Diffusion-based or flow-based models have achieved significant progress in video synthesis but require multiple iterative sampling steps, which incurs substantial computational overhead. While many distillation methods that are solely based on trajectory-preserving or distribution-matching have been developed to accelerate video generation models, these approaches often suffer from performance breakdown or increased artifacts in few-step settings. To address these limitations, we propose SwiftVideo, a unified and stable distillation framework that combines the advantages of trajectory-preserving and distribution-matching strategies. Our approach introduces continuous-time consistency distillation to ensure precise preservation of ODE trajectories. Subsequently, We propose a dual-perspective alignment encompassing distribution alignment between synthetic and real data along with trajectory alignment across different inference steps. Our method maintains high-quality video generation while substantially reducing the number of inference steps. Quantitative evaluations on the OpenVid-1M benchmark demonstrate that our method significantly outperforms existing approaches in few-step video generation.

We introduce a one-step generative policy for offline reinforcement learning that maps *noise* directly to *actions* via a *residual reformulation* of MeanFlow, making it compatible with Q-learning. While one-step Gaussian policies enable fast inference, they struggle to capture complex, multimodal action distributions. Existing flow-based methods improve expressivity but typically rely on distillation and two-stage training when trained with Q-learning. To overcome these limitations, we propose to reformulate MeanFlow to enable *direct noise-to-action generation* by integrating the velocity field and noise-to-action transformation into a single policy network—eliminating the need for separate velocity estimation. We explore several reformulation variants and identify an effective *residual formulation* that supports expressive and stable policy learning. Our method offers three key advantages: 1) efficient one-step noise-to-action generation, 2) expressive modelling of multimodal action distributions, and 3) efficient and stable policy learning via Q-learning in a single-stage training setup. Extensive experiments on 73 tasks across the OGBench and D4RL benchmarks demonstrate that our method achieves strong performance in both offline and offline-to-online reinforcement learning settings.

Reasoning in large language models has long been a central research focus, and recent studies employing reinforcement learning (RL) have introduced diverse methods that yield substantial performance gains with minimal or even no external supervision. Surprisingly, some studies even suggest that random or incorrect reward signals can enhance performance. However, these breakthroughs are predominantly observed for the mathematically strong Qwen2.5 series on benchmarks such as MATH-500, AMC, and AIME, and seldom transfer to models like Llama, which warrants a more in-depth investigation. In this work, our empirical analysis reveals that pre-training on massive web-scale corpora leaves Qwen2.5 susceptible to data contamination in widely used benchmarks. Consequently, conclusions derived from contaminated benchmarks on Qwen2.5 series may be unreliable. To obtain trustworthy evaluation results, we introduce a generator that creates fully clean arithmetic problems of arbitrary length and difficulty, dubbed RandomCalculation. Using this leakage-free dataset, we show that only accurate reward signals yield steady improvements that surpass the base model’s performance boundary in mathematical reasoning, whereas random or incorrect rewards do not. Moreover, we conduct more fine-grained analyses to elucidate the factors underlying the different performance observed on the MATH-500 and RandomCalculation benchmarks. Consequently, we recommend that future studies evaluate models on uncontaminated benchmarks and, when feasible, test various model series to ensure trustworthy conclusions about RL and related methods.

Controllable image-to-video (I2V) generation transforms a reference image into a coherent video guided by user-specified control signals. While precise control over camera motion, object motion, and lighting is essential for high-fidelity creation, existing methods often treat these factors independently. This overlooks the physical coupling among viewpoint, geometry, and illumination in dynamic scenes, leading to visual inconsistencies such as mismatched shadows and perspective drift under simultaneous changes. We present VidCRAFT3, a unified and flexible I2V framework that explicitly models cross-factor interactions among geometry, motion, and illumination, enabling both independent and joint control over camera motion, object motion, and lighting direction. Image2Cloud provides explicit 3D geometric priors for accurate camera motion control. ObjMotionNet encodes sparse object trajectories into multi-scale motion features to guide realistic object motion. A Spatial Triple-Attention Transformer integrates lighting direction through lighting cross-attention for consistent relighting. To address the scarcity of jointly annotated data, we construct the VideoLightingDirection (VLD) dataset with accurate per-frame lighting direction annotations, and introduce a three-stage progressive training strategy that enables robust learning without fully joint annotations. Extensive experiments demonstrate that VidCRAFT3 achieves state-of-the-art performance in control precision and visual coherence across diverse scenarios.

Visual storytelling involves generating a sequence of coherent frames from a textual storyline while maintaining consistency in characters and scenes. Existing autoregressive methods, which rely on previous frame-sentence pairs, struggle with high memory usage, slow generation speeds, and limited context integration. To address these issues, we propose ContextualStory, a novel framework designed to generate coherent story frames and extend frames for visual storytelling. ContextualStory utilizes Spatially-Enhanced Temporal Attention to capture spatial and temporal dependencies, handling significant character movements effectively. Additionally, we introduce a Storyline Contextualizer to enrich context in storyline embedding, and a StoryFlow Adapter to measure scene changes between frames for guiding the model. Extensive experiments on PororoSV and FlintstonesSV datasets demonstrate that ContextualStory significantly outperforms existing SOTA methods in both story visualization and continuation.

Recent advances in image inpainting increasingly use generative models to handle large irregular masks. However, these models can create unrealistic inpainted images due to two main issues: (1) Unwanted object insertion: Even with unmasked areas as context, generative models may still generate arbitrary objects in the masked region that don’t align with the rest of the image. (2) Color inconsistency: Inpainted regions often have color shifts that causes a smeared appearance, reducing image quality. Retraining the generative model could help solve these issues, but it’s costly since state-of-the-art latent-based diffusion and rectified flow models require a three-stage training process: training a VAE, training a generative U-Net or transformer, and fine-tuning for inpainting. Instead, this paper proposes a post-processing approach, dubbed as ASUKA (Aligned Stable inpainting with UnKnown Areas prior), to improve inpainting models. To address unwanted object insertion, we leverage a Masked Auto-Encoder (MAE) for reconstruction-based priors. This mitigates object hallucination while maintaining the model’s generation capabilities. To address color inconsistency, we propose a specialized VAE decoder that treats latent-to-image decoding as a local harmonization task, significantly reducing color shifts for color-consistent inpainting. We validate ASUKA on SD 1.5 and FLUX inpainting variants with Places2 and MISATO, our proposed diverse collection of datasets. Results show that ASUKA mitigates object hallucination and improves color consistency over standard diffusion and rectified flow models and other inpainting methods.

We introduce MVGenMaster, a multi-view diffusion model enhanced with 3D priors to address versatile Novel View Synthesis (NVS) tasks. MVGenMaster leverages 3D priors that are warped using metric depth and camera poses, significantly enhancing both generalization and 3D consistency in NVS. Our model features a simple yet effective pipeline that can generate up to 100 novel views conditioned on variable reference views and camera poses with a single forward process. Additionally, we have developed a comprehensive large-scale multi-view image dataset called MvD-1M, comprising up to 1.6 million scenes, equipped with well-aligned metric depth to train MVGenMaster. Moreover, we present several training and model modifications to strengthen the model with scaled-up datasets. Extensive evaluations across in- and out- of- domain benchmarks demonstrate the effectiveness of our proposed method and data formulation.

Co-speech gestures are crucial non-verbal cues that enhance speech clarity and expressiveness in human communication, which have attracted increasing attention in multimodal research. While the existing methods have made strides in gesture accuracy, challenges remain in generating diverse and coherent gestures, as most approaches assume independence among multimodal inputs and lack explicit modeling of their interactions. In this work, we propose a novel multimodal learning method named HOP for co-speech gesture generation that captures the heterogeneous entanglement between gesture motion, audio rhythm, and text semantics, enabling the generation of coordinated gestures. By leveraging spatiotemporal graph modeling, we achieve the alignment of audio and action. Moreover, to enhance modality coherence, we build the audio-text semantic representation based on a reprogramming module, which is beneficial for cross-modality adaptation. Our approach enables the trimodal system to learn each other’s features and represent them in the form of topological entanglement. Extensive experiments demonstrate that HOP achieves state-of-the-art performance, offering more natural and expressive co-speech gesture generation. More information, codes, and demos are available here: https://star-uu-wang.github.io/HOP/.

This paper tackles category-level pose estimation of articulated objects in robotic manipulation tasks and introduces a new benchmark dataset. While recent methods estimate part poses and sizes at the category level, they often rely on geometric cues and complex multi-stage pipelines that first segment parts from the point cloud, followed by Normalized Part Coordinate Space (NPCS) estimation for 6D poses. These approaches overlook dense semantic cues from RGB images, leading to suboptimal accuracy, particularly for objects with small parts. To address these limitations, we propose a single-stage Network, CAP-Net, for estimating the 6D poses and sizes of Categorical Articulated Parts. This method combines RGB-D features to generate instance segmentation and NPCS representations for each part in an end-to-end manner. CAP-Net uses a unified network to simultaneously predict point-wise class labels, centroid offsets, and NPCS maps. A clustering algorithm then groups points of the same predicted class based on their estimated centroid distances to isolate each part. Finally, the NPCS region of each part is aligned with the point cloud to recover its final pose and size. To bridge the sim-to-real domain gap, we introduce the RGBD-Art dataset, the largest RGB-D articulated dataset to date, featuring photorealistic RGB images and depth noise simulated from real sensors. Experimental evaluations on the RGBD-Art dataset demonstrate that our method significantly outperforms the state-of-the-art approach. Real-world deployments of our model in robotic tasks underscore its robustness and exceptional sim-to-real transfer capabilities, confirming its substantial practical utility. Our dataset, code and pre-trained models are available on the project page2.

Recent advances in diffusion-based text-to-image models have simplified creating high-fidelity images, but preserving the identity (ID) of specific elements, like a personal dog, is still challenging. Object customization, using reference images and textual descriptions, is key to addressing this issue. Current object customization methods are either object-specific, requiring extensive fine-tuning, or object-agnostic, offering zero-shot customization but limited to specialized domains. The primary issue of promoting zero-shot object customization from specific domains to the general domain is to establish a large-scale general ID dataset for model pre-training, which is time-consuming and labor-intensive. In this paper, we propose a novel pipeline to construct a large dataset of general objects and build the Multi-Category ID-Consistent (MC-IDC) dataset, featuring 315k text-image samples across 10k categories. With the help of MC-IDC, we introduce Customizing Anything (CustAny), a zero-shot framework that maintains ID fidelity and supports flexible text editing for general objects. CustAny features three key components: a general ID extraction module, a dual-level ID injection module, and an ID-aware decoupling module, allowing it to customize any object from a single reference image and text prompt. Experiments demonstrate that CustAny outperforms existing methods in both general object customization and specialized domains like human customization and virtual try-on. Our contributions include a large-scale dataset, the CustAny framework and novel ID processing to advance this field. The official project page is in https://lingjiekong-fdu.github.io.

Open-vocabulary 3D visual grounding and reasoning aim to localize objects in a scene based on implicit language descriptions, even when they are occluded. This ability is crucial for tasks such as vision-language navigation and autonomous robotics. However, current methods struggle because they rely heavily on fine-tuning with 3D annotations and mask proposals, which limits their ability to handle diverse semantics and common knowledge required for effective reasoning. In this work, we propose ReasonGrounder, an LVLM-guided framework that uses hierarchical 3D feature Gaussian fields for adaptive grouping based on physical scale, enabling open-vocabulary 3D grounding and reasoning. ReasonGrounder interprets implicit instructions using large vision-language models (LVLM) and localizes occluded objects through 3D Gaussian splatting. By incorporating 2D segmentation masks from the SAM and multi-view CLIP embeddings, ReasonGrounder selects Gaussian groups based on object scale, enabling accurate localization through both explicit and implicit language understanding, even in novel, occluded views. We also contribute ReasoningGD, a new dataset containing over 10K scenes and 2 million annotations for evaluating open-vocabulary 3D grounding and amodal perception under occlusion. Experiments show that ReasonGrounder significantly improves 3D grounding accuracy in real-world scenarios.

Handling complex or nonlinear motion patterns has long posed challenges for video frame interpolation. Although recent advances in diffusion-based methods offer improvements over traditional optical flow-based approaches, they still struggle to generate sharp, temporally consistent frames in scenarios with large motion. To address this limitation, we introduce EDEN, an Enhanced Diffusion for high-quality large-motion vidEo frame iNterpolation. Our approach first utilizes a transformer-based tokenizer to produce refined latent representations of the intermediate frames for diffusion models. We then enhance the diffusion transformer with temporal attention across the process and incorporate a start-end frame difference embedding to guide the generation of dynamic motion. Extensive experiments demonstrate that EDEN achieves state-of-the-art results across popular benchmarks, including nearly a 10% LPIPS reduction on DAVIS and SNU-FILM, and an 8% improvement on DAIN-HD.

As large-scale diffusion models continue to advance, they excel at producing high-quality images but often generate unwanted content, such as sexually explicit or violent imagery. Existing methods for removing such content typically guide the image generation process but can inadvertently modify unrelated regions, leading to inconsistencies with the original model. We propose a novel approach for targeted concept replacement in diffusion models, enabling specific unwanted concepts to be removed without significantly affecting non-target areas. Our method introduces a dedicated concept localizer for precisely identifying the target concept during the denoising process, using few-shot learning to minimize the need for labeled data.Within the identified region, we further introduce a Dual Prompts Cross-Attention module that operates without additional training to substitute the target concept, ensuring minimal disruption to surrounding content. We evaluate our method in terms of concept localization precision and replacement efficiency. Experimental results demonstrate that our method achieves superior precision in localizing target concepts and performs coherent concept replacement with minimal impact on non-target areas, outperforming existing approaches. The code is available at https://github.com/zhang-lingyun/ConceptReplacer

Cloth-changing person re-identification aims at recognizing the same person with clothing changes across non-overlapping cameras. Advanced methods either resort to identity-related auxiliary modalities (e.g., sketches, silhouettes, and keypoints) or clothing labels to mitigate the impact of clothes. However, relying on unpractical and inflexible auxiliary modalities or annotations limits their real-world applicability. In this paper, we promote cloth-changing person re-identification by leveraging abundant semantics present within pedestrian images, without the need for any auxiliaries. Specifically, we first propose a unified Semantics Mining and Refinement (SMR) module to extract robust identity-related content and salient semantics, mitigating interference from clothing appearances effectively. We further propose the Content and Salient Semantics Collaboration (CSSC) framework to collaborate and leverage various semantics, facilitating cross-parallel semantic interaction and refinement. Our proposed method achieves state-of-the-art performance on three cloth-changing benchmarks, demonstrating its superiority over advanced competitors. The code is available at https://github.com/QizaoWang/CSSC-CCReID.

Visual imitation learning is effective for robots to learn versatile tasks. However, many existing methods rely on behavior cloning with supervised historical trajectories, limiting their 3D spatial and 4D spatiotemporal awareness. Consequently, these methods struggle to capture the 3D structures and 4D spatiotemporal relationships necessary for real-world deployment. In this work, we propose 4D Diffusion Policy (DP4), a novel visual imitation learning method that incorporates spatiotemporal awareness into diffusion-based policies. Unlike traditional approaches that rely on trajectory cloning, DP4 leverages a dynamic Gaussian world model to guide the learning of 3D spatial and 4D spatiotemporal perceptions from interactive environments. Our method constructs the current 3D scene from a single-view RGB-D observation and predicts the future 3D scene, optimizing trajectory generation by explicitly modeling both spatial and temporal dependencies. Extensive experiments across 17 simulation tasks with 173 variants and 3 real-world robotic tasks demonstrate that the 4D Diffusion Policy (DP4) outperforms baseline methods, improving the average simulation task success rate by 16.4% (Adroit), 14% (DexArt), and 6.45% (RLBench), and the average real-world robotic task success rate by 8.6%.

Bimanual manipulation is crucial in robotics, enabling complex tasks in industrial automation and household services. However, it poses significant challenges due to the high-dimensional action space and intricate coordination requirements. While video prediction has been recently studied for representation learning and control, leveraging its ability to capture rich dynamic and behavioral information, its potential for enhancing bimanual coordination remains underexplored. To bridge this gap, we propose a unified diffusion-based framework for the joint optimization of video and action prediction. Specifically, we propose a multi-frame latent prediction strategy that encodes future states in a compressed latent space, preserving task-relevant features. Furthermore, we introduce a unidirectional attention mechanism where video prediction is conditioned on the action, while action prediction remains independent of video prediction. This design allows us to omit video prediction during inference, significantly enhancing efficiency. Experiments on two simulated benchmarks and a real-world setting demonstrate a significant improvement in the success rate over the strong baseline ACT using our method, achieving a \textbf{24.9\%} increase on ALOHA, an \textbf{11.1\%} increase on RoboTwin, and a \textbf{32.5\%} increase in real-world experiments. Our models and code are publicly available at https://github.com/return-sleep/Diffusion_based_imaginative_Coordination.

Large transformers have demonstrated remarkable success, making it necessary to compress these models to reduce inference costs while preserving their performance. Current compression algorithms prune transformers at fixed compression ratios, requiring a unique pruning process for each ratio, which results in high computational costs. In contrast, we propose pruning of pretrained transformers at any desired ratio within a single pruning stage, based on a differential inclusion for a mask parameter. This dynamic can generate the whole regularization solution path of the mask parameter, whose support set identifies the network structure. Therefore, the solution path identifies a Transformer weight family with various sparsity levels, offering greater flexibility and customization.In this paper, weintroduce such an effective pruning method, termed SPP (Solution Path Pruning). To achieve effective pruning, we segment the transformers into paired modules, including query-key pairs, value-projection pairs, and sequential linear layers, and apply low-rank compression to these pairs, maintaining the output structure while enabling structural compression within the inner states. Extensive experiments conducted on various well-known transformer backbones have demonstrated the efficacy of SPP.

Unveiling an empty street from crowded observations captured by in-car cameras is crucial for autonomous driving. However, removing all temporarily static objects, such as stopped vehicles and standing pedestrians, presents a significant challenge. Unlike object-centric 3D inpainting, which relies on thorough observation in a small scene, street scene cases involve long trajectories that differ from previous 3D inpainting tasks. The camera-centric moving environment of captured videos further complicates the task due to the limited degree and time duration of object observation. To address these obstacles, we introduce StreetUnveiler to reconstruct an empty street. StreetUnveiler learns a 3D representation of the empty street from crowded observations. Our representation is based on the hard-label semantic 2D Gaussian Splatting (2DGS) for its scalability and ability to identify Gaussians to be removed. We inpaint rendered image after removing unwanted Gaussians to provide pseudo-labels and subsequently re-optimize the 2DGS. Given its temporal continuous movement, we divide the empty street scene into observed, partial-observed, and unobserved regions, which we propose to locate through a rendered alpha map. This decomposition helps us to minimize the regions that need to be inpainted. To enhance the temporal consistency of the inpainting, we introduce a novel time-reversal framework to inpaint frames in reverse order and use later frames as references for earlier frames to fully utilize the long-trajectory observations. Our experiments conducted on the street scene dataset successfully reconstructed a 3D representation of the empty street. The mesh representation of the empty street can be extracted for further applications.

Human image animation aims to generate a video from a static image by following a specified pose sequence. Existing methods typically adopt a multi-stage pipeline that separately learns appearance and motion, leading to appearance degradation and temporal inconsistencies. To address these issues, we propose VividPose, an innovative end-to-end pipeline based on Stable Video Diffusion (SVD) that ensures superior temporal stability. To enhance the retention of human identity, we propose an identity-aware appearance controller that integrates additional facial information without compromising other appearance details such as clothing texture and background. To accommodate diverse human body shapes and hand movements, we introduce a geometry-aware pose controller that utilizes both rendering maps and skeleton maps. Extensive qualitative and quantitative experiments on the UBCFashion and TikTok benchmarks demonstrate that our method achieves state-of-the-art performance. Furthermore, VividPose exhibits superior generalization capabilities on our proposed in-the-wild dataset. Our project page is available at https://kelu007.github.io/vivid-pose.

Bivariate causal discovery is challenging when unmeasured confounders exist. To adjust for the bias, previous methods employed the proxy variable (i.e., negative control outcome (NCO)) to test the treatment-outcome relationship through integral equations – and assumed that violation of this equation indicates the causal relationship. Upon this, they could establish asymptotic properties for causal hypothesis testing. However, these methods either relied on parametric assumptions or required discretizing continuous variables, which may lead to information loss. Moreover, it is unclear when this underlying integral-related assumption holds, making it difficult to justify the utility in practice. To address these problems, we first consider the scenario where only NCO is available. We propose a novel non-parametric procedure, which enjoys asymptotic properties and preserves more information. Moreover, we find that when NCO affects the outcome, the above integral-related assumption may not hold, rendering the causal relation unidentifiable. Informed by this, we further consider the scenario when the negative control exposure (NCE) is also available. In this scenario, we construct another integral restriction aided by this proxy, which can discover causation when NCO affects the outcome. We demonstrate these findings and the effectiveness of our proposals through comprehensive numerical studies.

