze communication behaviors with complete annotations of objects and human faces, human attention, and communication structures and labels in both atomic-level and event-level. Together with VACATION, we propose a spatio-temporal graph neural network to explicitly represent the diverse gaze interactions in the social scenes and to infer atomic-level gaze communication by message passing. We further propose an event network with encoder-decoder structure to predict the event-level gaze communication. Our experiments demonstrate that the proposed model improves various baselines significantly in predicting the atomic-level and event-level gaze communications.

This paper proposes a human-aware deblurring model that disentangles the motion blur between foreground (FG) humans and background (BG). The proposed model is based on a triple-branch encoder-decoder architecture. The first two branches are learned for sharpening FG humans and BG details, respectively; while the third one produces global, harmonious results by comprehensively fusing multi-scale deblurring information from the two domains. The proposed model is further endowed with a supervised, human-aware attention mechanism in an end-to-end fashion. It learns a soft mask that encodes FG human information and explicitly drives the FG/BG decoder-branches to focus on their specific domains. Above designs lead to a fully differentiable motion deblurring network, which can be trained end-to-end. To further benefit the research towards Human-aware Image Deblurring, we introduce a large-scale dataset, named HIDE, which consists of 8,422 blurry and sharp image pairs with 65,784 densely annotated FG human bounding boxes. HIDE is specifically built to span a broad range of scenes, human object sizes, motion patterns, and background complexities. Extensive experiments on public benchmarks and our dataset demonstrate that our model performs favorably against the state-of-the-art motion deblurring methods, especially in capturing semantic details.

This work proposes a novel attentive graph neural network (AGNN) for zero-shot video object segmentation (ZVOS). The suggested AGNN recasts this task as a process of iterative information fusion over video graphs. Specifically, AGNN builds a fully connected graph to efficiently represent frames as nodes, and relations between arbitrary frame pairs as edges. The underlying pair-wise relations are described by a differentiable attention mechanism. Through parametric message passing, AGNN is able to efficiently capture and mine much richer and higher-order relations between video frames, thus enabling a more complete understanding of video content and more accurate foreground estimation. Experimental results on three video segmentation datasets show that AGNN sets a new state-of-the-art in each case. To further demonstrate the generalizability of our framework, we extend AGNN to an additional task: image object co-segmentation (IOCS). We perform experiments on two famous IOCS datasets and observe again the superiority of our AGNN model. The extensive experiments verify that AGNN is able to learn the underlying semantic/appearance relationships among video frames or related images, and discover the common objects.

This work proposes to combine neural networks with the compositional hierarchy of human bodies for efficient and complete human parsing. We formulate the approach as a neural information fusion framework. Our model assembles the information from three inference processes over the hierarchy: direct inference (directly predicting each part of a human body using image information), bottom-up inference (assembling knowledge from constituent parts), and top-down inference (leveraging context from parent nodes). The bottom-up and top-down inferences explicitly model the compositional and decompositional relations in human bodies, respectively. In addition, the fusion of multi-source information is conditioned on the inputs, i.e., by estimating and considering the confidence of the sources. The whole model is end-to-end differentiable, explicitly modeling information flows and structures. Our approach is extensively evaluated on four popular datasets, outperforming the state-of-the-arts in all cases, with a fast processing speed of 23fps. Our code and results have been released to help ease future research in this direction.

Current CNN-based solutions to salient object detection (SOD) mainly rely on the optimization of cross-entropy loss (CELoss). Then the quality of detected saliency maps is often evaluated in terms of F-measure. In this paper, we investigate an interesting issue: can we consistently use the F-measure formulation in both training and evaluation for SOD? By reformulating the standard F-measure we propose the relaxed F-measure which is differentiable w.r.t the posterior and can be easily appended to the back of CNNs as the loss function. Compared to the conventional cross-entropy loss of which the gradients decrease dramatically in the saturated area, our loss function, named FLoss, holds considerable gradients even when the activation approaches the target. Consequently, the FLoss can continuously force the network to produce polarized activations. Comprehensive benchmarks on several popular datasets show that FLoss outperforms the state-of-the-art with a considerable margin. More specifically, due to the polarized predictions, our method is able to obtain high-quality saliency maps without carefully tuning the optimal threshold, showing significant advantages in real-world applications.

We study the problem of photo cropping, which aims to find a cropping window of an input image to preserve as much as possible its important parts while being aesthetically pleasant. Seeking a deep learning-based solution, we design a neural network that has two branches for attention box prediction (ABP) and aesthetics assessment (AA), respectively. Given the input image, the ABP network predicts an attention bounding box as an initial minimum cropping window, around which a set of cropping candidates are generated with little loss of important information. Then, the AA network is employed to select the final cropping window with the best aesthetic quality among the candidates. The two sub-networks are designed to share the same full-image convolutional feature map, and thus are computationally efficient. By leveraging attention prediction and aesthetics assessment, the cropping model produces high-quality cropping results, even with the limited availability of training data for photo cropping. The experimental results on benchmark datasets clearly validate the effectiveness of the proposed approach. In addition, our approach runs at 5 fps, outperforming most previous solutions. The code and results are available at: https://github.com/shenjianbing/DeepCropping.

We introduce a semi-supervised video segmentation approach based on an efficient video representation, called as "super-trajectory". A super-trajectory corresponds to a group of compact point trajectories that exhibit consistent motion patterns, similar appearances, and close spatiotemporal relationships. We generate the compact trajectories using a probabilistic model, which enables handling of occlusions and drifts effectively. To reliably group point trajectories, we adopt a modified version of the density peaks based clustering algorithm that allows capturing rich spatiotemporal relations among trajectories in the clustering process. We incorporate two intuitive mechanisms for segmentation, called as reverse-tracking and object re-occurrence, for robustness and boosting the performance. Building on the proposed video representation, our segmentation method is discriminative enough to accurately propagate the initial annotations in the first frame onto the remaining frames. Our extensive experimental analyses on three challenging benchmarks demonstrate that, given the annotation in the first frame, our method is capable of extracting the target objects from complex backgrounds, and even reidentifying them after prolonged occlusions, producing high-quality video object segments.

Currently, the most widely used point trajectories generation methods estimate the trajectories from the dense optical flow, by using a consistency check strategy to detect the occluded regions. However, these methods will miss some important trajectories, thus resulting in breaking smooth areas without any structure especially around the motion boundaries (MBs). We suggest exploring MBs in video to generate more accurate dense point trajectories. Estimating MBs from the video improves the point trajectory accuracy of the discontinuity or occluded areas. Then, we obtain trajectories by tracking the initial feature points through all frames. The experimental results demonstrate that our method outperforms the state-of-the-art methods on the challenging benchmark.

We present an unsupervised segmentation framework for stereo videos using stereoscopic trajectories. The proposed stereo trajectory shows favorable properties for modeling the long-term motion information through the whole sequence and explicitly capturing the corresponding relationships between two stereo views. The stereo prior is important for inferring the desired object and guarantees the consistent spatial-temporal segmentation, which contributes to an enjoyable stereo experience. We start by deriving stereo trajectories from left and right views simultaneously, which are represented via a graph structure. Then we detect object-like stereo trajectories via the graph structure to efficiently infer the desired object. Finally, an energy optimization function is proposed to produce the stereo segmentation results via leveraging the object information from stereo trajectories. To benefit potential research, we collected a new stereoscopic video benchmark, which consists of a total of 50 stereo video clips and includes many challenges in segmentation. Extensive experimental results demonstrate that our stereo segmentation method achieves higher performance and preserves better stereo structures, compared with prevailing competitors. The source code and results are available at: https://github.com/shenjianbing/StereoSeg.