Recent advances in diffusion bridge models leverage Doob’s $h$-transform to establish fixed endpoints between distributions, demonstrating promising results in image translation and restoration tasks. However, these approaches frequently produce blurred or excessively smoothed image details and lack a comprehensive theoretical foundation to explain these shortcomings. To address these limitations, we propose UniDB, a unified framework for diffusion bridges based on Stochastic Optimal Control (SOC). UniDB formulates the problem through an SOC-based optimization and derives a closed-form solution for the optimal controller, thereby unifying and generalizing existing diffusion bridge models. We demonstrate that existing diffusion bridges employing Doob’s $h$-transform constitute a special case of our framework, emerging when the terminal penalty coefficient in the SOC cost function tends to infinity. By incorporating a tunable terminal penalty coefficient, UniDB achieves an optimal balance between control costs and terminal penalties, substantially improving detail preservation and output quality. Notably, UniDB seamlessly integrates with existing diffusion bridge models, requiring only minimal code modifications. Extensive experiments across diverse image restoration tasks validate the superiority and adaptability of the proposed framework. Our code is available at https://github.com/UniDB-SOC/UniDB/.

This paper addresses the problem of category-level pose estimation for articulated objects in robotic manipulation tasks. Recent works have shown promising results in estimating part pose and size at the category level. However, these approaches primarily follow a complex multi-stage pipeline that first segments part instances in the point cloud and then estimates the Normalized Part Coordinate Space (NPCS) representation for 6D poses. These approaches suffer from high computational costs and low performance in real-time robotic tasks. To address these limitations, we propose YOEO, a single-stage method that simultaneously outputs instance segmentation and NPCS representations in an end-to-end manner. We use a unified network to generate point-wise semantic labels and centroid offsets, allowing points from the same part instance to vote for the same centroid. We further utilize a clustering algorithm to distinguish points based on their estimated centroid distances. Finally, we first separate the NPCS region of each instance. Then, we align the separated regions with the real point cloud to recover the final pose and size. Experimental results on the GAPart dataset demonstrate the pose estimation capabilities of our proposed single-shot method. We also deploy our synthetically-trained model in a real-world setting, providing real-time visual feedback at 200Hz, enabling a physical Kinova robot to interact with unseen articulated objects. This showcases the utility and effectiveness of our proposed method2.

Despite remarkable progress in image-based virtual try-on systems, generating realistic and robust fitting images for cross-category virtual try-on remains a challenging task. The primary difficulty arises from the absence of human-like reasoning, which involves addressing size mismatches between garments and models while recognizing and leveraging the distinct functionalities of various regions within the model images. To address this issue, we draw inspiration from human cognitive processes and disentangle the complex reasoning required for cross-category try-on into a structured framework. This framework systematically decomposes the model image into three distinct regions: try-on, reconstruction, and imagination zones. Each zone plays a specific role in accommodating the garment and facilitating realistic synthesis. To endow the model with robust reasoning capabilities for cross-category scenarios, we propose an iterative data constructor. This constructor encompasses diverse scenarios, including intra-category try-on, any-to-dress transformations (replacing any garment category with a dress), and dress-to-any transformations (replacing a dress with another garment category). Utilizing the generated dataset, we introduce a tri-zone priors generator that intelligently predicts the try-on, reconstruction, and imagination zones by analyzing how the input garment is expected to align with the model image. Guided by these tri-zone priors, our proposed method, CrossVTON, achieves state-of-the-art performance, surpassing existing baselines in both qualitative and quantitative evaluations. Notably, it demonstrates superior capability in handling cross-category virtual try-on, meeting the complex demands of real-world applications.

This paper presents TransSoft, a novel soft robotic hand with a reconfigurable design for grasping objects of varying properties. While recent soft robotic hands have improved grasping capabilities, they often struggle with a limited range of manipulable object categories and tasks due to hardware constraints. TransSoft addresses these limitations with a scalable, low-cost, and highly adaptable structure that significantly expands the diversity of graspable objects and executable tasks. Unlike previous designs, TransSoft features a unique kinematic structure that enhances radial reconfigurability, allowing it to adjust grasping strategies dynamically based on object size, shape, and material properties. The hand is cost-effective, built from off-the-shelf components in three hours for just $200. We evaluated TransSoft through extensive real-world grasping experiments, and the results demonstrate its superior adaptability and grasping performance. Supplementary materials, including design details and experiment results, are available on our project website†.

Sequentially grasping multiple objects with multi-fingered hands is common in daily life, where humans can fully leverage the dexterity of their hands to enclose multiple objects. However, the diversity of object geometries and the complex contact interactions required for high-DOF hands to grasp one object while enclosing another make sequential multi-object grasping challenging for robots. In this paper, we propose SeqMultiGrasp, a system for sequentially grasping objects with a four-fingered Allegro Hand. We focus on sequentially grasping two objects, ensuring that the hand fully encloses one object before lifting it and then grasps the second object without dropping the first. Our system first synthesizes single-object grasp candidates, where each grasp is constrained to use only a subset of the hand’s links. These grasps are then validated in a physics simulator to ensure stability and feasibility. Next, we merge the validated single-object grasp poses to construct multi-object grasp configurations. For real-world deployment, we train a diffusion model conditioned on point clouds to propose grasp poses, followed by a heuristic-based execution strategy. We test our system using 8 × 8 object combinations in simulation and 6 × 3 object combinations in real. Our diffusion-based grasp model obtains an average success rate of 65.8% over 1,600 simulation trials and 56.7% over 90 real-world trials, suggesting that it is a promising approach for sequential multi-object grasping with multi-fingered hands. Supplementary material is available on our project website: https://hesic73.github.io/SeqMultiGrasp.

Accurate 6D pose estimation is key for robotic manipulation, enabling precise object localization for tasks like grasping. We present RAG-6DPose, a retrieval-augmented approach that leverages 3D CAD models as a knowledge base by integrating both visual and geometric cues. Our RAG-6DPose roughly contains three stages: 1) Building a Multi-Modal CAD Knowledge Base by extracting 2D visual features from multi-view CAD rendered images and also attaching 3D points; 2) Retrieving relevant CAD features from the knowledge base based on the current query image via our ReSPC module; and 3) Incorporating retrieved CAD information to refine pose predictions via retrieval-augmented decoding. Experimental results on standard benchmarks and real-world robotic tasks demonstrate the effectiveness and robustness of our approach, particularly in handling occlusions and novel viewpoints. Supplementary material is available on our project website: https://sressers.github.io/RAG-6DPose.

Visual language navigation (VLN) poses challenges in guiding agents through unseen environments based on natural language instructions. Existing methods either rely on imitation learning, for which training across various complex scenarios remains challenging, or leverage large visual language models (LVLMs) for zero-shot object recognition and expert iterative reasoning for improved scene understanding. Although LVLMs enhance target detection generalization, current VLN methods lack robustness in terms of environmental generalization and struggle with multi-step, coarsely directed instructions. Addressing these challenges, we introduce Ali-UI, a novel vision-language navigation approach that enables agents to navigate from random starting points in unvisited scenes and handle complex multi-step instructions. Specifically, we incorporate continuously accumulating global grid maps and local semantic maps as scene memory by employing frontier-based exploration. Multi-step coarsely directed commands are broken down with the assistance of LLaVA and matched with the scene, considering temporal and spatial alignment. Panoramic data are saved in topological form and queried by instruction segments for sequential navigation. Extensive experiments carried out in simulated environments demonstrate that Ali-UI outperforms existing state-of-the-art methods in terms of flexible human instructions and scene generalization, with the success rate improved by 23.37% and the SPL increased by 19.27% in R2R dataset.

Open-vocabulary 3D visual grounding aims to localize target objects based on free-form language queries, which is crucial for embodied AI applications such as autonomous navigation, robotics, and augmented reality. Learning 3D language fields through neural representations enables accurate understanding of 3D scenes from limited viewpoints and facilitates the localization of target objects in complex environments. However, existing language field methods struggle to accurately localize instances using spatial relations in language queries, such as ''the book on the chair.'' This limitation mainly arises from inadequate reasoning about spatial relations in both language queries and 3D scenes. In this work, we propose SpatialReasoner, a novel neural representation-based framework with large language model (LLM)-driven spatial reasoning that constructs a visual properties-enhanced hierarchical feature field for open-vocabulary 3D visual grounding. To enable spatial reasoning in language queries, SpatialReasoner fine-tunes an LLM to capture spatial relations and explicitly infer instructions for the target, anchor, and spatial relation. To enable spatial reasoning in 3D scenes, SpatialReasoner incorporates visual properties (opacity and color) to construct a hierarchical feature field. This field represents language and instance features using distilled CLIP features and masks extracted via the Segment Anything Model (SAM). The field is then queried using the inferred instructions in a hierarchical manner to localize the target 3D instance based on the spatial relation in the language query. Notably, SpatialReasoner is not limited to a specific 3D neural representation; it serves as a framework adaptable to various representations, such as Neural Radiance Fields (NeRF) or 3D Gaussian Splatting (3DGS). Extensive experiments show that our framework can be seamlessly integrated into different neural representations, outperforming baseline models in 3D visual grounding while empowering their spatial reasoning capability. Project Homepage:ZhenyangLiu.github.io/SpatialReasoner.

Recent advances in Talking Head Generation (THG) have achieved impressive lip synchronization and visual quality through diffusion models; yet existing methods struggle to generate emotionally expressive portraits while preserving speaker identity. We identify three critical limitations in current emotional talking head generation: insufficient utilization of audio's inherent emotional cues, identity leakage in emotion representations, and isolated learning of emotion correlations. To address these challenges, we propose a novel framework dubbed as DICE-Talk, following the idea of disentangling identity with emotion, and then cooperating emotions with similar characteristics. First, we develop a disentangled emotion embedder that jointly models audio-visual emotional cues through cross-modal attention, representing emotions as identity-agnostic Gaussian distributions. Second, we introduce a correlation-enhanced emotion conditioning module with learnable emotion banks that explicitly capture inter-emotion relationships through vector quantization and attention-based feature aggregation. Third, we design an emotion discrimination objective that enforces affective consistency during the diffusion process through latent-space classification. Extensive experiments on MEAD and HDTF datasets demonstrate our method's superiority, outperforming state-of-the-art approaches in emotion accuracy while maintaining competitive lip-sync performance. Qualitative results and user studies further confirm our method's ability to generate identity-preserving portraits with rich, correlated emotional expressions that naturally adapt to unseen identities.

In daily life, people often move through spaces to find objects that meet their needs, posing a key challenge in embodied AI. Traditional Demand-Driven Navigation (DDN) handles one need at a time but does not reflect the complexity of real-world tasks involving multiple needs and personal choices. To bridge this gap, we introduce Task-Preferenced Multi-Demand-Driven Navigation (TP-MDDN), a new benchmark for long-horizon navigation involving multiple sub-demands with explicit task preferences. To solve TP-MDDN, we propose AWMSystem, an autonomous decision-making system composed of three key modules: BreakLLM (instruction decomposition), LocateLLM (goal selection), and StatusMLLM (task monitoring). For spatial memory, we design MASMap, which combines 3D point cloud accumulation with 2D semantic mapping for accurate and efficient environmental understanding. Our Dual-Tempo action generation framework integrates zero-shot planning with policy-based fine control, and is further supported by an Adaptive Error Corrector that handles failure cases in real time. Experiments demonstrate that our approach outperforms state-of-the-art baselines in both perception accuracy and navigation robustness.

Cross-Domain Few-Shot Object Detection (CD-FSOD) aims to detect novel objects with only a handful of labeled samples from previously unseen domains. While data augmentation and generative methods have shown promise in few-shot learning, their effectiveness for CD-FSOD remains unclear due to the need for both visual realism and domain alignment. Existing strategies, such as copy-paste augmentation and text-to-image generation, often fail to preserve the correct object category or produce backgrounds coherent with the target domain, making them non-trivial to apply directly to CD-FSOD. To address these challenges, we propose Domain-RAG, a training-free, retrieval-guided compositional image generation framework tailored for CD-FSOD. Domain-RAG consists of three stages: domain-aware background retrieval, domain-guided background generation, and foreground-background composition. Specifically, the input image is first decomposed into foreground and background regions. We then retrieve semantically and stylistically similar images to guide a generative model in synthesizing a new background, conditioned on both the original and retrieved contexts. Finally, the preserved foreground is composed with the newly generated domain-aligned background to form the generated image. Without requiring any additional supervision or training, Domain-RAG produces high-quality, domain-consistent samples across diverse tasks, including CD-FSOD, remote sensing FSOD, and camouflaged FSOD. Extensive experiments show consistent improvements over strong baselines and establish new state-of-the-art results. Codes will be released upon acceptance.The source code and instructions are available at https://github.com/LiYu0524/Domain-RAG.

Temporally consistent depth estimation from stereo video is critical for real-world applications such as augmented reality, where inconsistent depth estimation disrupts the immersion of users. Despite its importance, this task remains challenging due to the difficulty in modeling long-term temporal consistency in a computationally efficient manner. Previous methods attempt to address this by aggregating spatio-temporal information but face a fundamental trade-off: limited temporal modeling provides only modest gains, whereas capturing long-range dependencies significantly increases computational cost. To address this limitation, we introduce a memory buffer for modeling long-range spatio-temporal consistency while achieving efficient dynamic stereo matching. Inspired by the two-stage decision-making process in humans, we propose a Pick-and-Play Memory (PPM) construction module for dynamic Stereo matching, dubbed as PPMStereo. PPM consists of a pick process that identifies the most relevant frames and a play process that weights the selected frames adaptively for spatio-temporal aggregation. This two-stage collaborative process maintains a compact yet highly informative memory buffer while achieving temporally consistent information aggregation. Extensive experiments validate the effectiveness of PPMStereo, demonstrating state-of-the-art performance in both accuracy and temporal consistency.Codes are available at \textcolor{blue}{https://github.com/cocowy1/PPMStereo}.

Visual In-Context Learning (VICL) has emerged as a prominent approach for adapting visual foundation models to novel tasks, by effectively exploiting contextual information embedded in in-context examples, which can be formulated as a global ranking problem of potential candidates. Current VICL methods, such as Partial2Global and VPR, are grounded in the similarity-priority assumption that images more visually similar to a query image serve as better in-context examples. This foundational assumption, while intuitive, lacks sufficient justification for its efficacy in selecting optimal in-context examples. Furthermore, Partial2Global constructs its global ranking from a series of randomly sampled pairwise preference predictions. Such a reliance on random sampling can lead to incomplete coverage and redundant samplings of comparisons, thus further adversely impacting the final global ranking. To address these issues, this paper introduces an enhanced variant of Partial2Global designed for reliable and holistic selection of in-context examples in VICL. Our proposed method, dubbed RH-Partial2Global, leverages a jackknife conformal prediction-guided strategy to construct reliable alternative sets and a covering design-based sampling approach to ensure comprehensive and uniform coverage of pairwise preferences. Extensive experiments demonstrate that RH-Partial2Global achieves excellent performance and outperforms Partial2Global across diverse visual tasks.

Camera and human motion controls have been extensively studied for video generation, but existing approaches typically address them separately, suffering from limited data with high-quality annotations for both aspects. To overcome this, we present Uni3C, a unified 3D-enhanced framework for precise control of both camera and human motion in video generation. Uni3C includes two key contributions. First, we propose a plug-and-play control module trained with a frozen video generative backbone, PCDController, which utilizes unprojected point clouds from monocular depth to achieve accurate camera control. By leveraging the strong 3D priors of point clouds and the powerful capacities of video foundational models, PCDController shows impressive generalization, performing well regardless of whether the inference backbone is frozen or fine-tuned. This flexibility enables different modules of Uni3C to be trained in specific domains, i.e., either camera control or human motion control, reducing the dependency on jointly annotated data. Second, we propose a jointly aligned 3D world guidance for the inference phase that seamlessly integrates both scenic point clouds and SMPL-X characters to unify the control signals for camera and human motion, respectively. Extensive experiments confirm that PCDController enjoys strong robustness in driving camera motion for fine-tuned backbones of video generation. Uni3C substantially outperforms competitors in both camera controllability and human motion quality. Additionally, we collect tailored validation sets featuring challenging camera movements and human actions to validate the effectiveness of our method. Codes are released at https://github.com/alibaba-damo-academy/Uni3C.

Reconstructing 3D visuals from functional Magnetic Resonance Imaging (fMRI) data, introduced as Recon3DMind, is of significant interest to both cognitive neuroscience and computer vision. To advance this task, we present the fMRI-3D dataset, which includes data from 15 participants and showcases a total of 4,768 3D objects. The dataset consists of two components: fMRI-Shape, previously introduced and available at https://huggingface.co/datasets/Fudan-fMRI/fMRI-Shape, and fMRI-Objaverse, proposed in this paper and available at https://huggingface.co/datasets/Fudan-fMRI/fMRI-Objaverse. fMRI-Objaverse includes data from 5 subjects, 4 of whom are also part of the core set in fMRI-Shape. Each subject views 3,142 3D objects across 117 categories, all accompanied by text captions. This significantly enhances the diversity and potential applications of the dataset. Moreover, we propose MinD-3D++, a novel framework for decoding textured 3D visual information from fMRI signals. The framework evaluates the feasibility of not only reconstructing 3D objects from the human mind but also generating, for the first time, 3D textured meshes with detailed textures from fMRI data. We establish new benchmarks by designing metrics at the semantic, structural, and textured levels to evaluate model performance. Furthermore, we assess the model's effectiveness in out-of-distribution settings and analyze the attribution of the proposed 3D pari fMRI dataset in visual regions of interest (ROIs) in fMRI signals. Our experiments demonstrate that MinD-3D++ not only reconstructs 3D objects with high semantic and spatial accuracy but also provides deeper insights into how the human brain processes 3D visual information.

Deep learning models have emerged as strong and efficient tools that can be applied to a broad spectrum of complex learning problems and many real-world applications. However, more and more works show that deep models are vulnerable to adversarial examples. Compared to vanilla attack settings, this paper advocates a more practical setting of data-free black-box attack, for which the attackers can completely not access the structures and parameters of the target model, as well as the intermediate features and any training data associated with the model. To tackle this task, previous methods generate transferable adversarial examples from a transparent substitute model to the target model. However, we found that these works have the limitations of taking static substitute model structure for different targets, only using hard synthesized examples once, and still relying on data statistics of the target model. This may potentially harm the performance of attacking the target model. To this end, we propose a novel Dynamic Routing and Knowledge Re-Learning framework (DraKe) to effectively learn a dynamic substitute model from the target model. Specifically, given synthesized training samples, a dynamic substitute structure learning strategy is proposed to adaptively generate optimal substitute model structure via a policy network according to different target models and tasks. To facilitate the substitute training, we present a graph-based structure information learning to capture the structural knowledge learned from the target model. For the inherent limitation that online data generation can only be learned once, a dynamic knowledge re-learning strategy is proposed to adjust the weights of optimization objectives and re-learn hard samples. Extensive experiments on four public image classification datasets and one face recognition benchmark are conducted to evaluate the efficacy of our Drake. We can obtain significant improvement compared with state-of-the-art competitors. More importantly, our DraKe consistently achieves attack superiority for different target models (e.g., residual networks, and vision transformers), showing great potential for complex real-world applications.

Facial Appearance Editing (FAE) focuses on modifying physical attributes like pose, expression, and lighting in facial images while preserving identity and background, which is crucial in photography. Despite significant progress, current research faces three main challenges: low generation fidelity, poor attribute preservation, and inefficient inference. To address these issues, this paper introduces MagicFace, a slot-driven, high-fidelity, one-shot FAE framework. Particularly, MagicFace employs Space-sensitive Physical Customization (SPC) for accurate query attribute transfer, utilizing rendering textures from the 3D Morphable Model (3DMM) to ensure fidelity and generalization. To preserve source attributes, we propose the Region-responsive Semantic Composition (RSC) module, guided by slot attention to learn and preserve decoupled source features. This approach can successfully maintain identity and reduces artifacts related to non-facial attributes such as hair, clothes, and background. Additionally, we introduce a consistency regularization technique to enhance editing controllability by leveraging prior knowledge from attention matrices in the diffusion model. Extensive experiments demonstrate that MagicFace achieves state-of-the-art performance in FAE task, outperforming existing methods.

With the continuous expansion of intelligent surveillance networks, lifelong person re-identification (LReID) has received widespread attention, pursuing the need of self-evolution across different domains. However, existing LReID studies accumulate knowledge with the assumption that people would not change their clothes. In this paper, we propose a more practical task, namely lifelong person re-identification with hybrid clothing states (LReID-Hybrid), which takes a series of cloth-changing and same-cloth domains into account during lifelong learning. To tackle the challenges of knowledge granularity mismatch and knowledge presentation mismatch in LReID-Hybrid, we take advantage of the consistency and generalization capabilities of the text space, and propose a novel framework, dubbed Teata, to effectively align, transfer, and accumulate knowledge in an "image-text-image" closed loop. Concretely, to achieve effective knowledge transfer, we design a Structured Semantic Prompt (SSP) learning to decompose the text prompt into several structured pairs to distill knowledge from the image space with a unified granularity of text description. Then, we introduce a Knowledge Adaptation and Projection (KAP) strategy, which tunes text knowledge via a slow-paced learner to adapt to different tasks without catastrophic forgetting. Extensive experiments demonstrate the superiority of our proposed Teata for LReID-Hybrid as well as on conventional LReID benchmarks over advanced methods.