We introduce a novel approach for synthesizing realistic speeches for comics. Using a comic page as input, our approach synthesizes speeches for each comic character following the reading flow. It adopts a cascading strategy to synthesize speeches in two stages: Comic Visual Analysis and Comic Speech Synthesis. In the first stage, the input comic page is analyzed to identify the gender and age of the characters, as well as texts each character speaks and corresponding emotion. Guided by this analysis, in the second stage, our approach synthesizes realistic speeches for each character, which are consistent with the visual observations. Our experiments show that the proposed approach can synthesize realistic and lively speeches for different types of comics. Perceptual studies performed on the synthesis results of multiple sample comics validate the efficacy of our approach.

In this paper, we propose a pose grammar to tackle the problem of 3D human pose estimation. Our model directly takes 2D pose as input and learns a generalized 2D-3D mapping function. The proposed model consists of a base network which efficiently captures pose-aligned features and a hierarchy of Bi-directional RNNs (BRNN) on the top to explicitly incorporate a set of knowledge regarding human body configuration (i.e., kinematics, symmetry, motor coordination). The proposed model thus enforces high-level constraints over human poses. In learning, we develop a pose sample simulator to augment training samples in virtual camera views, which further improves our model generalizability. We validate our method on public 3D human pose benchmarks and propose a new evaluation protocol working on cross-view setting to verify the generalization capability of different methods. We empirically observe that most state-of-the-art methods encounter difficulty under such setting while our method can well handle such challenges.

Given a pre-trained CNN without any testing samples, this paper proposes a simple yet effective method to diagnose feature representations of the CNN. We aim to discover representation flaws caused by potential dataset bias. More specifically, when the CNN is trained to estimate image attributes, we mine latent relationships between representations of different attributes inside the CNN. Then, we compare the mined attribute relationships with ground-truth attribute relationships to discover the CNN's blind spots and failure modes due to dataset bias. In fact, representation flaws caused by dataset bias cannot be examined by conventional evaluation strategies based on testing images, because testing images may also have a similar bias. Experiments have demonstrated the effectiveness of our method.

Hyperparameters are numerical presets whose values are assigned prior to the commencement of the learning process. Selecting appropriate hyperparameters is critical for the accuracy of tracking algorithms, yet it is difficult to determine their optimal values, in particular, adaptive ones for each specific video sequence. Most hyperparameter optimization algorithms depend on searching a generic range and they are imposed blindly on all sequences. Here, we propose a novel hyperparameter optimization method that can find optimal hyperparameters for a given sequence using an action-prediction network leveraged on Continuous Deep Q-Learning. Since the common state-spaces for object tracking tasks are significantly more complex than the ones in traditional control problems, existing Continuous Deep Q-Learning algorithms cannot be directly applied. To overcome this challenge, we introduce an efficient heuristic to accelerate the convergence behavior. We evaluate our method on several tracking benchmarks and demonstrate its superior performance1.

This paper addresses a new problem of inferring shared attention in third-person social scene videos. Shared attention is a phenomenon that two or more individuals simultaneously look at a common target in social scenes. Perceiving and identifying shared attention in videos plays crucial roles in social activities and social scene understanding. We propose a spatial-temporal neural network to detect shared attention intervals in videos and predict shared attention locations in frames. In each video frame, human gaze directions and potential target boxes are two key features for spatially detecting shared attention in the social scene. In temporal domain, a convolutional Long Short-Term Memory network utilizes the temporal continuity and transition constraints to optimize the predicted shared attention heatmap. We collect a new dataset VideoCoAtt1 from public TV show videos, containing 380 complex video sequences with more than 492,000 frames that include diverse social scenes for shared attention study. Experiments on this dataset show that our model can effectively infer shared attention in videos. We also empirically verify the effectiveness of different components in our model.

Research in visual saliency has been focused on two major types of models namely fixation prediction and salient object detection. The relationship between the two, however, has been less explored. In this paper, we propose to employ the former model type to identify and segment salient objects in scenes. We build a novel neural network called Attentive Saliency Network (ASNet) that learns to detect salient objects from fixation maps. The fixation map, derived at the upper network layers, captures a high-level understanding of the scene. Salient object detection is then viewed as fine-grained object-level saliency segmentation and is progressively optimized with the guidance of the fixation map in a top-down manner. ASNet is based on a hierarchy of convolutional LSTMs (convLSTMs) that offers an efficient recurrent mechanism for sequential refinement of the segmentation map. Several loss functions are introduced for boosting the performance of the ASNet. Extensive experimental evaluation shows that our proposed ASNet is capable of generating accurate segmentation maps with the help of the computed fixation map. Our work offers a deeper insight into the mechanisms of attention and narrows the gap between salient object detection and fixation prediction.

In this work, we contribute to video saliency research in two ways. First, we introduce a new benchmark for predicting human eye movements during dynamic scene free-viewing, which is long-time urged in this field. Our dataset, named DHF1K (Dynamic Human Fixation), consists of 1K high-quality, elaborately selected video sequences spanning a large range of scenes, motions, object types and background complexity. Existing video saliency datasets lack variety and generality of common dynamic scenes and fall short in covering challenging situations in unconstrained environments. In contrast, DHF1K makes a significant leap in terms of scalability, diversity and difficulty, and is expected to boost video saliency modeling. Second, we propose a novel video saliency model that augments the CNN-LSTM network architecture with an attention mechanism to enable fast, end-to-end saliency learning. The attention mechanism explicitly encodes static saliency information, thus allowing LSTM to focus on learning more flexible temporal saliency representation across successive frames. Such a design fully leverages existing large-scale static fixation datasets, avoids overfitting, and significantly improves training efficiency and testing performance. We thoroughly examine the performance of our model, with respect to state-of-the-art saliency models, on three large-scale datasets (i.e., DHF1K, Hollywood2, UCF sports). Experimental results over more than 1.2K testing videos containing 400K frames demonstrate that our model outperforms other competitors.

This paper proposes a knowledge-guided fashion network to solve the problem of visual fashion analysis, e.g., fashion landmark localization and clothing category classification. The suggested fashion model is leveraged with high-level human knowledge in this domain. We propose two important fashion grammars: (i) dependency grammar capturing kinematics-like relation, and (ii) symmetry grammar accounting for the bilateral symmetry of clothes. We introduce Bidirectional Convolutional Recurrent Neural Networks (BCRNNs) for efficiently approaching message passing over grammar topologies, and producing regularized landmark layouts. For enhancing clothing category classification, our fashion network is encoded with two novel attention mechanisms, i.e., landmark-aware attention and category-driven attention. The former enforces our network to focus on the functional parts of clothes, and learns domain-knowledge centered representations, leading to a supervised attention mechanism. The latter is goal-driven, which directly enhances task-related features and can be learned in an implicit, top-down manner. Experimental results on large-scale fashion datasets demonstrate the superior performance of our fashion grammar network.

This paper proposes a 3D shape descriptor network, which is a deep convolutional energy-based model, for modeling volumetric shape patterns. The maximum likelihood training of the model follows an "analysis by synthesis" scheme and can be interpreted as a mode seeking and mode shifting process. The model can synthesize 3D shape patterns by sampling from the probability distribution via MCMC such as Langevin dynamics. The model can be used to train a 3D generator network via MCMC teaching. The conditional version of the 3D shape descriptor net can be used for 3D object recovery and 3D object super-resolution. Experiments demonstrate that the proposed model can generate realistic 3D shape patterns and can be useful for 3D shape analysis.