Existing gait recognition benchmarks mostly include minor clothing variations in the laboratory environments, but lack persistent changes in appearance over time and space. In this paper, we propose the first in-the-wild benchmark CCGait for cloth-changing gait recognition, which incorporates diverse clothing changes, indoor and outdoor scenes, and multi-modal statistics over 92 days. To further address the coupling effect of clothing and viewpoint variations, we propose a hybrid approach HybridGait that exploits both temporal dynamics and the projected 2D information of 3D human meshes. Specifically, we introduce a Canonical Alignment Spatial-Temporal Transformer (CA-STT) module to encode human joint position-aware features, and fully exploit 3D dense priors via a Silhouette-guided Deformation with 3D-2D Appearance Projection (SilD) strategy. Our contributions are twofold: we provide a challenging benchmark CCGait that captures realistic appearance changes over expanded time and space, and we propose a hybrid framework HybridGait that outperforms prior works on CCGait and Gait3D benchmarks. Our project page is available at https://github.com/HCVLab/HybridGait.

This paper introduces LeftRefill, an innovative approach to efficiently harness large Text-to-Image (T2I) diffusion models for reference-guided image synthesis. As the name implies, LeftRefill horizontally stitches reference and target views together as a whole input. The reference image occupies the left side, while the target canvas is positioned on the right. Then, LeftRefill paints the rightside target canvas based on the left-side reference and specific task instructions. Such a task formulation shares some similarities with contextual inpainting, akin to the actions of a human painter. This novel formulation efficiently learns both structural and textured correspondence between reference and target without other image encoders or adapters. We inject task and view information through cross-attention modules in T2I models, and further exhibit multi-view reference ability via the re-arranged self-attention modules. These enable LeftRefill to perform consistent generation as a generalized model without requiring testtime fine-tuning or model modifications. Thus, LeftRefill can be seen as a simple yet unified framework to address reference-guided synthesis. As an exemplar, we leverage LeftRefill to address two different challenges: reference-guided inpainting and novel view synthesis, based on the pre-trained StableDiffusion. Codes&models are released at https://github.com/ewrfcas/LeftRefill.

Optical flow is a classical task that is important to the vision community. Classical optical flow estimation uses two frames as input, whilst some recent methods consider multiple frames to explicitly model long-range information. The former ones limit their ability to fully leverage temporal coherence along the video sequence; and the latter ones incur heavy computational overhead, typically not possible for real-time flow estimation. Some multi-frame-based approaches even necessitate unseen future frames for current estimation, compromising real-time applicability in safety-critical scenarios. To this end, we present MemFlow, a real-time method for optical flow estimation and prediction with memory. Our method enables memory readout and update modules for aggregating historical motion information in real-time. Furthermore, we integrate resolution-adaptive re-scaling to accommodate diverse video resolutions. Besides, our approach seamlessly extends to the future prediction of optical flow based on past observations. Leveraging effective historical motion aggregation, our method outperforms VideoFlow with fewer parameters and faster inference speed on Sintel and KITTI-15 datasets in terms of generalization performance. At the time of submission, MemFlow also leads in performance on the 1080p Spring dataset. Codes and models will be available at: https://dqiaole.github.io/MemFlow/.

Object-centric learning (OCL) extracts the representation of objects with slots, offering an exceptional blend of flexibility and interpretability for abstracting low-level perceptual features. A widely adopted method within OCL is slot attention, which utilizes attention mechanisms to iteratively refine slot representations. However, a major draw-back of most object-centric models, including slot attention, is their reliance on predefining the number of slots. This not only necessitates prior knowledge of the dataset but also overlooks the inherent variability in the number of objects present in each instance. To overcome this fundamental limitation, we present a novel complexity-aware object auto-encoder framework. Within this framework, we introduce an adaptive slot attention (AdaSlot) mecha-nism that dynamically determines the optimal number of slots based on the content of the data. This is achieved by proposing a discrete slot sampling module that is responsible for selecting an appropriate number of slots from a candidate list. Furthermore, we introduce a masked slot decoder that suppresses unselected slots during the decoding process. Our framework, tested extensively on object discovery tasks with various datasets, shows performance matching or exceeding top fixed-slot models. Moreover, our analysis substantiates that our method exhibits the capability to dynamically adapt the slot number according to each instance's complexity, offering the potential for further exploration in slot attention research. Project will be available at https://kfan21.github.io/AdaSlot/

Out-of-Distribution (OOD) detection aims to address the excessive confidence prediction by neural networks by triggering an alert when the input sample deviates significantly from the training distribution (in-distribution), indicating that the output may not be reliable. Current OOD detection approaches explore all kinds of cues to identify OOD data, such as finding irregular patterns in the feature space, logit space, gradient space, or the raw image space. Surprisingly, we observe a linear trend between the OOD score produced by current OOD detection algorithms and the network features on several datasets. We conduct a thorough investigation, theoretically and empirically, to analyze and understand the meaning of such a linear trend in OOD detection. This paper proposes a Robust Test-time Linear method (RTL) to utilize such linear trends like a ‘free lunch’ when we have a batch of data to perform OOD detection. By using a simple linear regression as a test time adaptation, we can make a more precise OOD prediction. We further propose an online variant of the proposed method, which achieves promising performance and is more practical for real applications. Theoretical analysis is given to prove the effectiveness of our methods. Extensive experiments on several OOD datasets show the efficacy of RTL for OOD detection tasks, significantly improving the results of base OOD detectors. Project will be available at https://github.com/kfan21/RTL.

Pixel2Mesh (P2M) is a classical approach for reconstructing 3D shapes from a single color image through coarse-to-fine mesh deformation. Although P2M is capable of generating plausible global shapes, its Graph Convolution Network (GCN) often produces overly smooth results, causing the loss of fine-grained geometry details. Moreover, P2M generates non-credible features for occluded regions and struggles with the domain gap from synthetic data to real-world images, which is a common challenge for single-view 3D reconstruction methods. To address these challenges, we propose a novel Transformer-boosted architecture, named T-Pixel2Mesh, inspired by the coarse-to-fine approach of P2M. Specifically, we use a global Transformer to control the holistic shape and a local Transformer to progressively refine the local geometry details with graph-based point upsampling. To enhance real-world reconstruction, we present the simple yet effective Linear Scale Search (LSS), which serves as prompt tuning during the input preprocessing. Our experiments on ShapeNet demonstrate state-of-the-art performance, while results on real-world data show the generalization capability.

Recent advancements in learning-based Multi-View Stereo (MVS) methods have prominently featured transformer-based models with attention mechanisms. However, existing approaches have not thoroughly investigated the profound influence of transformers on different MVS modules, resulting in limited depth estimation capabilities. In this paper, we introduce MVSFormer++, a method that prudently maximizes the inherent characteristics of attention to enhance various components of the MVS pipeline. Formally, our approach involves infusing cross-view information into the pre-trained DINOv2 model to facilitate MVS learning. Furthermore, we employ different attention mechanisms for the feature encoder and cost volume regularization, focusing on feature and spatial aggregations respectively. Additionally, we uncover that some design details would substantially impact the performance of transformer modules in MVS, including normalized 3D positional encoding, adaptive attention scaling, and the position of layer normalization. Comprehensive experiments on DTU, Tanks-and-Temples, BlendedMVS, and ETH3D validate the effectiveness of the proposed method. Notably, MVSFormer++ achieves state-of-the-art performance on the challenging DTU and Tanks-and-Temples benchmarks. Codes and models are available at https://github.com/maybeLx/MVSFormerPlusPlus.

Proximal causal learning is a powerful framework for identifying the causal effect under the existence of unmeasured confounders. Within this framework, the doubly robust (DR) estimator was derived and has shown its effectiveness in estimation, especially when the model assumption is violated. However, the current form of the DR estimator is restricted to binary treatments, while the treatments can be continuous in many real-world applications. The primary obstacle to continuous treatments resides in the delta function present in the original DR estimator, making it infeasible in causal effect estimation and introducing a heavy computational burden in nuisance function estimation. To address these challenges, we propose a kernel-based DR estimator that can well handle continuous treatments for proximal causal learning. Equipped with its smoothness, we show that its oracle form is a consistent approximation of the influence function. Further, we propose a new approach to efficiently solve the nuisance functions. We then provide a comprehensive convergence analysis in terms of the mean square error. We demonstrate the utility of our estimator on synthetic datasets and real-world applications.

This paper investigates the task of the open-ended interactive robotic manipulation on table-top scenarios. While recent Large Language Models (LLMs) enhance robots' comprehension of user instructions, their lack of visual grounding constrains their ability to physically interact with the environment. This is because the robot needs to locate the target object for manipulation within the physical workspace. To this end, we introduce an interactive robotic manipulation framework called Polaris, which integrates perception and interaction by utilizing GPT-4 alongside grounded vision models. For precise manipulation, it is essential that such grounded vision models produce detailed object pose for the target object, rather than merely identifying pixels belonging to them in the image. Consequently, we propose a novel Synthetic-to-Real (Syn2Real) pose estimation pipeline. This pipeline utilizes rendered synthetic data for training and is then transferred to real-world manipulation tasks. The real-world performance demonstrates the efficacy of our proposed pipeline and underscores its potential for extension to more general categories. Moreover, real-robot experiments have showcased the impressive performance of our framework in grasping and executing multiple manipulation tasks. This indicates its potential to generalize to scenarios beyond the tabletop. More information and video results are available here: https://star-uu-wang.github.io/Polaris/.

This paper addresses the challenge of perceiving complete object shapes through visual perception. While prior studies have demonstrated encouraging outcomes in segmenting the visible parts of objects within a scene, amodal segmentation, in particular, has the potential to allow robots to infer the occluded parts of objects. To this end, this paper introduces a new framework that explores amodal segmentation for robotic grasping in cluttered scenes, thus greatly enhancing robotic grasping abilities. Initially, we use a conventional segmentation algorithm to detect the visible segments of the target object, which provides shape priors for completing the full object mask. Particularly, to explore how to utilize semantic features from RGB images and geometric information from depth images, we propose a Linear-fusion Attention-guided Convolutional Network (LAC-Net). LAC-Net utilizes the linear-fusion strategy to effectively fuse this cross-modal data, and then uses the prior visible mask as attention map to guide the network to focus on target feature locations for further complete mask recovery. Using the amodal mask of the target object provides advantages in selecting more accurate and robust grasp points compared to relying solely on the visible segments. The results on different datasets show that our method achieves state-of-the-art performance. Furthermore, the robot experiments validate the feasibility and robustness of this method in the real world. Our code and demonstrations are available on the project page: https://jrryzh.github.io/LAC-Net.

Visual In-Context Learning (VICL) is a prevailing way to transfer visual foundation models to new tasks by leveraging contextual information contained in in-context examples to enhance learning and prediction of query sample. The fundamental problem in VICL is how to select the best prompt to activate its power as much as possible, which is equivalent to the ranking problem to test the in-context behavior of each candidate in the alternative set and select the best one. To utilize more appropriate ranking metric and leverage more comprehensive information among the alternative set, we propose a novel in-context example selection framework to approximately identify the global optimal prompt, i.e. choosing the best performing in-context examples from all alternatives for each query sample. Our method, dubbed Partial2Global, adopts a transformer-based list-wise ranker to provide a more comprehensive comparison within several alternatives, and a consistency-aware ranking aggregator to generate globally consistent ranking. The effectiveness of Partial2Global is validated through experiments on foreground segmentation, single object detection and image colorization, demonstrating that Partial2Global selects consistently better in-context examples compared with other methods, and thus establish the new state-of-the-arts.

Novel View Synthesis (NVS) and 3D generation have recently achieved prominent improvements. However, these works mainly focus on confined categories or synthetic 3D assets, which are discouraged from generalizing to challenging in-the-wild scenes and fail to be employed with 2D synthesis directly. Moreover, these methods heavily depended on camera poses, limiting their real-world applications. To overcome these issues, we propose MVInpainter, re-formulating the 3D editing as a multi-view 2D inpainting task. Specifically, MVInpainter partially inpaints multi-view images with the reference guidance rather than intractably generating an entirely novel view from scratch, which largely simplifies the difficulty of in-the-wild NVS and leverages unmasked clues instead of explicit pose conditions. To ensure cross-view consistency, MVInpainter is enhanced by video priors from motion components and appearance guidance from concatenated reference key\&value attention. Furthermore, MVInpainter incorporates slot attention to aggregate high-level optical flow features from unmasked regions to control the camera movement with pose-free training and inference. Sufficient scene-level experiments on both object-centric and forward-facing datasets verify the effectiveness of MVInpainter, including diverse tasks, such as multi-view object removal, synthesis, insertion, and replacement. The project page is https://ewrfcas.github.io/MVInpainter/.

Visual-Language Alignment (VLA) has gained a lot of attention since CLIP's groundbreaking work. Although CLIP performs well, the typical direct latent feature alignment lacks clarity in its representation and similarity scores. On the other hand, lexical representation, a vector whose element represents the similarity between the sample and a word from the vocabulary, is a natural sparse representation and interpretable, providing exact matches for individual words. However, lexical representations are difficult to learn due to no ground-truth supervision and false-discovery issues, and thus requires complex design to train effectively. In this paper, we introduce LexVLA, a more interpretable VLA framework by learning a unified lexical representation for both modalities without complex design. We use DINOv2 as our visual model for its local-inclined features and Llama 2, a generative language model, to leverage its in-context lexical prediction ability. To avoid the false discovery, we propose an overuse penalty to refrain the lexical representation from falsely frequently activating meaningless words. We demonstrate that these two pre-trained uni-modal models can be well-aligned by fine-tuning on the modest multi-modal dataset and avoid intricate training configurations. On cross-modal retrieval benchmarks, LexVLA, trained on the CC-12M multi-modal dataset, outperforms baselines fine-tuned on larger datasets (e.g., YFCC15M) and those trained from scratch on even bigger datasets (e.g., 1.1B data, including CC-12M). We conduct extensive experiments to analyze LexVLA. Codes are available at https://github.com/Clementine24/LexVLA.

Structure from Motion (SfM) is a fundamental computer vision problem which has not been well handled by deep learning. One of the promising solutions is to apply explicit structural constraint, e.g., 3D cost volume, into the neural network. Obtaining accurate camera poses from images alone can be challenging, especially with complicated environmental factors. Existing methods usually assume accurate camera poses from GT or other methods, which is unrealistic in practice and additional sensors are needed. In this work, we design a physical driven architecture, namely DeepSFM, inspired by traditional Bundle Adjustment, which consists of two cost volume based architectures to iteratively refine depth and pose. The explicit constraints on both depth and pose, when combined with the learning components, bring merit from both traditional BA and emerging deep learning technology. To speed up the learning and inference efficiency, we apply the Gated Recurrent Units (GRUs)-based depth and pose update modules with coarse to fine cost volumes on the iterative refinements. In addition, with the extended residual depth prediction module, our model can be adapted to dynamic scenes effectively. Extensive experiments on various datasets show that our model achieves state-of-the-art performance with superior robustness against challenging inputs.

One-shot fine-grained visual recognition often suffers from the problem of having few training examples for new fine-grained classes. To alleviate this problem, off-the-shelf image generation techniques based on Generative Adversarial Networks (GANs) can potentially create additional training images. However, these GAN-generated images are often not helpful for actually improving the accuracy of one-shot fine-grained recognition. In this paper, we propose a meta-learning framework to combine generated images with original images, so that the resulting "hybrid" training images improve one-shot learning. Specifically, the generic image generator is updated by a few training instances of novel classes, and a Meta Image Reinforcing Network (MetaIRNet) is proposed to conduct one-shot fine-grained recognition as well as image reinforcement. Our experiments demonstrate consistent improvement over baselines on one-shot fine-grained image classification benchmarks. Furthermore, our analysis shows that the reinforced images have more diversity compared to the original and GAN-generated images.

A noisy training set usually leads to the degradation of the generalization and robustness of neural networks. In this article, we propose a novel theoretically guaranteed clean sample selection framework for learning with noisy labels. Specifically, we first present a Scalable Penalized Regression (SPR) method, to model the linear relation between network features and one-hot labels. In SPR, the clean data are identified by the zero mean-shift parameters solved in the regression model. We theoretically show that SPR can recover clean data under some conditions. Under general scenarios, the conditions may be no longer satisfied; and some noisy data are falsely selected as clean data. To solve this problem, we propose a data-adaptive method for Scalable Penalized Regression with Knockoff filters (Knockoffs-SPR), which is provable to control the False-Selection-Rate (FSR) in the selected clean data. To improve the efficiency, we further present a split algorithm that divides the whole training set into small pieces that can be solved in parallel to make the framework scalable to large datasets. While Knockoffs-SPR can be regarded as a sample selection module for a standard supervised training pipeline, we further combine it with a semi-supervised algorithm to exploit the support of noisy data as unlabeled data. Experimental results on several benchmark datasets and real-world noisy datasets show the effectiveness of our framework and validate the theoretical results of Knockoffs-SPR.

Cloth-changing person Re-IDentification (Re-ID) is a particularly challenging task, suffering from two limitations of inferior discriminative features and limited training samples. Existing methods mainly leverage auxiliary information to facilitate identity-relevant feature learning, including soft-biometrics features of shapes or gaits, and additional labels of clothing. However, this information may be unavailable in real-world applications. In this paper, we propose a novel FIne-grained Representation and Recomposition (FIRe2) framework to tackle both limitations without any auxiliary annotation or data. Specifically, we first design a Fine-grained Feature Mining (FFM) module to separately cluster images of each person. Images with similar so-called fine-grained attributes (e.g., clothes and viewpoints) are encouraged to cluster together. An attribute-aware classification loss is introduced to perform fine-grained learning based on cluster labels, which are not shared among different people, promoting the model to learn identity-relevant features. Furthermore, to take full advantage of fine-grained attributes, we present a Fine-grained Attribute Recomposition (FAR) module by recomposing image features with different attributes in the latent space. It significantly enhances robust feature learning. Extensive experiments demonstrate that FIRe2 can achieve state-of-the-art performance on five widely-used cloth-changing person Re-ID benchmarks. The code is available athttps://github.com/QizaoWang/FIRe-CCReID.

This paper introduces a new few-shot learning pipeline that casts relevance ranking for image retrieval as binary ranking relation classification. In comparison to image classification, ranking relation classification is sample efficient and domain agnostic. Besides, it provides a new perspective on few-shot learning and is complementary to state-of-the-art methods. The core component of our deep neural network is a simple MLP, which takes as input an image triplet encoded as the difference between two vector-Kronecker products, and outputs a binary relevance ranking order. The proposed RankMLP can be built on top of any state-of-the-art feature extractors, and our entire deep neural network is called the ranking deep neural network, or RankDNN. Meanwhile, RankDNN can be flexibly fused with other post-processing methods. During the meta test, RankDNN ranks support images according to their similarity with the query samples, and each query sample is assigned the class label of its nearest neighbor. Experiments demonstrate that RankDNN can effectively improve the performance of its baselines based on a variety of backbones and it outperforms previous state-of-the-art algorithms on multiple few-shot learning benchmarks, including miniImageNet, tieredImageNet, Caltech-UCSD Birds, and CIFAR-FS. Furthermore, experiments on the cross-domain challenge demonstrate the superior transferability of RankDNN.The code is available at: https://github.com/guoqianyu-alberta/RankDNN.

Optical flow estimation is a challenging problem remaining unsolved. Recent deep learning based optical flow models have achieved considerable success. However, these models often train networks from the scratch on standard optical flow data, which restricts their ability to robustly and geometrically match image features. In this paper, we propose a rethinking to previous optical flow estimation. We particularly leverage Geometric Image Matching (GIM) as a pre-training task for the optical flow estimation (MatchFlow) with better feature representations, as GIM shares some common challenges as optical flow estimation, and with massive labeled real-world data. Thus, matching static scenes helps to learn more fundamental feature correlations of objects and scenes with consistent displacements. Specifically, the proposed MatchFlow model employs a QuadTree attention-based network pre-trained on MegaDepth to extract coarse features for further flow regression. Extensive experiments show that our model has great cross-dataset generalization. Our method achieves 11.5% and 10.1% error reduction from GMA on Sintel clean pass and KITTI test set. At the time of anonymous submission, our MatchFlow(G) enjoys state-of-the-art performance on Sintel clean and final pass compared to published approaches with comparable computation and memory footprint. Codes and models will be released in https://github.com/DQiaole/MatchFlow.

Cross-Domain Few-Shot Learning (CD-FSL) is a recently emerging task that tackles few-shot learning across different domains. It aims at transferring prior knowledge learned on the source dataset to novel target datasets. The CD-FSL task is especially challenged by the huge domain gap between different datasets. Critically, such a domain gap actually comes from the changes of visual styles, and wave-SAN [10] empirically shows that spanning the style distribution of the source data helps alleviate this issue. However, wave-SAN simply swaps styles of two images. Such a vanilla operation makes the generated styles “real” and “easy”, which still fall into the original set of the source styles. Thus, inspired by vanilla adversarial learning, a novel model-agnostic meta Style Adversarial training (StyleAdv) method together with a novel style adversarial attack method is proposed for CD-FSL. Particularly, our style attack method synthesizes both “virtual” and “hard” adversarial styles for model training. This is achieved by perturbing the original style with the signed style gradients. By continually attacking styles and forcing the model to recognize these challenging adversarial styles, our model is gradually robust to the visual styles, thus boosting the generalization ability for novel target datasets. Besides the typical CNN-based backbone, we also employ our StyleAdv method on large-scale pre-trained vision transformer. Extensive experiments conducted on eight various target datasets show the effectiveness of our method. Whether built upon ResNet or ViT, we achieve the new state of the art for CD-FSL. Code is available at https://github.com/lovelyqian/StyleAdv-CDFSL.