Video saliency, aiming for estimation of a single dominant object in a sequence, offers strong object-level cues for unsupervised video object segmentation. In this paper, we present a geodesic distance based technique that provides reliable and temporally consistent saliency measurement of superpixels as a prior for pixel-wise labeling. Using undirected intra-frame and inter-frame graphs constructed from spatiotemporal edges or appearance and motion, and a skeleton abstraction step to further enhance saliency estimates, our method formulates the pixel-wise segmentation task as an energy minimization problem on a function that consists of unary terms of global foreground and background models, dynamic location models, and pairwise terms of label smoothness potentials. We perform extensive quantitative and qualitative experiments on benchmark datasets. Our method achieves superior performance in comparison to the current state-of-the-art in terms of accuracy and speed.

We introduce the term video co-saliency to denote the task of extracting the common noticeable, or salient, regions from multiple relevant videos. The proposed video co-saliency approach accounts for both inter-video foreground correspondences and intra-video saliency stimuli to emphasize the salient foreground regions of video frames and, at the same time, disregard irrelevant visual information of the background. Compared with image co-saliency, it is more reliable due to the utilization of temporal information of video sequence. Benefiting from the discriminability of video co-saliency, we present a unified framework for segmenting out the common salient regions of relevant videos, guided by video co-saliency prior. Unlike naive video co-segmentation approaches employing simple color differences and local motion features, the presented video co-saliency provides a more powerful indicator for the common salient regions, thus conducting video co-segmentation efficiently. Extensive experiments show that the proposed method successfully infers video co-saliency and extracts the common salient regions, outperforming the state-of-the-art methods.

In this paper, we introduce a novel approach to identify salient object regions in videos via object proposals. The core idea is to solve the saliency detection problem by ranking and selecting the salient proposals based on object-level saliency cues. Object proposals offer a more complete and high-level representation, which naturally caters to the needs of salient object detection. As well as introducing this novel solution for video salient object detection, we reorganize various discriminative saliency cues and traditional saliency assumptions on object proposals. With object candidates, a proposal ranking and voting scheme, based on various object-level saliency cues, is designed to screen out nonsalient parts, select salient object regions, and to infer an initial saliency estimate. Then a saliency optimization process that considers temporal consistency and appearance differences between salient and nonsalient regions is used to refine the initial saliency estimates. Our experiments on public datasets (SegTrackV2, Freiburg-Berkeley Motion Segmentation Dataset, and Densely Annotated Video Segmentation) validate the effectiveness, and the proposed method produces significant improvements over state-of-the-art algorithms.

In this paper, we aim to predict human eye fixation with view-free scenes based on an end-to-end deep learning architecture. Although convolutional neural networks (CNNs) have made substantial improvement on human attention prediction, it is still needed to improve the CNN-based attention models by efficiently leveraging multi-scale features. Our visual attention network is proposed to capture hierarchical saliency information from deep, coarse layers with global saliency information to shallow, fine layers with local saliency response. Our model is based on a skip-layer network structure, which predicts human attention from multiple convolutional layers with various reception fields. Final saliency prediction is achieved via the cooperation of those global and local predictions. Our model is learned in a deep supervision manner, where supervision is directly fed into multi-level layers, instead of previous approaches of providing supervision only at the output layer and propagating this supervision back to earlier layers. Our model thus incorporates multi-level saliency predictions within a single network, which significantly decreases the redundancy of previous approaches of learning multiple network streams with different input scales. Extensive experimental analysis on various challenging benchmark data sets demonstrate our method yields the state-of-the-art performance with competitive inference time.