Most existing point cloud upsampling methods have roughly three steps: feature extraction, feature expansion and 3D coordinate prediction. However, they usually suffer from two critical issues: (1) fixed upsampling rate after one-time training, since the feature expansion unit is customized for each upsampling rate; (2) outliers or shrinkage artifact caused by the difficulty of precisely predicting 3D coordinates or residuals of upsampled points. To adress them, we propose a new framework for accurate point cloud upsampling that supports arbitrary upsampling rates. Our method first interpolates the low-res point cloud according to a given upsampling rate. And then refine the positions of the interpolated points with an iterative optimization process, guided by a trained model estimating the difference between the current point cloud and the high-res target. Extensive quantitative and qualitative results on benchmarks and downstream tasks demonstrate that our method achieves the state-of-the-art accuracy and efficiency.

Most existing works solving Room-to-Room VLN problem only utilize RGB images and do not consider local context around candidate views, which lack sufficient visual cues about surrounding environment. Moreover, natural language contains complex semantic information thus its correlations with visual inputs are hard to model merely with cross attention. In this paper, we propose GeoVLN, which learns Geometry-enhanced visual representation based on slot attention for robust Visual-and-Language Navigation. The RGB images are compensated with the corresponding depth maps and normal maps predicted by Omnidata as visual inputs. Technically, we introduce a two-stage module that combine local slot attention and CLIP model to produce geometry-enhanced representation from such input. We employ V&L BERT to learn a cross-modal representation that incorporate both language and vision informations. Additionally, a novel multiway attention module is designed, encouraging different phrases of input instruction to exploit the most related features from visual input. Extensive experiments demonstrate the effectiveness of our newly designed modules and show the compelling performance of the proposed method.

Previous efforts in vision community are mostly made on learning good representations from visual patterns. Beyond this, this paper emphasizes the high-level ability of causal reasoning. We thus present a case study of solving the challenging task of Overall Survival (OS) time in primary liver cancers. Critically, the prediction of OS time at the early stage remains challenging, due to the unobvious image patterns of reflecting the OS. To this end, we propose a causal inference system by leveraging the intraoperative attributes and the correlation among them, as an intermediate supervision to bridge the gap between the images and the final OS. Particularly, we build a causal graph, and train the images to estimate the intraoperative attributes for final as prediction. We present a novel Causally-aware Intraoperative Imputation Model (CAWIM) that can sequentially predict each attribute using its parent nodes in the estimated causal graph. To determine the causal directions, we propose a splitting-voting mechanism, which votes for the direction for each pair of adjacent nodes among multiple predictions obtained via causal discovery from heterogeneity. The practicability and effectiveness of our method are demonstrated by the promising results on liver cancer dataset of 361 patients with long-term observations.

Learning robust local image feature matching is a fundamental low-level vision task, which has been widely explored in the past few years. Recently, detector-free local feature matchers based on transformers have shown promising results, which largely outperform pure Convolutional Neural Network (CNN) based ones. But correlations produced by transformer-based methods are spatially limited to the center of source views’ coarse patches, because of the costly attention learning. In this work, we rethink this issue and find that such matching formulation degrades pose estimation, especially for low-resolution images. So we propose a transformer-based cascade matching model – Cascade feature Matching TRansformer (CasMTR)§, to efficiently learn dense feature correlations, which allows us to choose more reliable matching pairs for the relative pose estimation. Instead of re-training a new detector, we use a simple yet effective Non-Maximum Suppression (NMS) post-process to filter keypoints through the confidence map, and largely improve the matching precision. CasMTR achieves state-of-the-art performance in indoor and outdoor pose estimation as well as visual localization. Moreover, thorough ablations show the efficacy of the proposed components and techniques.

In this paper, we show that recent advances in video representation learning and pre-trained vision-language models allow for substantial improvements in self-supervised video object localization. We propose a method that first localizes objects in videos via a slot attention approach and then assigns text to the obtained slots. The latter is achieved by an unsupervised way to read localized semantic information from the pre-trained CLIP model. The resulting video object localization is entirely unsupervised apart from the implicit annotation contained in CLIP, and it is effectively the first unsupervised approach that yields good results on regular video benchmarks.

Video amodal segmentation is a particularly challenging task in computer vision, which requires to deduce the full shape of an object from the visible parts of it. Recently, some studies have achieved promising performance by using motion flow to integrate information across frames under a self-supervised setting. However, motion flow has a clear limitation by the two factors of moving cameras and object deformation. This paper presents a rethinking to previous works. We particularly leverage the supervised signals with object-centric representation in real-world scenarios. The underlying idea is the supervision signal of the specific object and the features from different views can mutually benefit the deduction of the full mask in any specific frame. We thus propose an Efficient object-centric Representation amodal Segmentation (EoRaS). Specially, beyond solely relying on supervision signals, we design a translation module to project image features into the Bird’s-Eye View (BEV), which introduces 3D information to improve current feature quality. Furthermore, we propose a multi-view fusion layer based temporal module which is equipped with a set of object slots and interacts with features from different views by attention mechanism to fulfill sufficient object representation completion. As a result, the full mask of the object can be decoded from image features updated by object slots. Extensive experiments on both real-world and synthetic benchmarks demonstrate the superiority of our proposed method, achieving state-of-the-art performance. Our code will be released at https://github.com/kfan21/EoRaS.

Amodal object segmentation is a challenging task that involves segmenting both visible and occluded parts of an object. In this paper, we propose a novel approach, called Coarse-to-Fine Segmentation (C2F-Seg), that addresses this problem by progressively modeling the amodal segmentation. C2F-Seg initially reduces the learning space from the pixel-level image space to the vector-quantized latent space. This enables us to better handle long-range dependencies and learn a coarse-grained amodal segment from visual features and visible segments. However, this latent space lacks detailed information about the object, which makes it difficult to provide a precise segmentation directly. To address this issue, we propose a convolution refine module to inject fine-grained information and provide a more precise amodal object segmentation based on visual features and coarse-predicted segmentation. To help the studies of amodal object segmentation, we create a synthetic amodal dataset, named as MOViD-Amodal (MOViD-A), which can be used for both image and video amodal object segmentation. We extensively evaluate our model on two benchmark datasets: KINS and COCO-A. Our empirical results demonstrate the superiority of C2F-Seg. Moreover, we exhibit the potential of our approach for video amodal object segmentation tasks on FISHBOWL and our proposed MOViD-A. Project page at: https://jianxgao.github.io/C2F-Seg.

Liquid perception is critical for robotic pouring tasks. It usually requires the robust visual detection of flowing liquid. However, while recent works have shown promising results in liquid perception, they typically require labeled data for model training, a process that is both time-consuming and reliant on human labor. To this end, this paper proposes a simple yet effective framework PourIt!, to serve as a tool for robotic pouring tasks. We design a simple data collection pipeline that only needs image-level labels to reduce the reliance on tedious pixel-wise annotations. Then, a binary classification model is trained to generate Class Activation Map (CAM) that focuses on the visual difference between these two kinds of collected data, i.e., the existence of liquid drop or not. We also devise a feature contrast strategy to improve the quality of the CAM, thus entirely and tightly covering the actual liquid regions. Then, the container pose is further utilized to facilitate the 3D point cloud recovery of the detected liquid region. Finally, the liquid-to-container distance is calculated for visual closed-loop control of the physical robot. To validate the effectiveness of our proposed method, we also contribute a novel dataset for our task and name it PourIt! dataset. Extensive results on this dataset and physical Franka robot have shown the utility and effectiveness of our method in the robotic pouring tasks. Our dataset, code and pre-trained models will be available on the project page1.

Auto-Regressive (AR) models have achieved impressive results in 2D image generation by modeling joint distributions in the grid space. While this approach has been extended to the 3D domain for powerful shape generation, it still has two limitations: expensive computations on volumetric grids and ambiguous auto-regressive order along grid dimensions. To overcome these limitations, we propose the Improved Auto-regressive Model (ImAM) for 3D shape generation, which applies discrete representation learning based on a latent vector instead of volumetric grids. Our approach not only reduces computational costs but also preserves essential geometric details by learning the joint distribution in a more tractable order. Moreover, thanks to the simplicity of our model architecture, we can naturally extend it from unconditional to conditional generation by concatenating various conditioning inputs, such as point clouds, categories, images, and texts. Extensive experiments demonstrate that ImAM can synthesize diverse and faithful shapes of multiple categories, achieving state-of-the-art performance.

Unsupervised object-centric learning methods allow the partitioning of scenes into entities without additional localization information and are excellent candidates for reducing the annotation burden of multiple-object tracking (MOT) pipelines. Unfortunately, they lack two key properties: objects are often split into parts and are not consistently tracked over time. In fact, state-of-the-art models achieve pixel-level accuracy and temporal consistency by relying on supervised object detection with additional ID labels for the association through time. This paper proposes a video object-centric model for MOT. It consists of an index-merge module that adapts the object-centric slots into detection outputs and an object memory module that builds complete object prototypes to handle occlusions. Benefited from object-centric learning, we only require sparse detection labels (0%-6.25%) for object localization and feature binding. Relying on our self-supervised Expectation-Maximization-inspired loss for object association, our approach requires no ID labels. Our experiments significantly narrow the gap between the existing object-centric model and the fully supervised state-of-the-art and outperform several unsupervised trackers. Code is available at https://github.com/amazon-science/object-centric-multiple-object-tracking.

Given a single RGB image and the attribute-rich language instructions, this paper investigates the novel problem of using Fine-grained instructions for the Language guided robotic Grasping (FLarG). This problem is made challenging by learning fine-grained language descriptions to ground target objects. Recent advances have been made in visually grounding the objects simply by several coarse attributes [1]. However, these methods have poor performance as they cannot well align the multi-modal features, and do not make the best of recent powerful large pre-trained vision and language models, e.g., CLIP. To this end, this paper proposes a FLarG pipeline including stages of CLIP-guided object localization, and 6-DoF category-level object pose estimation for grasping. Specially, we first take the CLIP-based segmentation model CRIS as the backbone and propose an end-to-end DyCRIS model that uses a novel dynamic mask strategy to well fuse the multi-level language and vision features. Then, the well-trained instance segmentation backbone Mask R-CNN is adopted to further improve the predicted mask of our DyCRIS. Finally, the target object pose is inferred for the robotics grasping by using the recent 6-DoF object pose estimation method. To validate our CLIP-enhanced pipeline, we also construct a validation dataset for our FLarG task and name it RefNOCS. Extensive results on RefNOCS have shown the utility and effectiveness of our proposed method. The project homepage is available at https://sunqiang85.github.ioIFLarG/.

Recent studies of two-view correspondence learning usually establish an end-to-end network to jointly predict correspondence reliability and relative pose. We improve such a framework from two aspects. First, we propose a Local Feature Consensus (LFC) plugin block to augment the features of existing models. Given a correspondence feature, the block augments its neighboring features with mutual neighborhood consensus and aggregates them to produce an enhanced feature. As inliers obey a uniform cross-view transformation and share more consistent learned features than outliers, feature consensus strengthens inlier correlation and suppresses outlier distraction, which makes output features more discriminative for classifying inliers/outliers. Second, existing approaches supervise network training with the ground truth correspondences and essential matrix projecting one image to the other for an input image pair, without considering the information from the reverse mapping. We extend existing models to a Siamese network with a reciprocal loss that exploits the supervision of mutual projection, which considerably promotes the matching performance without introducing additional model parameters. Building upon MSA-Net [30], we implement the two proposals and experimentally achieve state-of-the-art performance on benchmark datasets.

Conventional 3D object detection approaches concentrate on bounding boxes representation learning with several parameters, i.e., localization, dimension, and orientation. Despite its popularity and universality, such a straightforward paradigm is sensitive to slight numerical deviations, especially in localization. By exploiting the property that point clouds are naturally captured on the surface of objects along with accurate location and intensity information, we introduce a new perspective that views bounding box regression as an implicit function. This leads to our proposed framework, termed Implicit Detection or ImpDet, which leverages implicit field learning for 3D object detection. Our ImpDet assigns specific values to points in different local 3D spaces, thereby high-quality boundaries can be generated by classifying points inside or outside the boundary. To solve the problem of sparsity on the object surface, we further present a simple yet efficient virtual sampling strategy to not only fill the empty region, but also learn rich semantic features to help refine the boundaries. Extensive experimental results on KITTI and Waymo benchmarks demonstrate the effectiveness and robustness of unifying implicit fields into object detection.

Image inpainting involves filling missing areas of a corrupted image. Despite impressive results have been achieved recently, restoring images with both vivid textures and reasonable structures remains a significant challenge. Previous methods have primarily addressed regular textures while disregarding holistic structures due to the limited receptive fields of Convolutional Neural Networks (CNNs). To this end, we study learning a Zero-initialized residual addition based Incremental Transformer on Structural priors (ZITS++), an improved model upon our conference work, ZITS (Dong et al. 2022). Specifically, given one corrupt image, we present the Transformer Structure Restorer (TSR) module to restore holistic structural priors at low image resolution, which are further upsampled by Simple Structure Upsampler (SSU) module to higher image resolution. To recover image texture details, we use the Fourier CNN Texture Restoration (FTR) module, which is strengthened by Fourier and large-kernel attention convolutions. Furthermore, to enhance the FTR, the upsampled structural priors from TSR are further processed by Structure Feature Encoder (SFE) and optimized with the Zero-initialized Residual Addition (ZeroRA) incrementally. Besides, a new masking positional encoding is proposed to encode the large irregular masks. Compared with ZITS, ZITS++ improves the FTR's stability and inpainting ability with several techniques. More importantly, we comprehensively explore the effects of various image priors for inpainting and investigate how to utilize them to address high-resolution image inpainting with extensive experiments. This investigation is orthogonal to most inpainting approaches and can thus significantly benefit the community.

The great success of deep neural networks is built upon their over-parameterization, which smooths the optimization landscape without degrading the generalization ability. Despite the benefits of over-parameterization, a huge amount of parameters makes deep networks cumbersome in daily life applications. On the other hand, training neural networks without over-parameterization faces many practical problems, e.g., being trapped in the local optimal. Though techniques such as pruning and distillation are developed, they are expensive in fully training a dense network as backward selection methods; and there is still a void on systematically exploring forward selection methods for learning structural sparsity in deep networks. To fill in this gap, this paper proposes a new approach based on differential inclusions of inverse scale spaces. Specifically, our method can generate a family of models from simple to complex ones along the dynamics via coupling a pair of parameters, such that over-parameterized deep models and their structural sparsity can be explored simultaneously. This kind of differential inclusion scheme has a simple discretization, dubbed Deep structure splitting Linearized Bregman Iteration (DessiLBI), whose global convergence in learning deep networks could be established under the Kurdyka-Łojasiewicz framework. Particularly, we explore several applications of DessiLBI, including finding sparse structures of networks directly via the coupled structure parameter and growing networks from simple to complex ones progressively. Experimental evidence shows that our method achieves comparable and even better performance than the competitive optimizers in exploring the sparse structure of several widely used backbones on the benchmark datasets. Remarkably, with early stopping, our method unveils "winning tickets" in early epochs: the effective sparse network structures with comparable test accuracy to fully trained over-parameterized models, that are further transferable to similar alternative tasks. Furthermore, our method is able to grow networks efficiently with adaptive filter configurations, demonstrating the good performance with much less computational cost. Codes and models can be downloaded at https://github.com/DessiLBI2020/DessiLBI.

Despite the impressive results achieved by deep learning based 3D reconstruction, the techniques of directly learning to model 4D human captures with detailed geometry have been less studied. This work presents a novel neural compositional representation for Human 4D Modeling with transformER (H4MER). Specifically, our H4MER is a compact and compositional representation for dynamic human by exploiting the human body prior from the widely used SMPL parametric model. Thus, H4MER can represent a dynamic 3D human over a temporal span with the codes of shape, initial pose, motion and auxiliaries. A simple yet effective linear motion model is proposed to provide a rough and regularized motion estimation, followed by per-frame compensation for pose and geometry details with the residual encoded in the auxiliary codes. We present a novel Transformer-based feature extractor and conditional GRU decoder to facilitate learning and improve the representation capability. Extensive experiments demonstrate our method is not only effective in recovering dynamic human with accurate motion and detailed geometry, but also amenable to various 4D human related tasks, including monocular video fitting, motion retargeting, 4D completion, and future prediction.

We study the problem of shape generation in 3D mesh representation from a small number of color images with or without camera poses. While many previous works learn to hallucinate the shape directly from priors, we adopt to further improve the shape quality by leveraging cross-view information with a graph convolution network. Instead of building a direct mapping function from images to 3D shape, our model learns to predict series of deformations to improve a coarse shape iteratively. Inspired by traditional multiple view geometry methods, our network samples nearby area around the initial mesh's vertex locations and reasons an optimal deformation using perceptual feature statistics built from multiple input images. Extensive experiments show that our model produces accurate 3D shapes that are not only visually plausible from the input perspectives, but also well aligned to arbitrary viewpoints. With the help of physically driven architecture, our model also exhibits generalization capability across different semantic categories, and the number of input images. Model analysis experiments show that our model is robust to the quality of the initial mesh and the error of camera pose, and can be combined with a differentiable renderer for test-time optimization.

The task of Few-shot learning (FSL) aims to transfer the knowledge learned from base categories with sufficient labelled data to novel categories with scarce known information. It is currently an important research question and has great practical values in the real-world applications. Despite extensive previous efforts are made on few-shot learning tasks, we emphasize that most existing methods did not take into account the distributional shift caused by sample selection bias in the FSL scenario. Such a selection bias can induce spurious correlation between the semantic causal features, that are causally and semantically related to the class label, and the other non-causal features. Critically, the former ones should be invariant across changes in distributions, highly related to the classes of interest, and thus well generalizable to novel classes, while the latter ones are not stable to changes in the distribution. To resolve this problem, we propose a novel data augmentation strategy dubbed as PatchMix that can break this spurious dependency by replacing the patch-level information and supervision of the query images with random gallery images from different classes from the query ones. We theoretically show that such an augmentation mechanism, different from existing ones, is able to identify the causal features. To further make these features to be discriminative enough for classification, we propose Correlation-guided Reconstruction (CGR) and Hardness-Aware module for instance discrimination and easier discrimination between similar classes. Moreover, such a framework can be adapted to the unsupervised FSL scenario. The utility of our method is demonstrated on the state-of-the-art results consistently achieved on several benchmarks including miniImageNet, tieredImageNet, CIFAR-FS, CUB, Cars, Places and Plantae, in all settings of single-domain, cross-domain and unsupervised FSL. By studying the intra-variance property of learned features and visualizing the learned features, we further quantitatively and qualitatively show that such a promising result is due to the effectiveness in learning causal features.

The generic object detection (GOD) task has been successfully tackled by recent deep neural networks, trained by an avalanche of annotated training samples from some common classes. However, it is still non-trivial to generalize these object detectors to the novel long-tailed object classes, which have only few labeled training samples. To this end, the Few-Shot Object Detection (FSOD) has been topical recently, as it mimics the humans’ ability of learning to learn and intelligently transfers the learned generic object knowledge from the common heavy-tailed to the novel long-tailed object classes. Especially, the research in this emerging field has been flourishing in recent years with various benchmarks, backbones, and methodologies proposed. To review these FSOD works, there are several insightful FSOD survey articles [ 58 , 59 , 74 , 78 ] that systematically study and compare them as the groups of fine-tuning/transfer learning and meta-learning methods. In contrast, we review the existing FSOD algorithms from a new perspective under a new taxonomy based on their contributions, i.e., data-oriented, model-oriented, and algorithm-oriented. Thus, a comprehensive survey with performance comparison is conducted on recent achievements of FSOD. Furthermore, we also analyze the technical challenges, the merits and demerits of these methods, and envision the future directions of FSOD. Specifically, we give an overview of FSOD, including the problem definition, common datasets, and evaluation protocols. The taxonomy is then proposed that groups FSOD methods into three types. Following this taxonomy, we provide a systematic review of the advances in FSOD. Finally, further discussions on performance, challenges, and future directions are presented.

Three-dimensional (3D) human-like body reconstruction via a single RGB image has attracted significant research attention recently. Most of the existing methods rely on the Skinned Multi-Person Linear model and thus can only predict unified human bodies. Moreover, meshes reconstructed by current methods sometimes perform well from a canonical view but not from other views, as the reconstruction process is commonly supervised by only a single view. To address these limitations, this article proposes a multi-view shape generation network for a 3D human-like body. Particularly, we propose a coarse-to-fine learning model that gradually deforms a template body toward the ground truth body. Our model utilizes the information of multi-view renderings and corresponding 3D vertex transformation as supervision. Such supervision will help to generate 3D bodies well aligned to all views. To accurately operate mesh deformation, a graph convolutional network structure is introduced to support the shape generation from 3D vertex representation. Additionally, a graph up-pooling operation is designed over the intermediate representations of the graph convolutional network, and thus our model can generate 3D shapes with higher resolution. Novel loss functions are employed to help optimize the whole multi-view generation model, resulting in smoother surfaces. In addition, two multi-view human body datasets are produced and contributed to the community. Extensive experiments conducted on the benchmark datasets demonstrate the efficacy of our model over the competitors.