This paper proposes a deep learning model to efficiently detect salient regions in videos. It addresses two important issues: 1) deep video saliency model training with the absence of sufficiently large and pixel-wise annotated video data and 2) fast video saliency training and detection. The proposed deep video saliency network consists of two modules, for capturing the spatial and temporal saliency information, respectively. The dynamic saliency model, explicitly incorporating saliency estimates from the static saliency model, directly produces spatiotemporal saliency inference without time-consuming optical flow computation. We further propose a novel data augmentation technique that simulates video training data from existing annotated image data sets, which enables our network to learn diverse saliency information and prevents overfitting with the limited number of training videos. Leveraging our synthetic video data (150K video sequences) and real videos, our deep video saliency model successfully learns both spatial and temporal saliency cues, thus producing accurate spatiotemporal saliency estimate. We advance the state-of-the-art on the densely annotated video segmentation data set (MAE of .06) and the Freiburg-Berkeley Motion Segmentation data set (MAE of .07), and do so with much improved speed (2 fps with all steps).This paper proposes a deep learning model to efficiently detect salient regions in videos. It addresses two important issues: 1) deep video saliency model training with the absence of sufficiently large and pixel-wise annotated video data and 2) fast video saliency training and detection. The proposed deep video saliency network consists of two modules, for capturing the spatial and temporal saliency information, respectively. The dynamic saliency model, explicitly incorporating saliency estimates from the static saliency model, directly produces spatiotemporal saliency inference without time-consuming optical flow computation. We further propose a novel data augmentation technique that simulates video training data from existing annotated image data sets, which enables our network to learn diverse saliency information and prevents overfitting with the limited number of training videos. Leveraging our synthetic video data (150K video sequences) and real videos, our deep video saliency model successfully learns both spatial and temporal saliency cues, thus producing accurate spatiotemporal saliency estimate. We advance the state-of-the-art on the densely annotated video segmentation data set (MAE of .06) and the Freiburg-Berkeley Motion Segmentation data set (MAE of .07), and do so with much improved speed (2 fps with all steps).

We model the photo cropping problem as a cascade of attention box regression and aesthetic quality classification, based on deep learning. A neural network is designed that has two branches for predicting attention bounding box and analyzing aesthetics, respectively. The predicted attention box is treated as an initial crop window where a set of cropping candidates are generated around it, without missing important information. Then, aesthetics assessment is employed to select the final crop as the one with the best aesthetic quality. With our network, cropping candidates share features within full-image convolutional feature maps, thus avoiding repeated feature computation and leading to higher computation efficiency. Via leveraging rich data for attention prediction and aesthetics assessment, the proposed method produces high-quality cropping results, even with the limited availability of training data for photo cropping. The experimental results demonstrate the competitive results and fast processing speed (5 fps with all steps).

We introduce a novel semi-supervised video segmentation approach based on an efficient video representation, called as “super-trajectory”. Each super-trajectory corresponds to a group of compact trajectories that exhibit consistent motion patterns, similar appearance and close spatiotemporal relationships. We generate trajectories using a probabilistic model, which handles occlusions and drifts in a robust and natural way. To reliably group trajectories, we adopt a modified version of the density peaks based clustering algorithm that allows capturing rich spatiotemporal relations among trajectories in the clustering process. The presented video representation is discriminative enough to accurately propagate the initial annotations in the first frame onto the remaining video frames. Extensive experimental analysis on challenging benchmarks demonstrate our method is capable of distinguishing the target objects from complex backgrounds and even reidentifying them after occlusions.

Conventional video segmentation approaches rely heavily on appearance models. Such methods often use appearance descriptors that have limited discriminative power under complex scenarios. To improve the segmentation performance, this paper presents a pyramid histogram-based confidence map that incorporates structure information into appearance statistics. It also combines geodesic distance-based dynamic models. Then, it employs an efficient measure of uncertainty propagation using local classifiers to determine the image regions, where the object labels might be ambiguous. The final foreground cutout is obtained by refining on the uncertain regions. Additionally, to reduce manual labeling, our method determines the frames to be labeled by the human operator in a principled manner, which further boosts the segmentation performance and minimizes the labeling effort. Our extensive experimental analyses on two big benchmarks demonstrate that our solution achieves superior performance, favorable computational efficiency, and reduced manual labeling in comparison to the state of the art.