Image inpainting has made significant advances in recent years. However, it is still challenging to recover corrupted images with both vivid textures and reasonable structures. Some specific methods only tackle regular textures while losing holistic structures due to the limited receptive fields of convolutional neural networks (CNNs). On the other hand, attention-based models can learn better long-range dependency for the structure recovery, but they are limited by the heavy computation for inference with large image sizes. To address these issues, we propose to leverage an additional structure restorer to facilitate the image inpainting incrementally. The proposed model restores holistic image structures with a powerful attention-based transformer model in a fixed low-resolution sketch space. Such a grayscale space is easy to be upsampled to larger scales to convey correct structural information. Our structure restorer can be integrated with other pretrained inpainting models efficiently with the zero-initialized residual addition. Furthermore, a masking positional encoding strategy is utilized to improve the performance with large irregular masks. Extensive experiments on various datasets validate the efficacy of our model compared with other competitors. Our codes are released in https://github.com/DQiaole/ZITS_inpainting.

Local density of point clouds is crucial for representing local details, but has been overlooked by existing point cloud compression methods. To address this, we propose a novel deep point cloud compression method that preserves local density information. Our method works in an auto-encoder fashion: the encoder downsamples the points and learns point-wise features, while the decoder upsamples the points using these features. Specifically, we propose to encode local geometry and density with three embeddings: density embedding, local position embedding and ancestor embedding. During the decoding, we explicitly predict the upsampling factor for each point, and the directions and scales of the upsampled points. To mitigate the clustered points issue in existing methods, we design a novel sub-point convolution layer, and an upsampling block with adaptive scale. Furthermore, our method can also compress point-wise attributes, such as normal. Extensive qualitative and quantitative results on SemanticKITTI and ShapeNet demonstrate that our method achieves the state-of-the-art rate-distortion trade-off.

Despite the impressive results achieved by deep learning based 3D reconstruction, the techniques of directly learning to model 4D human captures with detailed geometry have been less studied. This work presents a novel framework that can effectively learn a compact and compositional representation for dynamic human by exploiting the human body prior from the widely used SMPL parametric model. Particularly, our representation, named H4D, represents a dynamic 3D human over a temporal span with the SMPL parameters of shape and initial pose, and latent codes encoding motion and auxiliary information. A simple yet effective linear motion model is proposed to provide a rough and regularized motion estimation, followed by perframe compensation for pose and geometry details with the residual encoded in the auxiliary code. Technically, we introduce novel GRU-based architectures to facilitate learning and improve the representation capability. Extensive experiments demonstrate our method is not only efficacy in recovering dynamic human with accurate motion and detailed geometry, but also amenable to various 4D human related tasks, including motion retargeting, motion completion and future prediction.

Recent progress in few-shot learning promotes a more realistic cross-domain setting, where the source and target datasets are in different domains. Due to the domain gap and disjoint label spaces between source and target datasets, their shared knowledge is extremely limited. This encourages us to explore more information in the target domain rather than to overly elaborate training strategies on the source domain as in many existing methods. Hence, we start from a generic representation pre-trained by a cross-entropy loss and a conventional distance-based classifier, along with an image retrieval view, to employ a re-ranking process to calibrate a target distance matrix by discovering the k-reciprocal neighbours within the task. Assuming the pre-trained representation is biased towards the source, we construct a non-linear subspace to minimise task-irrelevant features therewithin while keep more transferrable discriminative information by a hyperbolic tangent transformation. The calibrated distance in this target-aware non-linear sub-space is complementary to that in the pre-trained representation. To impose such distance calibration information onto the pre-trained representation, a Kullback-Leibler divergence loss is employed to gradually guide the model towards the calibrated distance-based distribution. Extensive evaluations on eight target domains show that this target ranking calibration process can improve conventional distance-based classifiers in few-shot learning.

Given a single scene image, this paper proposes a method of Category-level 6D Object Pose and Size Estimation (COPSE) from the point cloud of the target object, without external real pose-annotated training data. Specifically, beyond the visual cues in RGB images, we rely on the shape information predominately from the depth (D) channel. The key idea is to explore the shape alignment of each instance against its corresponding category-level template shape, and the symmetric correspondence of each object category for estimating a coarse 3D object shape. Our framework deforms the point cloud of the category-level template shape to align the observed instance point cloud for implicitly representing its 3D rotation. Then we model the symmetric correspondence by predicting symmetric point cloud from the partially observed point cloud. The concatenation of the observed point cloud and symmetric one reconstructs a coarse object shape, thus facilitating object center (3D translation) and 3D size estimation. Extensive experiments on the category-level NOCS benchmark demonstrate that our lightweight model still competes with state-of-the-art approaches that require labeled real-world images. We also deploy our approach to a physical Baxter robot to perform grasping tasks on unseen but category-known instances, and the results further validate the efficacy of our proposed model. Code and pre-trained models are available on the project webpage11Project webpage. https://hetolin.github.io/SAR-Net.

Noisy training set usually leads to the degradation of generalization and robustness of neural networks. In this paper, we propose using a theoretically guaranteed noisy label detection framework to detect and remove noisy data for Learning with Noisy Labels (LNL). Specifically, we design a penalized regression to model the linear relation between network features and one-hot labels, where the noisy data are identified by the non-zero mean shift parameters solved in the regression model. To make the framework scalable to datasets that contain a large number of categories and training data, we propose a split algorithm to divide the whole training set into small pieces that can be solved by the penalized regression in parallel, leading to the Scalable Penalized Regression (SPR) framework. We provide the non-asymptotic probabilistic condition for SP R to correctly identify the noisy data. While SPR can be regarded as a sample selection module for standard supervised training pipeline, we further combine it with semi-supervised algorithm to further exploit the support of noisy data as unlabeled data. Experimental results on several benchmark datasets and real-world noisy datasets show the effectiveness of our framework. Our code and pretrained models are released at https://github.com/Yikai-Wang/SPR-LNL.

Existing text-guided image manipulation methods aim to modify the appearance of the image or to edit a few objects in a virtual or simple scenario, which is far from practical application. In this work, we study a novel task on text-guided image manipulation on the entity level in the real world. The task imposes three basic requirements, (1) to edit the entity consistent with the text descriptions, (2) to preserve the text-irrelevant regions, and (3) to merge the manipulated entity into the image naturally. To this end, we propose a new transformer-based framework based on the two-stage image synthesis method, namely ManiTrans, which can not only edit the appearance of entities but also generate new entities corresponding to the text guidance. Our framework incorporates a semantic alignment module to locate the image regions to be manipulated, and a semantic loss to help align the relationship between the vision and language. We conduct extensive experiments on the real datasets, CUB, Oxford, and COCO datasets to verify that our method can distinguish the relevant and irrelevant regions and achieve more precise and flexible manipulation compared with baseline methods.

With the wide applications of deep neural network models in various computer vision tasks, more and more works study the model vulnerability to adversarial examples. For data-free black box attack scenario, existing methods are inspired by the knowledge distillation, and thus usually train a substitute model to learn knowledge from the target model using generated data as input. However, the substitute model always has a static network structure, which limits the attack ability for various target models and tasks. In this paper, we propose a novel dynamic substitute training attack method to encourage substitute model to learn better and faster from the target model. Specifically, a dynamic substitute structure learning strategy is proposed to adaptively generate optimal substitute model structure via a dy-namic gate according to different target models and tasks. Moreover, we introduce a task-driven graph-based structure information learning constrain to improve the quality of generated training data, and facilitate the substitute model learning structural relationships from the target model multiple outputs. Extensive experiments have been conducted to verify the efficacy of the proposed attack method, which can achieve better performance compared with the state-of-the-art competitors on several datasets. Project page: https://wxwangiris.github.io/DST

This paper studies the task of One-Shot image Generation (OSG), where generation network learned on base dataset should be generalizable to synthesize images of novel categories with only one available sample per novel category. Most existing methods for feature transfer in oneshot image generation only learn reusable features implicitly on pre-training tasks. Such methods would be likely to overfit pre-training tasks. In this paper, we propose a novel model to explicitly learn and memorize reusable features that can help hallucinate novel category images. To be specific, our algorithm learns to decompose image features into the Category-Related (CR) and Category-Independent(CI) features. Our model learning to memorize class-independent CI features which are further utilized by our feature hallucination component to generate target novel category images. We validate our model on several benchmarks. Extensive experiments demonstrate that our model effectively boosts the OSG performance and can generate compelling and diverse samples.

We present ONCE-3DLanes, a real-world autonomous driving dataset with lane layout annotation in 3D space. Conventional 2D lane detection from a monocular image yields poor performance of following planning and control tasks in autonomous driving due to the case of uneven road. Predicting the 3D lane layout is thus necessary and enables effective and safe driving. However, existing 3D lane detection datasets are either unpublished or synthesized from a simulated environment, severely hampering the development of this field. In this paper, we take steps towards addressing these issues. By exploiting the explicit relationship between point clouds and image pixels, a dataset annotation pipeline is designed to automatically generate high-quality 3D lane locations from 2D lane annotations in 211K road scenes. In addition, we present an extrinsic-free, anchorfree method, called SALAD, regressing the 3D coordinates of lanes in image view without converting the feature map into the bird's-eye view (BEV). To facilitate future research on 3D lane detection, we benchmark the dataset and provide a novel evaluation metric, performing extensive experiments of both existing approaches and our proposed method. The aim of our work is to revive the interest of 3D lane detection in a real-world scenario. We believe our work can lead to the expected and unexpected innovations in both academia and industry.

This paper studies the task of sketch-guided high-fidelity portrait editing. Advanced unconditional generators, such as StyleGAN, can generate a high-quality portrait image with great diversity. In previous researches, StyleGAN has successfully been utilized for color-guided image editing through latent vector optimization. Nonetheless, passing sketch information to the generating model directly is nontrivial. To this end, we present an algorithm that addresses the problem of well controlling the generation process via differentiable guided sketches from latent space. Specifically, we re-purpose the classic operator – eXtended difference-of-Gaussians (XDoG) that derives differentiable sketches from images. We also propose a multi-scale sketch loss assisted with which can finally guide the model follow the guidance sketch to generate. Extensive experiments validate the efficacy of our model in sketch-guided editing. We show that the quality of produced images is better than that of competitors.

Visual object tracking is basically formulated as target classification and bounding box estimation. Recent anchor-free Siamese trackers rely on predicting the distances to four sides for efficient regression but fail to estimate accurate bounding box in complex scenes. We argue that these approaches lack a clear probabilistic explanation, so it is desirable to model the uncertainty and ambiguity representation of target estimation. To address this issue, this paper presents an Uncertainty-Aware Siamese Tracker (UAST) by developing a novel distribution-based regression formulation with localization uncertainty. We exploit regression vectors to directly represent the discretized probability distribution for four offsets of boxes, which is general, flexible and informative. Based on the resulting distributed representation, our method is able to provide a probabilistic value of uncertainty. Furthermore, considering the high correlation between the uncertainty and regression accuracy, we propose to learn a joint representation head of classification and localization quality for reliable tracking, which also avoids the inconsistency of classification and quality estimation between training and inference. Extensive experiments on several challenging tracking benchmarks demonstrate the effectiveness of UAST and its superiority over other Siamese trackers.

This paper studies the task of any objects grasping from the known categories by free-form language instructions. This task demands the technique in computer vision, natural language processing, and robotics. We bring these disciplines together on this open challenge, which is essential to human-robot interaction. Critically, the key challenge lies in inferring the category of objects from linguistic instructions and accurately estimating the 6-DoF information of unseen objects from the known classes. In contrast, previous works focus on inferring the pose of object candidates at the instance level. This significantly limits its applications in real-world scenarios. In this paper, we propose a language-guided 6-DoF category-level object localization model to achieve robotic grasping by comprehending human intention. To this end, we propose a novel two-stage method. Particularly, the first stage grounds the target in the RGB image through language description of names, attributes, and spatial relations of objects. The second stage extracts and segments point clouds from the cropped depth image and estimates the full 6-DoF object pose at category-level. Under such a manner, our approach can locate the specific object by following human instructions, and estimate the full 6-DoF pose of a category-known but unseen instance which is not utilized for training the model. Extensive experimental results show that our method is competitive with the state-of-the-art language-conditioned grasp method. Importantly, we deploy our approach on a physical robot to validate the usability of our framework in real-world applications. Please refer to the supplementary for the demo videos of our robot experiments.

In this paper, we are interested in the problem of generating target grasps by understanding freehand sketches. The sketch is useful for the persons who cannot formulate language and the cases where a textual description is not available on the fly. However, very few works are aware of the usability of this novel interactive way between humans and robots. To this end, we propose a method to generate a potential grasp configuration relevant to the sketch -depicted objects. Due to the inherent ambiguity of sketches with abstract details, we take the advantage of the graph by incorporating the structure of the sketch to enhance the representation ability. This graph-represented sketch is further validated to improve the generalization of the network, capable of learning the sketch-queried grasp detection by using a small collection (around 100 samples) of hand-drawn sketches. Additionally, our model is trained and tested in an end-to-end manner which is easy to be implemented in real-world applications. Experiments on the multi-object VMRD and GraspNet-1Billion datasets demonstrate the good generalization of the proposed method. The physical robot experiments confirm the utility of our method in object-cluttered scenes.

Vision-and-language navigation (VLN), a frontier study aiming to pave the way for general-purpose robots, has been a hot topic in the computer vision and natural language processing community. The VLN task requires an agent to navigate to a goal location following natural language instructions in unfamiliar environments.

Positive-Unlabeled (PU) learning aims to learn a model with rare positive samples and abundant unlabeled samples. Compared with classical binary classification, the task of PU learning is much more challenging due to the existence of many incompletely-annotated data instances. Since only part of the most confident positive samples are available and evidence is not enough to categorize the rest samples, many of these unlabeled data may also be the positive samples. Research on this topic is particularly useful and essential to many real-world tasks which demand very expensive labelling cost. For example, the recognition tasks in disease diagnosis, recommendation system and satellite image recognition may only have few positive samples that can be annotated by the experts. While this problem is receiving increasing attention, most of the efforts have been dedicated to the design of trustworthy risk estimators such as uPU and nnPU and direct knowledge distillation, e.g., Self-PU. These methods mainly omit the intrinsic hardness of some unlabeled data, which can result in sub-optimal performance as a consequence of fitting the easy noisy data and not sufficiently utilizing the hard data. In this paper, we focus on improving the commonly-used nnPU with a novel training pipeline. We highlight the intrinsic difference of hardness of samples in the dataset and the proper learning strategies for easy and hard data. By considering this fact, we propose first splitting the unlabeled dataset with an early-stop strategy. The samples that have inconsistent predictions between the temporary and base model are considered as hard samples. Then the model utilizes a noise-tolerant Jensen-Shannon divergence loss for easy data; and a dual-source consistency regularization for hard data which includes a cross-consistency between student and base model for low-level features and self-consistency for high-level features and predictions, respectively. Our method achieves much better results compared with existing methods on CIFAR10 and two medical datasets of liver cancer survival time prediction, and low blood pressure diagnosis of pregnant, individually. The experimental results validates the efficacy of our proposed method.

Recently, Cross-Domain Few-Shot Learning (CD-FSL) which aims at addressing the Few-Shot Learning (FSL) problem across different domains has attracted rising attention. The core challenge of CD-FSL lies in the domain gap between the source and novel target datasets. Though many attempts have been made for CD-FSL without any target data during model training, the huge domain gap makes it still hard for existing CD-FSL methods to achieve very satisfactory results. Alternatively, learning CD-FSL models with few labeled target domain data which is more realistic and promising is advocated in previous work. Thus, in this paper, we stick to this setting and technically contribute a novel Multi-Expert Domain Decompositional Network (ME-D2N). Concretely, to solve the data imbalance problem between the source data with sufficient examples and the auxiliary target data with limited examples, we build our model under the umbrella of multi-expert learning. Two teacher models which can be considered to be experts in their corresponding domain are first trained on the source and the auxiliary target sets, respectively. Then, the knowledge distillation technique is introduced to transfer the knowledge from two teachers to a unified student model. Taking a step further, to help our student model learn knowledge from different domain teachers simultaneously, we further present a novel domain decomposition module that learns to decompose the student model into two domain-related sub-parts. This is achieved by a novel domain-specific gate that learns to assign each filter to only one specific domain in a learnable way. Extensive experiments demonstrate the effectiveness of our method. Codes and models are available at https://github.com/lovelyqian/ME-D2N\_for\_CDFSL.

Amodal perception requires inferring the full shape of an object that is partially occluded. This task is particularly challenging on two levels: (1) it requires more information than what is contained in the instant retina or imaging sensor, (2) it is difficult to obtain enough well-annotated amodal labels for supervision. To this end, this paper develops a new framework of Self-supervised amodal Video object segmentation (SaVos). Our method efficiently leverages the visual information of video temporal sequences to infer the amodal mask of objects. The key intuition is that the occluded part of an object can be explained away if that part is visible in other frames, possibly deformed as long as the deformation can be reasonably learned. Accordingly, we derive a novel self-supervised learning paradigm that efficiently utilizes the visible object parts as the supervision to guide the training on videos. In addition to learning type prior to complete masks for known types, SaVos also learns the spatiotemporal prior, which is also useful for the amodal task and could generalize to unseen types. The proposed framework achieves the state-of-the-art performance on the synthetic amodal segmentation benchmark FISHBOWL and the real world benchmark KINS-Video-Car. Further, it lends itself well to being transferred to novel distributions using test-time adaptation, outperforming existing models even after the transfer to a new distribution.

Deep learning based models have excelled in many computer vision tasks and appear to surpass humans' performance. However, these models require an avalanche of expensive human labeled training data and many iterations to train their large number of parameters. This severely limits their scalability to the real-world long-tail distributed categories, some of which are with a large number of instances, but with only a few manually annotated. Learning from such extremely limited labeled examples is known as Few-Shot Learning (FSL). Different to prior arts that leverage meta-learning or data augmentation strategies to alleviate this extremely data-scarce problem, this paper presents a statistical approach, dubbed Instance Credibility Inference (ICI) to exploit the support of unlabeled instances for few-shot visual recognition. Typically, we repurpose the self-taught learning paradigm to predict pseudo-labels of unlabeled instances with an initial classifier trained from the few shot and then select the most confident ones to augment the training set to re-train the classifier. This is achieved by constructing a (Generalized) Linear Model (LM/GLM) with incidental parameters to model the mapping from (un-)labeled features to their (pseudo-)labels, in which the sparsity of the incidental parameters indicates the credibility of the corresponding pseudo-labeled instance. We rank the credibility of pseudo-labeled instances along the regularization path of their corresponding incidental parameters, and the most trustworthy pseudo-labeled examples are preserved as the augmented labeled instances. This process is repeated until all the unlabeled samples are included in the expanded training set. Theoretically, under the conditions of restricted eigenvalue, irrepresentability, and large error, our approach is guaranteed to collect all the correctly-predicted pseudo-labeled instances from the noisy pseudo-labeled set. Extensive experiments under two few-shot settings show the effectiveness of our approach on four widely used few-shot visual recognition benchmark datasets including miniImageNet, tieredImageNet, CIFAR-FS, and CUB. Code and models are released at https://github.com/Yikai-Wang/ICI-FSL.

The vanilla Few-shot Learning (FSL) learns to build a classifier for a new concept from one or very few target examples, with the general assumption that source and target classes are sampled from the same domain. Recently, the task of Cross-Domain Few-Shot Learning (CD-FSL) aims at tackling the FSL where there is a huge domain shift between the source and target datasets. Extensive efforts on CD-FSL have been made via either directly extending the meta-learning paradigm of vanilla FSL methods, or employing massive unlabeled target data to help learn models. In this paper, we notice that in the CD-FSL task, the few labeled target images have never been explicitly leveraged to inform the model in the training stage. However, such a labeled target example set is very important to bridge the huge domain gap. Critically, this paper advocates a more practical training scenario for CD-FSL. And our key insight is to utilize a few labeled target data to guide the learning of the CD-FSL model. Technically, we propose a novel Generalized Meta-learning based Feature-Disentangled Mixup network, namely GMeta-FDMixup. We make three key contributions of utilizing GMeta-FDMixup to address CD-FSL. Firstly, we present two mixup modules - mixup-P and mixup-M that help facilitate utilizing the unbalanced and disjoint source and target datasets. These two novel modules enable diverse image generation for training the model on the source domain. Secondly, to narrow the domain gap explicitly, we contribute a novel feature disentanglement module that learns to decouple the domain-irrelevant and domain-specific features. By stripping the domain-specific features, we alleviate the negative effects caused by the domain inductive bias. Finally, we repurpose a new contrastive learning module, dubbed ConL. ConL prevents the model from only capturing category-related features via introducing contrastive loss. Thus, the generalization ability on novel categories is improved. Extensive experimental results on two benchmarks show the superiority of our setting and the effectiveness of our method. Code and models will be released.

Few-shot learning (FSL) aims to recognize target classes by adapting the prior knowledge learned from source classes. Such knowledge usually resides in a deep embedding model for a general matching purpose of the support and query image pairs. The objective of this paper is to repurpose the contrastive learning for such matching to learn a few-shot embedding model. We make the following contributions: (i) We investigate the contrastive learning with Noise Contrastive Estimation (NCE) in a supervised manner for training a few-shot embedding model; (ii) We propose a novel contrastive training scheme dubbed infoPatch, exploiting the patch-wise relationship to substantially improve the popular infoNCE; (iii) We show that the embedding learned by the proposed infoPatch is more effective; (iv) Our model is thoroughly evaluated on few-shot recognition task; and demonstrates state-of-the-art results on miniImageNet and appealing performance on tieredImageNet, Fewshot-CIFAR100 (FC-100).