The online learning methods are popular for visual tracking because of their robust performance for most video sequences. However, the drifting problem caused by noisy updates is still a challenge for most highly adaptive online classifiers. In visual tracking, target object appearance variation, such as deformation and long-term occlusion, easily causes noisy updates. To overcome this problem, a new real-time occlusion-aware visual tracking algorithm is introduced. First, we learn a novel two-stage classifier with circulant structure with kernel, named integrated circulant structure kernels (ICSK). The first stage is applied for transition estimation and the second is used for scale estimation. The circulant structure makes our algorithm realize fast learning and detection. Then, the ICSK is used to detect the target without occlusion and build a classifier pool to save these classifiers with noisy updates. When the target is in heavy occlusion or after long-term occlusion, we redetect it using an optimal classifier selected from the classifier-pool according to an entropy minimization criterion. Extensive experimental results on the full benchmark demonstrate our real-time algorithm achieves better performance than state-of-the-art methods.

In this paper, we propose a framework for automatically producing thumbnails from stereo image pairs. It has two components focusing respectively on stereo saliency detection and stereo thumbnail generation. The first component analyzes stereo saliency through various saliency stimuli, stereoscopic perception and the relevance between two stereo views. The second component uses stereo saliency to guide stereo thumbnail generation. We develop two types of thumbnail generation methods, both changing image size automatically. The first method is called content-persistent cropping (CPC), which aims at cropping stereo images for display devices with different aspect ratios while preserving as much content as possible. The second method is an object-aware cropping method (OAC) for generating the smallest possible thumbnail pair that retains the most important content only and facilitates quick visual exploration of a stereo image database. Quantitative and qualitative experimental evaluations demonstrate promising performance of our thumbnail generation methods in comparison to state-of-the-art algorithms.

In this paper, we propose a real-time image superpixel segmentation method with 50 frames/s by using the density-based spatial clustering of applications with noise (DBSCAN) algorithm. In order to decrease the computational costs of superpixel algorithms, we adopt a fast two-step framework. In the first clustering stage, the DBSCAN algorithm with color-similarity and geometric restrictions is used to rapidly cluster the pixels, and then, small clusters are merged into superpixels by their neighborhood through a distance measurement defined by color and spatial features in the second merging stage. A robust and simple distance function is defined for obtaining better superpixels in these two steps. The experimental results demonstrate that our real-time superpixel algorithm (50 frames/s) by the DBSCAN clustering outperforms the state-of-the-art superpixel segmentation methods in terms of both accuracy and efficiency.

In this paper, we show that large annotated data sets have great potential to provide strong priors for saliency estimation rather than merely serving for benchmark evaluations. To this end, we present a novel image saliency detection method called saliency transfer. Given an input image, we first retrieve a support set of best matches from the large database of saliency annotated images. Then, we assign the transitional saliency scores by warping the support set annotations onto the input image according to computed dense correspondences. To incorporate context, we employ two complementary correspondence strategies: a global matching scheme based on scene-level analysis and a local matching scheme based on patch-level inference. We then introduce two refinement measures to further refine the saliency maps and apply the random-walk-with-restart by exploring the global saliency structure to estimate the affinity between foreground and background assignments. Extensive experimental results on four publicly available benchmark data sets demonstrate that the proposed saliency algorithm consistently outperforms the current state-of-the-art methods.

A novel interactive image cosegmentation algorithm using likelihood estimation and higher order energy optimization is proposed for extracting common foreground objects from a group of related images. Our approach introduces the higher order clique's, energy into the cosegmentation optimization process successfully. A region-based likelihood estimation procedure is first performed to provide the prior knowledge for our higher order energy function. Then, a new cosegmentation energy function using higher order cliques is developed, which can efficiently cosegment the foreground objects with large appearance variations from a group of images in complex scenes. Both the quantitative and qualitative experimental results on representative datasets demonstrate that the accuracy of our cosegmentation results is much higher than the state-of-the-art cosegmentation methods.