Few-shot learning (FSL), which aims to recognise new classes by adapting the learned knowledge with extremely limited few-shot (support) examples, remains an important open problem in computer vision. Most of the existing methods for feature alignment in few-shot learning only consider image-level or spatial-level alignment while omitting the channel disparity. Our insight is that these methods would lead to poor adaptation with redundant matching, and leveraging channel-wise adjustment is the key to well adapting the learned knowledge to new classes. Therefore, in this paper, we propose to learn a dynamic alignment, which can effectively highlight both query regions and channels according to different local support information. Specifically, this is achieved by first dynamically sampling the neighbourhood of the feature position conditioned on the input few shot, based on which we further predict a both position-dependent and channel-dependent Dynamic Meta-filter. The filter is used to align the query feature with position-specific and channel-specific knowledge. Moreover, we adopt Neural Ordinary Differential Equation (ODE) to enable a more accurate control of the alignment. In such a sense our model is able to better capture fine-grained semantic context of the few-shot example and thus facilitates dynamical knowledge adaptation for few-shot learning. The resulting framework establishes the new state-of-the-arts on major few-shot visual recognition benchmarks, including miniImageNet and tieredImageNet.

Learning based representation has become the key to the success of many computer vision systems. While many 3D representations have been proposed, it is still an unaddressed problem how to represent a dynamically changing 3D object. In this paper, we introduce a compositional representation for 4D captures, i.e. a deforming 3D object over a temporal span, that disentangles shape, initial state, and motion respectively. Each component is represented by a latent code via a trained encoder. To model the motion, a neural Ordinary Differential Equation (ODE) is trained to update the initial state conditioned on the learned motion code, and a decoder takes the shape code and the updated state code to reconstruct the 3D model at each time stamp. To this end, we propose an Identity Exchange Training (IET) strategy to encourage the network to learn effectively decoupling each component. Extensive experiments demonstrate that the proposed method outperforms existing state-of-the-art deep learning based methods on 4D reconstruction, and significantly improves on various tasks, including motion transfer and completion.

Temporal action localization is an important yet challenging task in video understanding. Typically, such a task aims at inferring both the action category and localization of the start and end frame for each action instance in a long, untrimmed video. While most current models achieve good results by using pre-defined anchors and numerous actionness, such methods could be bothered with both large number of outputs and heavy tuning of locations and sizes corresponding to different anchors. Instead, anchor-free methods is lighter, getting rid of redundant hyper-parameters, but gains few attention. In this paper, we propose the first purely anchor-free temporal localization method, which is both efficient and effective. Our model includes (i) an end-to-end trainable basic predictor, (ii) a saliency-based refinement module to gather more valuable boundary features for each proposal with a novel boundary pooling, and (iii) several consistency constraints to make sure our model can find the accurate boundary given arbitrary proposals. Extensive experiments show that our method beats all anchor-based and actionness-guided methods with a remarkable margin on THUMOS14, achieving state-of-the-art results, and comparable ones on ActivityNet v1.3. Code is available at https://github.com/TencentYoutuResearch/ActionDetection-AFSD.

The objective of this paper is to learn context- and depth- aware feature representation to solve the problem of monocular 3D object detection. We make following contributions: (i) rather than appealing to the complicated pseudo-LiDAR based approach, we propose a depth-conditioned dynamic message propagation (DDMP) network to effectively integrate the multi-scale depth information with the image context; (ii) this is achieved by first adaptively sampling context-aware nodes in the image context and then dynamically predicting hybrid depth-dependent filter weights and affinity matrices for propagating information; (Hi) by augmenting a center-aware depth encoding (CDE) task, our method successfully alleviates the inaccurate depth prior; (iv) we thoroughly demonstrate the effectiveness of our proposed approach and show state-of-the-art results among the monocular-based approaches on the KITTI benchmark dataset. Particularly, we rank 1stin the highly competitive KITTI monocular 3D object detection track on the submission day (November 16th, 2020). Code and models are released at https: //github.com/fudan-zvg/DDMP

Deep models have shown their vulnerability when processing adversarial samples. As for the black-box attack, without access to the architecture and weights of the attacked model, training a substitute model for adversarial attacks has attracted wide attention. Previous substitute training approaches focus on stealing the knowledge of the target model based on real training data or synthetic data, without exploring what kind of data can further improve the transferability between the substitute and target models. In this paper, we propose a novel perspective substitute training that focuses on designing the distribution of data used in the knowledge stealing process. More specifically, a diverse data generation module is proposed to synthesize large-scale data with wide distribution. And adversarial substitute training strategy is introduced to focus on the data distributed near the decision boundary. The combination of these two modules can further boost the consistency of the substitute model and target model, which greatly improves the effectiveness of adversarial attack. Extensive experiments demonstrate the efficacy of our method against state-of-the-art competitors under non-target and target at-tack settings. Detailed visualization and analysis are also provided to help understand the advantage of our method.

Most recent semantic segmentation methods adopt a fully-convolutional network (FCN) with an encoder-decoder architecture. The encoder progressively reduces the spatial resolution and learns more abstract/semantic visual concepts with larger receptive fields. Since context modeling is critical for segmentation, the latest efforts have been focused on increasing the receptive field, through either dilated/atrous convolutions or inserting attention modules. However, the encoder-decoder based FCN architecture remains unchanged. In this paper, we aim to provide an alternative perspective by treating semantic segmentation as a sequence-to-sequence prediction task. Specifically, we deploy a pure transformer (i.e., without convolution and resolution reduction) to encode an image as a sequence of patches. With the global context modeled in every layer of the transformer, this encoder can be combined with a simple decoder to provide a powerful segmentation model, termed SEgmentation TRansformer (SETR). Extensive experiments show that SETR achieves new state of the art on ADE20K (50.28% mIoU), Pascal Context (55.83% mIoU) and competitive results on Cityscapes. Particularly, we achieve the first position in the highly competitive ADE20K test server leaderboard on the day of submission.

This paper studies the task of inpainting man-made scenes. It is very challenging due to the difficulty in preserving the visual patterns of images, such as edges, lines, and junctions. Especially, most previous works are failed to restore the object/building structures for images of man-made scenes. To this end, this paper proposes learning a Sketch Tensor (ST) space for inpainting man-made scenes. Such a space is learned to restore the edges, lines, and junctions in images, and thus makes reliable predictions of the holistic image structures. To facilitate the structure refinement, we propose a Multi-scale Sketch Tensor inpainting (MST) network, with a novel encoder-decoder structure. The encoder extracts lines and edges from the input images to project them into an ST space. From this space, the decoder is learned to restore the input images. Extensive experiments validate the efficacy of our model. Furthermore, our model can also achieve competitive performance in inpainting general nature images over the competitors.

The topical domain generalization (DG) problem asks trained models to perform well on an unseen target domain with different data statistics from the source training domains. In computer vision, data augmentation has proven one of the most effective ways of better exploiting the source data to improve domain generalization. However, existing approaches primarily rely on image-space data augmentation, which requires careful augmentation design, and provides limited diversity of augmented data. We argue that feature augmentation is a more promising direction for DG. We find that an extremely simple technique of perturbing the feature embedding with Gaussian noise during training leads to a classifier with domain-generalization performance comparable to existing state of the art. To model more meaningful statistics reflective of cross-domain variability, we further estimate the full class-conditional feature covariance matrix iteratively during training. Subsequent joint stochastic feature augmentation provides an effective domain randomization method, perturbing features in the directions of intra-class/cross-domain variability. We verify our proposed method on three standard domain generalization benchmarks, Digit-DG, VLCS and PACS, and show it is outperforming or comparable to the state of the art in all setups, together with experimental analysis to illustrate how our method works towards training a robust generalisable model.

We present a deep learning pipeline that leverages network self-prior to recover a full 3D model consisting of both a triangular mesh and a texture map from the colored 3D point cloud. Different from previous methods either exploiting 2D self-prior for image editing or 3D self-prior for pure surface reconstruction, we propose to exploit a novel hybrid 2D-3D self-prior in deep neural networks to significantly improve the geometry quality and produce a high-resolution texture map, which is typically missing from the output of commodity-level 3D scanners. In particular, we first generate an initial mesh using a 3D convolutional neural network with 3D self-prior, and then encode both 3D information and color information in the 2D UV atlas, which is further refined by 2D convolutional neural networks with the self-prior. In this way, both 2D and 3D self-priors are utilized for the mesh and texture recovery. Experiments show that, without the need of any additional training data, our method recovers the 3D textured mesh model of high quality from sparse input, and outperforms the state-of-the-art methods in terms of both geometry and texture quality.

Most of existing unsupervised person re-identification algorithms use single-scale structure to extract global features. However, the features extracted from different scales and spatial locations are crucial for person re-identification task mainly using body parts to identify. In this paper, we propose a novel global-local architecture called dynamic feature aggregation network (DFANet) to learn discriminative patch features at various semantic levels on unlabelled datasets and aggregate them with a dynamic aggregation mechanism. Specifically, DFANet starts with a global feature learning stage to learn global features at various semantic levels. Then a local stage formed by attention patch generation network and dynamic aggregation module is deployed to extract distinct and notable local features on unlabelled datasets. Extensive experimental results on Market1501 and DukeMTMC show that our proposed method outperforms state-of-the-art works.

Visual Language Navigation (VLN) is the grand goal of AI, which enables the agent to act by the language instructions from humans. In VLN task, the agent learns to search for a specific region described by the instructions in the training environments, and performs the navigation in the unseen environments. Normally, there exists a large domain gap be-tween the seen and unseen environments. Numerous works have been put on data augmentation and designing new loss in such a multi-task navigation setting. However, as a spatial and temporal searching task, a valuable signal source for the navigation – depth has not yet fully explored and thus been ignored in previous efforts. Typically, the current models lack the ability to capture the relative spatial directions to the grounding view. To address these issues, we propose an environment adaptive method based on a Depth-guided Adaptive Instance Normalization (DG-AdaIN) module to adjust the RGB features in term of the depth features, and develop a shift attention module to model the relative direct information in the attention map. Extensive experiments have validated the efficacy of our method on the benchmark dataset.

Multi-label image classification is a fundamental but challenging task in Multimedia community. It aims to predict a set of labels presented in an image. Great progress has been made by exploring convolutional neural network with binary cross-entropy loss recently. However, conventional approaches are limited to highlight the key visual contents associated with target labels and pay little attention to confining the distances between visual and positive/negative label representations. To target these aspects, we firstly introduce a variant transformer encoder model for acquiring the underlying and crucial visual information related to ground truth labels. Specifically, a novel primal feature guided net is designed to maintain the original visual features during encoding process. Secondly, we exploit a distance restricted learning strategy in a common semantic space to shrink the distances of images with positive labels while expand with the negative ones during training stage. Extensive experiments are executed on MSCOCO and WIDER Attribute datasets and outstanding performance is achieved compared with other state-of-the-art models.

Machine learning classifiers’ capability is largely dependent on the scale of available training data and limited by the model overfitting in data-scarce learning tasks. To address this problem, this work proposes a novel Meta Functional Learning (MFL) by meta-learning a generalisable functional model from data-rich tasks whilst simultaneously regularising knowledge transfer to data-scarce tasks. The MFL computes meta-knowledge on functional regularisation generalisable to different learning tasks by which functional training on limited labelled data promotes more discriminative functions to be learned. Moreover, we adopt an Iterative Update strategy on MFL (MFL-IU). This improves knowledge transfer regularisation from MFL by progressively learning the functional regularisation in knowledge transfer. Experiments on three Few-Shot Learning (FSL) benchmarks (miniImageNet, CIFAR-FS and CUB) show that meta functional learning for regularisation knowledge transfer can benefit improving FSL classifiers.

Given a video demonstration, can we imitate the action contained in this video? In this paper, we introduce a novel task, dubbed mesh-based action imitation. The goal of this task is to enable an arbitrary target human mesh to perform the same action shown on the video demonstration. To achieve this, a novel Mesh-based Video Action Imitation (M-VAI) method is proposed by us. M-VAI first learns to reconstruct the meshes from the given source image frames, then the initial recovered mesh sequence is fed into mesh2mesh, a mesh sequence smooth module proposed by us, to improve the temporal consistency. Finally, we imitate the actions by transferring the pose from the constructed human body to our target identity mesh. High-quality and detailed human body meshes can be generated by using our M-VAI. Extensive experiments demonstrate the feasibility of our task and the effectiveness of our proposed method.

Non-Maximum Suppression (NMS) is essential for object detection and affects the evaluation results by incorporating False Positives (FP) and False Negatives (FN), especially in crowd occlusion scenes. In this paper, we raise the problem of weak connection between the training targets and the evaluation metrics caused by NMS and propose a novel NMS-Loss making the NMS procedure can be trained end-to-end without any additional network parameters. Our NMS-Loss punishes two cases when FP is not suppressed and FN is wrongly eliminated by NMS. Specifically, we propose a pull loss to pull predictions with the same target close to each other, and a push loss to push predictions with different targets away from each other. Experimental results show that with the help of NMS-Loss, our detector, namely NMS-Ped, achieves impressive results with Miss Rate of 5.92% on Caltech dataset and 10.08%on CityPersons dataset, which are both better than state-of-the-art competitors.

Traditional image captioning models mainly rely on one encoder-decoder architecture to generate one natural sentence for a given image. Such an architecture mostly uses deep neural networks to extract the neural representations of the image while ignoring the information of abstractive concepts as well as their intertwined relationships conveyed in the image. To this end, to comprehensively characterize the image content and bridge the gap between neural representations and high-level abstractive concepts, we make the first attempt to investigate the ability of neural symbolic representation of the image for the image captioning task. We first parse and convert a given image to neural symbolic representation in the form of an attributed relational graph, with the nodes denoting the abstractive concepts and the branches indicating the relationships between connected nodes, respectively. By performing computations over the attributed relational graph, the neural symbolic representation evolves step by step, with the node and branch representations as well as their corresponding importance weights transiting step by step. Empirically, extensive experiments validate the effectiveness of the proposed method. It enables a more comprehensive understanding of the given image by integrating the neural representation and neural symbolic representation, with the state-of-the-art results being achieved on both the MSCOCO and Flickr30k datasets. Besides, the proposed neural symbolic representation is demonstrated to better generalize to other domains with significant performance improvements compared with existing methods on the cross domain image captioning task.

A recent study [4] finds that existing few-shot learning methods, trained on the source domain, fail to generalize to the novel target domain when a domain gap is observed. This motivates the task of Cross-Domain Few-Shot Learning (CD-FSL). In this paper, we realize that the labeled target data in CD-FSL has not been leveraged in any way to help the learning process. Thus, we advocate utilizing few labeled target data to guide the model learning. Technically, a novel meta-FDMixup network is proposed. We tackle this problem mainly from two aspects. Firstly, to utilize the source and the newly introduced target data of two different class sets, a mixup module is re-proposed and integrated into the meta-learning mechanism. Secondly, a novel disentangle module together with a domain classifier is proposed to extract the disentangled domain-irrelevant and domain-specific features. These two modules together enable our model to narrow the domain gap thus generalizing well to the target datasets. Additionally, a detailed feasibility and pilot study is conducted to reflect the intuitive understanding of CD-FSL under our new setting. Experimental results show the effectiveness of our new setting and the proposed method. Codes and models are available at https://github.com/lovelyqian/Meta-FDMixup.

This paper proposes a novel approach for Sketch-Based Image Retrieval (SBIR), for which the key is to bridge the gap between sketches and photos in terms of the data representation. Inspired by channel-wise attention explored in recent years, we present a Domain-Aware Squeeze-and-Excitation (DASE) network, which seamlessly incorporates the prior knowledge of sample sketch or photo into SE module and make the SE module capable of emphasizing appropriate channels according to domain signal. Accordingly, the proposed network can switch its mode to achieve a better domain feature with lower intra-class discrepancy. Moreover, while previous works simply focus on minimizing intra-class distance and maximizing inter-class distance, we introduce a loss function, named Multiplicative Euclidean Margin Softmax (MEMS), which introduces multiplicative Euclidean margin into feature space and ensure that the maximum intra-class distance is smaller than the minimum inter-class distance. This facilitates learning a highly discriminative feature space and ensures a more accurate image retrieval result. Extensive experiments are conducted on two widely used SBIR benchmark datasets. Our approach achieves better results on both datasets, surpassing the state-of-the-art methods by a large margin.

Recently, AutoRegressive (AR) models for the whole image generation empowered by transformers have achieved comparable or even better performance compared to Generative Adversarial Networks (GANs). Unfortunately, directly applying such AR models to edit/change local image regions, may suffer from the problems of missing global information, slow inference speed, and information leakage of local guidance. To address these limitations, we propose a novel model -- image Local Autoregressive Transformer (iLAT), to better facilitate the locally guided image synthesis. Our iLAT learns the novel local discrete representations, by the newly proposed local autoregressive (LA) transformer of the attention mask and convolution mechanism. Thus iLAT can efficiently synthesize the local image regions by key guidance information. Our iLAT is evaluated on various locally guided image syntheses, such as pose-guided person image synthesis and face editing. Both quantitative and qualitative results show the efficacy of our model.

Recognizing people by faces and other biometrics has been extensively studied in computer vision. But these techniques do not work for identifying the wearer of an egocentric (first-person) camera because that person rarely (if ever) appears in their own first-person view. But while one's own face is not frequently visible, their hands are: in fact, hands are among the most common objects in one's own field of view. It is thus natural to ask whether the appearance and motion patterns of people's hands are distinctive enough to recognize them. In this paper, we systematically study the possibility of Egocentric Hand Identification (EHI) with unconstrained egocentric hand gestures. We explore several different visual cues, including color, shape, skin texture, and depth maps to identify users' hands. Extensive ablation experiments are conducted to analyze the properties of hands that are most distinctive. Finally, we show that EHI can improve generalization of other tasks, such as gesture recognition, by training adversarially to encourage these models to ignore differences between users.

The task of video and text sequence alignment is a pre-requisite step toward joint understanding of movie videos and screenplays. However, supervised methods face the obstacle of limited realistic training data. With this pa-per, we attempt to enhance data efficiency of the end-to-end alignment network NeuMATCH [15]. Recent research [56] suggests that network components dealing with different modalities may overfit and generalize at different speeds, creating difficulties for training. We propose to employ (1) layer-wise adaptive rate scaling (LARS) to align the magnitudes of gradient updates in different layers and balance the pace of learning and (2) sequence-wise batch normalization (SBN) to align the internal feature distributions from different modalities. Finally, we leverage random projection to reduce the dimensionality of input features. On the YouTube Movie Summary dataset, the combined use of these technique closes the performance gap when the pretraining on the LSMDC dataset is omitted and achieves the state-of-the-art result. Extensive empirical comparisons and analysis reveal that these techniques improve optimization and regularize the network more effectively than two different setups of layer normalization.

In this paper, we propose an end-to-end deep learning architecture that generates 3D triangular meshes from single color images. Restricted by the nature of prevalent deep learning techniques, the majority of previous works represent 3D shapes in volumes or point clouds. However, it is non-trivial to convert these representations to compact and ready-to-use mesh models. Unlike the existing methods, our network represents 3D shapes in meshes, which are essentially graphs and well suited for graph-based convolutional neural networks. Leveraging perceptual features extracted from an input image, our network produces the correct geometry by progressively deforming an ellipsoid. To make the whole deformation procedure stable, we adopt a coarse-to-fine strategy, and define various mesh/surface related losses to capture properties of various aspects, which benefits producing the visually appealing and physically accurate 3D geometry. In addition, our model by nature can be adapted to objects in specific domains, e.g., human faces, and be easily extended to learn per-vertex properties, e.g., color. Extensive experiments show that our method not only qualitatively produces the mesh model with better details, but also achieves the higher 3D shape estimation accuracy compared against the state-of-the-arts.

This paper studies the task of image captioning with novel objects, which only exist in testing images. Intrinsically, this task can reflect the generalization ability of models in understanding and captioning the semantic meanings of visual concepts and objects unseen in training set, sharing the similarity to one/zero-shot learning. The critical difficulty thus comes from that no paired images and sentences of the novel objects can be used to help train the captioning model. Inspired by recent work (Chen et al. 2019b) that boosts one-shot learning by learning to generate various image deformations, we propose learning meta-networks for deforming features for novel object captioning. To this end, we introduce the feature deformation meta-networks (FDM-net), which is trained on source data, and learn to adapt to the novel object features detected by the auxiliary detection model. FDM-net includes two sub-nets: feature deformation, and scene graph sentence reconstruction, which produce the augmented image features and corresponding sentences, respectively. Thus, rather than directly deforming images, FDM-net can efficiently and dynamically enlarge the paired images and texts by learning to deform image features. Extensive experiments are conducted on the widely used novel object captioning dataset, and the results show the effectiveness of our FDM-net. Ablation study and qualitative visualization further give insights of our model.

Previous researches of sketches often considered sketches in pixel format and leveraged CNN based models in the sketch understanding. Fundamentally, a sketch is stored as a sequence of data points, a vector format representation, rather than the photo-realistic image of pixels. SketchRNN studied a generative neural representation for sketches of vector format by Long Short Term Memory networks (LSTM). Unfortunately, the representation learned by SketchRNN is primarily for the generation tasks, rather than the other tasks of recognition and retrieval of sketches. To this end and inspired by the recent BERT model, we present a model of learning Sketch Bidirectional Encoder Representation from Transformer (Sketch-BERT). We generalize BERT to sketch domain, with the novel proposed components and pre-training algorithms, including the newly designed sketch embedding networks, and the self-supervised learning of sketch gestalt. Particularly, towards the pre-training task, we present a novel Sketch Gestalt Model (SGM) to help train the Sketch-BERT. Experimentally, we show that the learned representation of Sketch-BERT can help and improve the performance of the downstream tasks of sketch recognition, sketch retrieval, and sketch gestalt.

It is challenging in learning a makeup-invariant face verification model, due to (1) insufficient makeup/non-makeup face training pairs, (2) the lack of diverse makeup faces, and (3) the significant appearance changes caused by cosmetics. To address these challenges, we propose a unified Face Morphological Multi-branch Network (FMMu-Net) for makeup-invariant face verification, which can simultaneously synthesize many diverse makeup faces through face morphology network (FM-Net) and effectively learn cosmetics-robust face representations using attention-based multi-branch learning network (AttM-Net). For challenges (1) and (2), FM-Net (two stacked auto-encoders) can synthesize realistic makeup face images by transferring specific regions of cosmetics via cycle consistent loss. For challenge (3), AttM-Net, consisting of one global and three local (task-driven on two eyes and mouth) branches, can effectively capture the complementary holistic and detailed information. Unlike DeepID2 which uses simple concatenation fusion, we introduce a heuristic method AttM-FM, attached to AttM-Net, to adaptively weight the features of different branches guided by the holistic information. We conduct extensive experiments on makeup face verification benchmarks (M-501, M-203, and FAM) and general face recognition datasets (LFW and IJB-A). Our framework FMMu-Net achieves state-of-the-art performances.

Pose transfer has been studied for decades, in which the pose of a source mesh is applied to a target mesh. Particularly in this paper, we are interested in transferring the pose of source human mesh to deform the target human mesh, while the source and target meshes may have different identity information. Traditional studies assume that the paired source and target meshes are existed with the point-wise correspondences of user annotated landmarks/mesh points, which requires heavy labelling efforts. On the other hand, the generalization ability of deep models is limited, when the source and target meshes have different identities. To break this limitation, we proposes the first neural pose transfer model that solves the pose transfer via the latest technique for image style transfer, leveraging the newly proposed component -- spatially adaptive instance normalization. Our model does not require any correspondences between the source and target meshes. Extensive experiments show that the proposed model can effectively transfer deformation from source to target meshes, and has good generalization ability to deal with unseen identities or poses of meshes. Code is available at https://github.com/jiashunwang/Neural-Pose-Transfer.

Few-shot learning (FSL) aims to recognize new objects with extremely limited training data for each category. Previous efforts are made by either leveraging meta-learning paradigm or novel principles in data augmentation to alleviate this extremely data-scarce problem. In contrast, this paper presents a simple statistical approach, dubbed Instance Credibility Inference (ICI) to exploit the distribution support of unlabeled instances for few-shot learning. Specifically, we first train a linear classifier with the labeled few-shot examples and use it to infer the pseudo-labels for the unlabeled data. To measure the credibility of each pseudo-labeled instance, we then propose to solve another linear regression hypothesis by increasing the sparsity of the incidental parameters and rank the pseudo-labeled instances with their sparsity degree. We select the most trustworthy pseudo-labeled instances alongside the labeled examples to re-train the linear classifier. This process is iterated until all the unlabeled samples are included in the expanded training set, i.e. the pseudo-label is converged for unlabeled data pool. Extensive experiments under two few-shot settings show that our simple approach can establish new state-of-the-arts on four widely used few-shot learning benchmark datasets including miniImageNet, tieredImageNet, CIFAR-FS, and CUB. Our code is available at: https://github.com/Yikai-Wang/ICI-FSL

Over-parameterization is ubiquitous nowadays in training neural networks to benefit both optimization in seeking global optima and generalization in reducing prediction error. However, compressive networks are desired in many real world applications and direct training of small networks may be trapped in local optima. In this paper, instead of pruning or distilling over-parameterized models to compressive ones, we propose a new approach based on differential inclusions of inverse scale spaces. Specifically, it generates a family of models from simple to complex ones that couples a pair of parameters to simultaneously train over-parameterized deep models and structural sparsity on weights of fully connected and convolutional layers. Such a differential inclusion scheme has a simple discretization, proposed as Deep structurally splitting Linearized Bregman Iteration (DessiLBI), whose global convergence analysis in deep learning is established that from any initializations, algorithmic iterations converge to a critical point of empirical risks. Experimental evidence shows that DessiLBI achieve comparable and even better performance than the competitive optimizers in exploring the structural sparsity of several widely used backbones on the benchmark datasets. Remarkably, with early stopping, DessiLBI unveils “winning tickets” in early epochs: the effective sparse structure with comparable test accuracy to fully trained over-parameterized models.

Human beings not only have the ability to recognize novel unseen classes, but also can incrementally incorporate the new classes to existing knowledge preserved. However, zero-shot learning models assume that all seen classes should be known beforehand, while incremental learning models cannot recognize unseen classes. This paper introduces a novel and challenging task of Incrementally Zero-Shot Detection (IZSD), a practical strategy for both zero-shot learning and class-incremental learning in real-world object detection. An innovative end-to-end model - IZSD-EVer was proposed to tackle this task that requires incrementally detecting new classes and detecting the classes that have never been seen. Specifically, we propose a novel extreme value analyzer to detect objects from old seen, new seen, and unseen classes, simultaneously. Additionally and technically, we propose two innovative losses, i.e., background-foreground mean squared error loss alleviating the extreme imbalance of the background and foreground of images, and projection distance loss aligning the visual space and semantic spaces of old seen classes. Experiments demonstrate the efficacy of our model in detecting objects from both the seen and unseen classes, outperforming the alternative models on Pascal VOC and MSCOCO datasets.

Humans can easily recognize actions with only a few examples given, while the existing video recognition models still heavily rely on the large-scale labeled data inputs. This observation has motivated an increasing interest in few-shot video action recognition, which aims at learning new actions with only very few labeled samples. In this paper, we propose a depth guided Adaptive Meta-Fusion Network for few-shot video recognition which is termed as AMeFu-Net. Concretely, we tackle the few-shot recognition problem from three aspects: firstly, we alleviate this extremely data-scarce problem by introducing depth information as a carrier of the scene, which will bring extra visual information to our model; secondly, we fuse the representation of original RGB clips with multiple non-strictly corresponding depth clips sampled by our temporal asynchronization augmentation mechanism, which synthesizes new instances at feature-level; thirdly, a novel Depth Guided Adaptive Instance Normalization (DGAdaIN) fusion module is proposed to fuse the two-stream modalities efficiently. Additionally, to better mimic the few-shot recognition process, our model is trained in the meta-learning way. Extensive experiments on several action recognition benchmarks demonstrate the effectiveness of our model.

Building an intelligent defect segmentation system for textured images has attracted much increasing attention in both research and industrial communities, due to its significance values in the practical applications of industrial inspection and quality control. Previous models learned the classical classifiers for segmentation by designing handcrafted features. However, defect segmentation of textured surface images poses challenges such as ambiguous shapes and sizes of defects along with varying textures and patterns in the images. Thus, hand-crafted features based segmentation methods can only be applied to particular types of textured images. To this end, it is desirable to learn a general deep learning based representation for the automatic segmentation of defects. Furthermore, it is relatively less study in efficiently extracting the deep features in the frequency domain, which, nevertheless, should be very important to understand the patterns of textured images. In this paper, we propose a novel defect segmentation deep network - Main-Secondary Network (MS-Net). Our MS-Net is trained to model both features from the spatial domain and the frequency domain, where wavelet transform is utilized to extract discriminative information from the frequency domain. Extensive experiments show the effectiveness of our MS-Net.

Despite significant progress in object categorization, in recent years, a number of important challenges remain; mainly, the ability to learn from limited labeled data and to recognize object classes within large, potentially open, set of labels. Zero-shot learning is one way of addressing these challenges, but it has only been shown to work with limited sized class vocabularies and typically requires separation between supervised and unsupervised classes, allowing former to inform the latter but not vice versa. We propose the notion of vocabulary-informed learning to alleviate the above mentioned challenges and address problems of supervised, zero-shot, generalized zero-shot and open set recognition using a unified framework. Specifically, we propose a weighted maximum margin framework for semantic manifold-based recognition that incorporates distance constraints from (both supervised and unsupervised) vocabulary atoms. Distance constraints ensure that labeled samples are projected closer to their correct prototypes, in the embedding space, than to others. We illustrate that resulting model shows improvements in supervised, zero-shot, generalized zero-shot, and large open set recognition, with up to 310K class vocabulary on Animal with Attributes and ImageNet datasets.

Person re-identification (re-id) aims to match people across non-overlapping camera views in a public space. This is a challenging problem because the people captured in surveillance videos often wear similar clothing. Consequently, the differences in their appearance are typically subtle and only detectable at particular locations and scales. In this paper, we propose a deep re-id network (MuDeep) that is composed of two novel types of layers - a multi-scale deep learning layer, and a leader-based attention learning layer. Specifically, the former learns deep discriminative feature representations at different scales, while the latter utilizes the information from multiple scales to lead and determine the optimal weightings for each scale. The importance of different spatial locations for extracting discriminative features is learned explicitly via our leader-based attention learning layer. Extensive experiments are carried out to demonstrate that the proposed MuDeep outperforms the state-of-the-art on a number of benchmarks and has a better generalization ability under a domain generalization setting.

This paper aims at learning to score the figure skating sports videos. To address this task, we propose a deep architecture that includes two complementary components, i.e., Self-Attentive LSTM and Multi-scale Convolutional Skip LSTM. These two components can efficiently learn the local and global sequential information in each video. Furthermore, we present a large-scale figure skating sports video dataset - FisV dataset. This dataset includes 500 figure skating videos with the average length of 2 minutes and 50 seconds. Each video is annotated by two scores of nine different referees, i.e., Total Element Score(TES) and Total Program Component Score (PCS). Our proposed model is validated on FisV and MIT-skate datasets. The experimental results show the effectiveness of our models in learning to score the figure skating videos. The codes and datasets would be downloaded from https://github.com/loadder/MS_LSTM.git.

Deeper and wider convolutional neural networks (CNNs) achieve superior performance but bring expensive computation cost. Accelerating such overparameterized neural network has received increased attention. A typical pruning algorithm is a three-stage pipeline, i.e., training, pruning, and retraining. Prevailing approaches fix the pruned filters to zero during retraining and, thus, significantly reduce the optimization space. Besides, they directly prune a large number of filters at first, which would cause unrecoverable information loss. To solve these problems, we propose an asymptotic soft filter pruning (ASFP) method to accelerate the inference procedure of the deep neural networks. First, we update the pruned filters during the retraining stage. As a result, the optimization space of the pruned model would not be reduced but be the same as that of the original model. In this way, the model has enough capacity to learn from the training data. Second, we prune the network asymptotically. We prune few filters at first and asymptotically prune more filters during the training procedure. With asymptotic pruning, the information of the training set would be gradually concentrated in the remaining filters, so the subsequent training and pruning process would be stable. The experiments show the effectiveness of our ASFP on image classification benchmarks. Notably, on ILSVRC-2012, our ASFP reduces more than 40% FLOPs on ResNet-50 with only 0.14% top-5 accuracy degradation, which is higher than the soft filter pruning by 8%.

In recent years, the satellite videos have been captured by moving satellite platforms. In contrast to consumers, movies, and common surveillance videos, satellite videos can record the snapshots of city-scale scenes. In a broad fieldof-view of satellite videos, each moving target would be very tiny and usually composed of several pixels in frames. Even worse, the noise signals also exist in the video frames, and the background of the video frames subpixel-level and uneven moving thanks to the motion of satellites. We argue that it is a novel type of computer vision task since previous technologies are unable to detect such tiny moving vehicles efficiently. This paper proposes a novel framework that can identify small moving vehicles in satellite videos. In particular, we offer a novel detecting algorithm based on the local noise modeling. We differentiate the potential vehicle targets from noise patterns by an exponential probability distribution. Subsequently, a multi-morphologicalcue based discrimination strategy is designed to distinguish correct vehicle targets from the existing noises further. Another significant contribution is to introduce a series of evaluation protocols to measure the performance of tiny moving vehicle detection systematically. We annotate satellite videos manually to test our algorithms under different evaluation criterions. The proposed algorithm is also compared with the state-of-the-art baselines, which demonstrates the advantages of our framework over the benchmarks. Besides, the dataset would be downloaded from http://first.authour.github.com.

During the past decade, both multi-label learning and zero-shot learning have attracted huge research attention, and significant progress has been made. Multi-label learning algorithms aim to predict multiple labels given one instance, while most existing zero-shot learning approaches target at predicting a single testing label for each unseen class via transferring knowledge from auxiliary seen classes to target unseen classes. However, relatively less effort has been made on predicting multiple labels in the zero-shot setting, which is nevertheless a quite challenging task. In this work, we investigate and formalize a flexible framework consisting of two components, i.e., visual-semantic embedding and zero-shot multi-label prediction. First, we present a deep regression model to project the visual features into the semantic space, which explicitly exploits the correlations in the intermediate semantic layer of word vectors and makes label prediction possible. Then, we formulate the label prediction problem as a pairwise one and employ Ranking SVM to seek the unique multi-label correlations in the embedding space. Furthermore, we provide a transductive multi-label zeroshot prediction approach that exploits the testing data manifold structure. We demonstrate the effectiveness of the proposed approach on three popular multi-label datasets with state-of-theart performance obtained on both conventional and generalized ZSL settings.

The process of learning good representations for machine learning tasks can be very computationally expensive. Typically, we facilitate the same backbones learned on the training set to infer the labels of testing data. Interestingly, This learning and inference paradigm, however, is quite different from the typical inference scheme of human biological visual systems. Essentially, neuroscience studies have shown that the right hemisphere of the human brain predominantly makes a fast processing of low-frequency spatial signals, while the left hemisphere more focuses on analyzing high-frequency information in a slower way. And the low-pass analysis helps facilitate the high-pass analysis via a feedback form. Inspired by this biological vision mechanism, this paper explores the possibility of learning a layer-skippable inference network. Specifically, we propose a layer-skippable network that dynamically carries out coarse-tofine object categorization. Such a network has two branches to jointly deal with both coarse and fine-grained classification tasks. The layer-skipping mechanism is proposed to learn a gating network by generating dynamic inference graphs, and reducing the computational cost by detouring the inference path from some layers. This adaptive path inference strategy endows the network with better flexibility and larger capacity and makes the high-performance deep networks with dynamic structures. To efficiently train the gating network, a novel ranking-based loss function is presented. Furthermore, the learned representations are enhanced by the proposed top-down feedback facilitation and feature-wise affine transformation, individually. The former one employs features of a coarse branch to help the finegrained object recognition task, while the latter one encodes the selected path to enhance the final feature representations. Extensive experiments are conducted on several widely used coarse-to-fine object categorization benchmarks, and promising results are achieved by our proposed model. Quite surprisingly, our layer-skipping mechanism improves the network robustness to adversarial attacks. The codes and models are released on https://github.com/avalonstrel/DSN.

Generating realistic images with the guidance of reference images and human poses is challenging. Despite the success of previous works on synthesizing person images in the iconic views, no efforts are made towards the task of poseguided image synthesis in the non-iconic views. Particularly, we find that previous models cannot handle such a complex task, where the person images are captured in the non-iconic views by commercially-available digital cameras. To this end, we propose a new framework - Multi-branch Refinement Network (MR-Net), which utilizes several visual cues, including target person poses, foreground person body and scene images parsed. Furthermore, a novel Region of Interest (RoI) perceptual loss is proposed to optimize the MR-Net. Extensive experiments on two non-iconic datasets, Penn Action and BBC-Pose, as well as an iconic dataset - Market-1501, show the efficacy of the proposed model that can tackle the problem of pose-guided person image generation from the non-iconic views. The data, models, and codes are downloadable from https://github.com/loadder/MR-Net.

To counter the outbreak of COVID-19, the accurate diagnosis of suspected cases plays a crucial role in timely quarantine, medical treatment, and preventing the spread of the pandemic. Considering the limited training cases and resources (e.g, time and budget), we propose a Multi-task Multi-slice Deep Learning System (M3Lung-Sys) for multi-class lung pneumonia screening from CT imaging, which only consists of two 2D CNN networks, i.e., slice- and patient-level classification networks. The former aims to seek the feature representations from abundant CT slices instead of limited CT volumes, and for the overall pneumonia screening, the latter one could recover the temporal information by feature refinement and aggregation between different slices. In addition to distinguish COVID-19 from Healthy, H1N1, and CAP cases, our M3Lung-Sys also be able to locate the areas of relevant lesions, without any pixel-level annotation. To further demonstrate the effectiveness of our model, we conduct extensive experiments on a chest CT imaging dataset with a total of 734 patients (251 healthy people, 245 COVID-19 patients, 105 H1N1 patients, and 133 CAP patients). The quantitative results with plenty of metrics indicate the superiority of our proposed model on both slice- and patient-level classification tasks. More importantly, the generated lesion location maps make our system interpretable and more valuable to clinicians.

Emotional content is a crucial ingredient in user-generated videos. However, the sparsity of emotional expressions in the videos poses an obstacle to visual emotion analysis. In this paper, we propose a new neural approach, Bi-stream Emotion Attribution-Classification Network (BEAC-Net), to solve three related emotion analysis tasks: emotion recognition, emotion attribution, and emotion-oriented summarization, in a single integrated framework. BEAC-Net has two major constituents, an attribution network and a classification network. The attribution network extracts the main emotional segment that classification should focus on in order to mitigate the sparsity issue. The classification network utilizes both the extracted segment and the original video in a bi-stream architecture. We contribute a new dataset for the emotion attribution task with human-annotated ground-truth labels for emotion segments. Experiments on two video datasets demonstrate superior performance of the proposed framework and the complementary nature of the dual classification streams.

Given one or a few training instances of novel classes, oneshot learning task requires that the classifier generalizes to these novel classes. Directly training one-shot classifier may suffer from insufficient training instances in one-shot learning. Previous one-shot learning works investigate the metalearning or metric-based algorithms; in contrast, this paper proposes a Self-Training Jigsaw Augmentation (Self-Jig) method for one-shot learning. Particularly, we solve one-shot learning by directly augmenting the training images through leveraging the vast unlabeled instances. Precisely our proposed Self-Jig algorithm can synthesize new images from the labeled probe and unlabeled gallery images. The labels of gallery images are predicted to help the augmentation process, which can be taken as a self-training scheme. Intrinsically, we argue that we provide a very useful way of directly generating massive amounts of training images for novel classes. Extensive experiments and ablation study not only evaluate the efficacy but also reveal the insights, of the proposed Self-Jig method.

Humans can robustly learn novel visual concepts even when images undergo various deformations and loose certain information. Mimicking the same behavior and synthesizing deformed instances of new concepts may help visual recognition systems perform better one-shot learning, i.e., learning concepts from one or few examples. Our key insight is that, while the deformed images may not be visually realistic, they still maintain critical semantic information and contribute significantly to formulating classifier decision boundaries. Inspired by the recent progress of meta-learning, we combine a meta-learner with an image deformation sub-network that produces additional training examples, and optimize both models in an end-to-end manner. The deformation sub-network learns to deform images by fusing a pair of images --- a probe image that keeps the visual content and a gallery image that diversifies the deformations. We demonstrate results on the widely used one-shot learning benchmarks (miniImageNet and ImageNet 1K Challenge datasets), which significantly outperform state-of-the-art approaches.

We study the problem of shape generation in 3D mesh representation from a few color images with known camera poses. While many previous works learn to hallucinate the shape directly from priors, we resort to further improving the shape quality by leveraging cross-view information with a graph convolutional network. Instead of building a direct mapping function from images to 3D shape, our model learns to predict series of deformations to improve a coarse shape iteratively. Inspired by traditional multiple view geometry methods, our network samples nearby area around the initial mesh's vertex locations and reasons an optimal deformation using perceptual feature statistics built from multiple input images. Extensive experiments show that our model produces accurate 3D shape that are not only visually plausible from the input perspectives, but also well aligned to arbitrary viewpoints. With the help of physically driven architecture, our model also exhibits generalization capability across different semantic categories, number of input images, and quality of mesh initialization.

In semantic segmentation, researchers face the shortage of pixel-level annotated data. And it is particularly severe in the medical images. On the other hand, the unlabeled data are abundantly produced in the diagnosis routine. In the paper, we introduced the Parasitic GAN for the brain tumor segmentation to exploit the unlabeled data more efficiently. Parasitic GAN is composed of three parts: the segmentor S, the generator G, and the discriminator V. With the label maps produced by the segmentor and the supplementary label maps synthesized by the generator, the discriminator could learn a more precise boundary of ground truth. Thus, the segmentor benefits from the adversarial learning mechanism and the extra supervision provided by the discriminator. This parasitic relationship between the segmentor and the generative adversarial network (G and V) restricts the fitness ability of the segmentor and improves its generalization capacity. In practice, it definitely improved the performance of segmentor in brain tumor segmentation tasks, increasing the dice score 0.010-0.035.