We introduce an unsupervised, geodesic distance based, salient video object segmentation method. Unlike traditional methods, our method incorporates saliency as prior for object via the computation of robust geodesic measurement. We consider two discriminative visual features: spatial edges and temporal motion boundaries as indicators of foreground object locations. We first generate framewise spatiotemporal saliency maps using geodesic distance from these indicators. Building on the observation that foreground areas are surrounded by the regions with high spatiotemporal edge values, geodesic distance provides an initial estimation for foreground and background. Then, high-quality saliency results are produced via the geodesic distances to background regions in the subsequent frames. Through the resulting saliency maps, we build global appearance models for foreground and background. By imposing motion continuity, we establish a dynamic location model for each frame. Finally, the spatiotemporal saliency maps, appearance models and dynamic location models are combined into an energy minimization framework to attain both spatially and temporally coherent object segmentation. Extensive quantitative and qualitative experiments on benchmark video dataset demonstrate the superiority of the proposed method over the state-of-the-art algorithms.

With ever-increasing volumes of video data, automatic extraction of salient object regions became even more significant for visual analytic solutions. This surge has also opened up opportunities for taking advantage of collective cues encapsulated in multiple videos in a cooperative manner. However, it also brings up major challenges, such as handling of drastic appearance, motion pattern, and pose variations, of foreground objects as well as indiscriminate backgrounds. Here, we present a cosegmentation framework to discover and segment out common object regions across multiple frames and multiple videos in a joint fashion. We incorporate three types of cues, i.e., intraframe saliency, interframe consistency, and across-video similarity into an energy optimization framework that does not make restrictive assumptions on foreground appearance and motion model, and does not require objects to be visible in all frames. We also introduce a spatio-temporal scale-invariant feature transform (SIFT) flow descriptor to integrate across-video correspondence from the conventional SIFT-flow into interframe motion flow from optical flow. This novel spatio-temporal SIFT flow generates reliable estimations of common foregrounds over the entire video data set. Experimental results show that our method outperforms the state-of-the-art on a new extensive data set (ViCoSeg).

We present a novel spatiotemporal saliency detection method to estimate salient regions in videos based on the gradient flow field and energy optimization. The proposed gradient flow field incorporates two distinctive features: 1) intra-frame boundary information and 2) inter-frame motion information together for indicating the salient regions. Based on the effective utilization of both intra-frame and inter-frame information in the gradient flow field, our algorithm is robust enough to estimate the object and background in complex scenes with various motion patterns and appearances. Then, we introduce local as well as global contrast saliency measures using the foreground and background information estimated from the gradient flow field. These enhanced contrast saliency cues uniformly highlight an entire object. We further propose a new energy function to encourage the spatiotemporal consistency of the output saliency maps, which is seldom explored in previous video saliency methods. The experimental results show that the proposed algorithm outperforms state-of-the-art video saliency detection methods.

In this paper, we propose a novel approach to segment moving object in video by utilizing improved point trajectories . First, point trajectories are densely sampled from video and tracked through optical flow, which provides information of long-term temporal interactions among objects in the video sequence . Second, a novel affinity measurement method considering both global and local information of point trajectories is proposed to cluster trajectories into groups. Finally, we propose a new graph-based segmentation method which adopts both local and global motion information encoded by the tracked dense point trajectories. The proposed approach achieves good performance on trajectory clustering, and it also obtains accurate video object segmentation results on both the Moseg dataset and our new dataset containing more challenging videos.

We present a novel image superpixel segmentation approach using the proposed lazy random walk (LRW) algorithm in this paper. Our method begins with initializing the seed positions and runs the LRW algorithm on the input image to obtain the probabilities of each pixel. Then, the boundaries of initial superpixels are obtained according to the probabilities and the commute time. The initial superpixels are iteratively optimized by the new energy function, which is defined on the commute time and the texture measurement. Our LRW algorithm with self-loops has the merits of segmenting the weak boundaries and complicated texture regions very well by the new global probability maps and the commute time strategy. The performance of superpixel is improved by relocating the center positions of superpixels and dividing the large superpixels into small ones with the proposed optimization algorithm. The experimental results have demonstrated that our method achieves better performance than previous superpixel approaches.