Deep learning has played an important role in various computer vision tasks, and so does in single image dehazing. We think edges and colors are two key factors to obtain better dehazed images. Clear edges and balanced color make the dehazed images look natural and detailed. Therefore, we establish a novel two-stage and end-to-end network that comprises two characteristics. First, we propose the wavelet U-net, which uses discrete wavelet transform and inverse discrete wavelet transform to replace down-sampling and up-sampling, to extract edge features. Second, we apply the chromatic adaptation transform which can be implemented by convolutional layers mathematically to enhance images. Our neural network combining two concepts outperforms the state-of-art algorithms in visual performance and quantitative aspects.

Recent efforts have been made on continuously learning concepts over time, i.e., class-incremental learning, which, however, is still an open question to the task of object detection. For the first time, this paper systematically studies the task of learning an end-to-end class-incremental object detection model. Remarkably, this work tailors Faster R-CNN and proposes a Class-Incremental Faster R-CNN (CIFRCN) model that can dynamically add new classes by only using a few labeled images of new objects. Particularly, the domain of "foreground" in a Region Proposal Network is expanded to generate accurate bounding box proposals, and the classifier in Fast R-CNN is enlarged using knowledge distillation to accurately classify the proposals. Extensive experiments on two challenging datasets are conducted to demonstrate the efficacy of the proposed model for adding new objects in a class-incremental way, whereas other detectors quickly fail.

Recently, extensive efforts have been devoted to computer vision and machine learning by exploiting big data to explore many practical applications. However, these research fields are still quite limited not only by the sheer volume, but also the versatility and diversity, of the available datasets. In this paper, we target at four challenging and yet important computer vision tasks, namely, human-centered scene classification, attribute based zero-shot learning (recognition), human keypoint detection and image Chinese captioning. Four novel large-scale datasets are collected and annotated to facilitate these tasks of deeper image understanding. Labels, bounding boxes, attributes, keypoints and captions are annotated in corresponding datasets. These rich annotations bridge the semantic gap between low-level images and high-level concepts. Extensive experiments on baseline methods have been implemented and compared, which show that these learning tasks on our datasets are still challenging.

Object detection for automatic visual checkout in self-service vending machines is attracting significant attention in the retail industry. However, several critical challenges have not received enough attention. First, large-scale, high-quality retail image datasets are urgently demanded to train and evaluate the detection models. Second, the trained models should be able to cope with the frequently added new goods at low cost, while most cutting-edge models cannot. In this paper, we propose a new hierarchical large-scale object detection dataset, called Take Goods from Shelves (TGFS), containing 38K images of 24 fine-grained and 3 coarse classes. A preliminary method for solving the goods-adding problem, called Faster R-CNN Class-incremental Object Detector (FCIOD), is also described and evaluated. In addition, several popular methods are benchmarked on the TGFS dataset.

Given a photograph, the task of Visual Question Answering (VQA) requires joint image and language understanding to answer a question. It is challenging in effectively extracting the visual representation of images, and efficiently embedding the textual sentences of questions. To address these challenges, we propose a VQA model that utilizes the stacked self-attention for visual understanding, and the BERT-based question embedding model. Particularly, the stacked self-attention mechanism proposed enables the model to not only focus on a simple object but also the relations between objects. Furthermore, the BERT model is learned in an end-to-end manner to better embed the question sentences. Our model is validated on the well-known VQA v2.0 dataset, and achieves the state-of-the-art results.

One-shot learning aims to recognize novel target classes from few examples by transferring knowledge from source classes, under a general assumption that the source and target classes are semantically related but not exactly the same. Based on this assumption, recent work has focused on image-based one-shot learning, while little work has addressed video-based one shot learning. One of the challenges lies in that it is difficult to maintain the disjoint-class assumption for videos, since video clips of target classes may potentially appear in the videos of source classes. To address this issue, we introduce a novel setting, termed as embodied agents based one-shot learning, which leverages synthetic videos produced in a virtual environment to understand realistic videos of target classes. In this setting, we further propose two types of learning tasks: embodied one-shot video domain adaptation and embodied one-shot video transfer recognition. These tasks serve as a testbed for evaluating video related one-shot learning tasks. In addition, we propose a general video segment augmentation method, which significantly facilitates a variety of one-shot learning tasks. Experimental results validate the soundness of our setting and learning tasks, and also show the effectiveness of our augmentation approach to video recognition in the small-sample size regime.

Sketch has been employed as an effective communication tool to express the abstract and intuitive meaning of object. While content-based sketch recognition has been studied for several decades, the instance-level Sketch Based Image Retrieval (iSBIR) task has attracted significant research attention recently. In many previous iSBIR works -- TripletSN, and DSSA, edge maps were employed as intermediate representations in bridging the cross-domain discrepancy between photos and sketches. However, it is nontrivial to efficiently train and effectively use the edge maps in an iSBIR system. Particularly, we find that such an edge map based iSBIR system has several major limitations. First, the system has to be pre-trained on a significant amount of edge maps, either from large-scale sketch datasets, e.g., TU-Berlin~\citeeitz2012hdhso, or converted from other large-scale image datasets, e.g., ImageNet-1K\citedeng2009imagenet dataset. Second, the performance of such an iSBIR system is very sensitive to the quality of edge maps. Third and empirically, the multi-cropping strategy is essentially very important in improving the performance of previous iSBIR systems. To address these limitations, this paper advocates an end-to-end iSBIR system without using the edge maps. Specifically, we present a Triplet Classification Network (TC-Net) for iSBIR which is composed of two major components: triplet Siamese network, and auxiliary classification loss. Our TC-Net can break the limitations existed in previous works. Extensive experiments on several datasets validate the efficacy of the proposed network and system.

Facial expression is important in understanding our social interaction. Thus the ability to recognize facial expression enables the novel multimedia applications. With the advance of recent deep architectures, research on facial expression recognition has achieved great progress. However, these models are still suffering from the problems of lacking sufficient and diverse high quality training faces, vulnerability to the facial variations, and recognizing a limited number of basic types of emotions. To tackle these problems, this paper proposes a novel end-to-end Compositional Generative Adversarial Network (Comp-GAN) that is able to synthesize new face images with specified poses and desired facial expressions; and such synthesized images can be further utilized to help train a robust and generalized expression recognition model. Essentially, Comp-GAN can dynamically change the expression and pose of faces according to the input images while keeping the identity information. Specifically, the generator has two major components: one for generating images with desired expression and the other for changing the pose of faces. Furthermore, a face reconstruction learning process is applied to re-generate the input image and constrains the generator for preserving the key information such as facial identity. For the first time, various one/zero-shot facial expression recognition tasks have been created. We conduct extensive experiments to show that the images generated by Comp-GAN are helpful to improve the performance of one/zero-shot facial expression recognition.

This paper studies the task of one-shot fine-grained recognition, which suffers from the problem of data scarcity of novel fine-grained classes. To alleviate this problem, a off-the-shelf image generator can be applied to synthesize additional images to help one-shot learning. However, such synthesized images may not be helpful in one-shot fine-grained recognition, due to a large domain discrepancy between synthesized and original images. To this end, this paper proposes a meta-learning framework to reinforce the generated images by original images so that these images can facilitate one-shot learning. Specifically, the generic image generator is updated by few training instances of novel classes; and a Meta Image Reinforcing Network (MetaIRNet) is proposed to conduct one-shot fine-grained recognition as well as image reinforcement. The model is trained in an end-to-end manner, and our experiments demonstrate consistent improvement over baseline on one-shot fine-grained image classification benchmarks.

The ability to quickly recognize and learn new visual concepts from limited samples enables humans to quickly adapt to new tasks and environments. This ability is enabled by semantic association of novel concepts with those that have already been learned and stored in memory. Computers can start to ascertain similar abilities by utilizing a semantic concept space. A concept space is a high-dimensional semantic space in which similar abstract concepts appear close and dissimilar ones far apart. In this paper, we propose a novel approach to one-shot learning that builds on this core idea. Our approach learns to map a novel sample instance to a concept, relates that concept to the existing ones in the concept space and, using these relationships, generates new instances, by interpolating among the concepts, to help learning. Instead of synthesizing new image instance, we propose to directly synthesize instance features by leveraging semantics using a novel auto-encoder network we call dual TriNet. The encoder part of the TriNet learns to map multi-layer visual features from CNN to a semantic vector. In semantic space, we search for related concepts, which are then projected back into the image feature spaces by the decoder portion of the TriNet. Two strategies in the semantic space are explored. Notably, this seemingly simple strategy results in complex augmented feature distributions in the image feature space, leading to substantially better performance. The codes and models are released in the github: https://github.com/tankche1/ Semantic-Feature-Augmentation-in-Few-shot-Learning.

Inspired by the recent neuroscience studies on the left-right asymmetry of the human brain in processing low and high spatial frequency information, this paper introduces a dual skipping network which carries out coarse-to-fine object categorization. Such a network has two branches to simultaneously deal with both coarse and fine-grained classification tasks. Specifically, we propose a layer-skipping mechanism that learns a gating network to predict which layers to skip in the testing stage. This layer-skipping mechanism endows the network with good flexibility and capability in practice. Evaluations are conducted on several widely used coarse-to-fine object categorization benchmarks, and promising results are achieved by our proposed network model.

It is one typical and general topic of learning a good embedding model to efficiently learn the representation coefficients between two spaces/subspaces. To solve this task, $L_{1}$ regularization is widely used for the pursuit of feature selection and avoiding overfitting, and yet the sparse estimation of features in $L_{1}$ regularization may cause the underfitting of training data. $L_{2}$ regularization is also frequently used, but it is a biased estimator. In this paper, we propose the idea that the features consist of three orthogonal parts, namely sparse strong signals, dense weak signals and random noise, in which both strong and weak signals contribute to the fitting of data. To facilitate such novel decomposition, MSplit LBI is for the first time proposed to realize feature selection and dense estimation simultaneously. We provide theoretical and simulational verification that our method exceeds $L_{1}$ and $L_{2}$ regularization, and extensive experimental results show that our method achieves state-of-the-art performance in the few-shot and zero-shot learning.

Facial attribute recognition is an important and yet challenging research topic. Different from most previous approaches which predict attributes only based on the whole images, this paper leverages facial parts locations for better attribute prediction. A facial abstraction image which contains both local facial parts and facial texture information is introduced. This abstraction image is generated by a Generative Adversarial Network (GAN). Then we build a dual-path facial attribute recognition network to utilize features from the original face images and facial abstraction images. Empirically, the features of facial abstraction images are complementary to features of original face images. With the facial parts localized by the abstraction images, our method improves facial attributes recognition, especially the attributes located on small face regions. Extensive evaluations conducted on CelebA and LFWA benchmark datasets show that state-of-the-art performance is achieved.

This paper proposed a Soft Filter Pruning (SFP) method to accelerate the inference procedure of deep Convolutional Neural Networks (CNNs). Specifically, the proposed SFP enables the pruned filters to be updated when training the model after pruning. SFP has two advantages over previous works: (1) Larger model capacity. Updating previously pruned filters provides our approach with larger optimization space than fixing the filters to zero. Therefore, the network trained by our method has a larger model capacity to learn from the training data. (2) Less dependence on the pretrained model. Large capacity enables SFP to train from scratch and prune the model simultaneously. In contrast, previous filter pruning methods should be conducted on the basis of the pre-trained model to guarantee their performance. Empirically, SFP from scratch outperforms the previous filter pruning methods. Moreover, our approach has been demonstrated effective for many advanced CNN architectures. Notably, on ILSCRC-2012, SFP reduces more than 42% FLOPs on ResNet-101 with even 0.2% top-5 accuracy improvement, which has advanced the state-of-the-art. Code is publicly available on GitHub: https://github.com/he-y/softfilter-pruning

Zero-Shot Learning (ZSL) is generally achieved via aligning the semantic relationships between the visual features and the corresponding class semantic descriptions. However, using the global features to represent fine-grained images may lead to sub-optimal results since they neglect the discriminative differences of local regions. Besides, different regions contain distinct discriminative information. The important regions should contribute more to the prediction. To this end, we propose a novel stacked semantics-guided attention (S2GA) model to obtain semantic relevant features by using individual class semantic features to progressively guide the visual features to generate an attention map for weighting the importance of different local regions. Feeding both the integrated visual features and the class semantic features into a multi-class classification architecture, the proposed framework can be trained end-to-end. Extensive experimental results on CUB and NABird datasets show that the proposed approach has a consistent improvement on both fine-grained zero-shot classification and retrieval tasks.

Emotion is a key element in user-generated video. However, it is difficult to understand emotions conveyed in such videos due to the complex and unstructured nature of user-generated content and the sparsity of video frames expressing emotion. In this paper, for the first time, we propose a technique for transferring knowledge from heterogeneous external sources, including image and textual data, to facilitate three related tasks in understanding video emotion: emotion recognition, emotion attribution and emotion-oriented summarization. Specifically, our framework (1) learns a video encoding from an auxiliary emotional image dataset in order to improve supervised video emotion recognition, and (2) transfers knowledge from an auxiliary textual corpora for zero-shot recognition of emotion classes unseen during training. The proposed technique for knowledge transfer facilitates novel applications of emotion attribution and emotion-oriented summarization. A comprehensive set of experiments on multiple datasets demonstrate the effectiveness of our framework.

Person Re-identification (re-id) aims to match people across non-overlapping camera views in a public space. It is a challenging problem because many people captured in surveillance videos wear similar clothes. Consequently, the differences in their appearance are often subtle and only detectable at the right location and scales. Existing re-id models, particularly the recently proposed deep learning based ones match people at a single scale. In contrast, in this paper, a novel multi-scale deep learning model is proposed. Our model is able to learn deep discriminative feature representations at different scales and automatically determine the most suitable scales for matching. The importance of different spatial locations for extracting discriminative features is also learned explicitly. Experiments are carried out to demonstrate that the proposed model outperforms the state-of-the art on a number of benchmarks.

Emotional content is a key ingredient in user-generated videos. However, due to the emotion sparsely expressed in the user-generated video, it is very difficult to analayze emotions in videos. In this paper, we propose a new architecture--Frame-Transformer Emotion Classification Network (FT-EC-net) to solve three highly correlated emotion analysis tasks: emotion recognition, emotion attribution and emotion-oriented summarization. We also contribute a new dataset for emotion attribution task by annotating the ground-truth labels of attribution segments. A comprehensive set of experiments on two datasets demonstrate the effectiveness of our framework.

Deep neural networks have significantly improved the performance of face recognition and facial attribute prediction, which however are still very challenging on the million scale dataset, i.e. MegaFace. In this paper, we for the first time, advocate a multi-task deep neural network for jointly learning face recognition and facial attribute prediction tasks. Extensive experimental evaluation clearly demonstrates the effectiveness of our architecture. Remarkably, on the largest face recognition benchmark -- MegaFace dataset, our networks can achieve the Rank-1 identication accuracy of 77.74% and face verication accuracy 79.24% TAR at 10-6 FAR, which are the best performance on the small protocol among all the publicly released methods.

Multi-task learning aims to boost the performance of multiple prediction tasks by appropriately sharing relevant information among them. However, it always suffers from the negative transfer problem. And due to the diverse learning difficulties and convergence rates of different tasks, jointly optimizing multiple tasks is very challenging. To solve these problems, we present a weighted multi-task deep convolutional neural network for person attribute analysis. A novel validation loss trend algorithm is, for the first time proposed to dynamically and adaptively update the weight for learning each task in the training process. Extensive experiments on CelebA, Market-1501 attribute and Duke attribute datasets clearly show that state-of-the-art performance is obtained; and this validates the effectiveness of our proposed framework.

Modeling hairstyles for classification, synthesis and image editing has many practical applications. However, existing hairstyle datasets, such as the Beauty e-Expert dataset, are too small for developing and evaluating computer vision models, especially the recent deep generative models such as generative adversarial network (GAN). In this paper, we contribute a new large-scale hairstyle dataset called Hairstyle30k, which is composed of 30k images containing 64 different types of hairstyles. To enable automated generating and modifying hairstyles in images, we also propose a novel GAN model termed Hairstyle GAN (H-GAN) which can be learned efficiently. Extensive experiments on the new dataset as well as existing benchmark datasets demonstrate the effectiveness of proposed H-GAN model

Researchers often summarize their work in the form of posters. Posters provide a coherent and efficient way to convey core ideas from scientific papers. Generating a good scientific poster, however, is a complex and time consuming cognitive task, since such posters need to be readable, informative, and visually aesthetic. In this paper, for the first time, we study the challenging problem of learning to generate posters from scientific papers. To this end, a data-driven framework, that utilizes graphical models, is proposed. Specifically, given content to display, the key elements of a good poster, including panel layout and attributes of each panel, are learned and inferred from data. Then, given inferred layout and attributes, composition of graphical elements within each panel is synthesized. To learn and validate our model, we collect and make public a Poster-Paper dataset, which consists of scientific papers and corresponding posters with exhaustively labelled panels and attributes. Qualitative and quantitative results indicate the effectiveness of our approach.

Despite significant progress in object categorization, in recent years, a number of important challenges remain, mainly, ability to learn from limited labeled data and ability to recognize object classes within large, potentially open, set of labels. Zero-shot learning is one way of addressing these challenges, but it has only been shown to work with limited sized class vocabularies and typically requires separation between supervised and unsupervised classes, allowing former to inform the latter but not vice versa. We propose the notion of semi-supervised vocabulary-informed learning to alleviate the above mentioned challenges and address problems of supervised, zero-shot and open set recognition using a unified framework. Specifically, we propose a maximum margin framework for semantic manifold-based recognition that incorporates distance constraints from (both supervised and unsupervised) vocabulary atoms, ensuring that labeled samples are projected closest to their correct prototypes, in the embedding space, than to others. We show that resulting model shows improvements in supervised, zero-shot, and large open set recognition, with up to 310K class vocabulary on AwA and ImageNet datasets.

Large-scale action recognition and video categorization are important problems in computer vision. To address these problems, we propose a novel object-and scene-based semantic fusion network and representation. Our semantic fusion network combines three streams of information using a three-layer neural network: (i) frame-based low-level CNN features, (ii) object features from a state-of-the-art large-scale CNN object-detector trained to recognize 20K classes, and (iii) scene features from a state-of-the-art CNN scene-detector trained to recognize 205 scenes. The trained network achieves improvements in supervised activity and video categorization in two complex large-scale datasets - ActivityNet and FCVID, respectively. Further, by examining and back propagating information through the fusion network, semantic relationships (correlations) between video classes and objects/scenes can be discovered. These video class-object/video class-scene relationships can in turn be used as semantic representation for the video classes themselves. We illustrate effectiveness of this semantic representation through experiments on zero-shot action/video classification and clustering.

Traditional methods on video summarization are designed to generate summaries for single-view video records, and thus they cannot fully exploit the mutual information in multi-view video records. In this paper, we present a multiview metric learning framework for multi-view video summarization. It combines the advantages of maximum margin clustering with the disagreement minimization criterion. The learning framework thus has the ability to find a metric that best separates the input data, and meanwhile to force the learned metric to maintain underlying intrinsic structure of data points, for example geometric information. Facilitated by such a framework, a systematic solution to the multi-view video summarization problem is developed from the viewpoint of metric learning. The effectiveness of the proposed method is demonstrated by experiments.

Despite growing research interest, emotion understanding for user-generated videos remains a challenging problem. Major obstacles include the diversity and complexity of video content, as well as the sparsity of expressed emotions. For the first time, we systematically study large-scale video emotion recognition by transferring deep feature encodings. In addition to the traditional, supervised recognition, we study the problem of zero-shot emotion recognition, where emotions in the test set are unseen during training. To cope with this task, we utilize knowledge transferred from auxiliary image and text corpora. A novel auxiliary Image Transfer Encoding (ITE) process is proposed to efficiently encode and generate video representation. We also thoroughly investigate different configurations of convolutional neural networks. Comprehensive experiments on multiple datasets demonstrate the effectiveness of our framework.

The problem of estimating subjective visual properties from image and video has attracted increasing interest. A subjective visual property is useful either on its own (e.g. image and video interestingness) or as an intermediate representation for visual recognition (e.g. a relative attribute). Due to its ambiguous nature, annotating the value of a subjective visual property for learning a prediction model is challenging. To make the annotation more reliable, recent studies employ crowdsourcing tools to collect pairwise comparison labels. However, using crowdsourced data also introduces outliers. Existing methods rely on majority voting to prune the annotation outliers/errors. They thus require a large amount of pairwise labels to be collected. More importantly as a local outlier detection method, majority voting is ineffective in identifying outliers that can cause global ranking inconsistencies. In this paper, we propose a more principled way to identify annotation outliers by formulating the subjective visual property prediction task as a unified robust learning to rank problem, tackling both the outlier detection and learning to rank jointly. This differs from existing methods in that (1) the proposed method integrates local pairwise comparison labels together to minimise a cost that corresponds to global inconsistency of ranking order, and (2) the outlier detection and learning to rank problems are solved jointly. This not only leads to better detection of annotation outliers but also enables learning with extremely sparse annotations.

Learning from synthetic data has many important and practical applications, An example of application is photo-sketch recognition. Using synthetic data is challenging due to the differences in feature distributions between synthetic and real data, a phenomenon we term synthetic gap. In this paper, we investigate and formalize a general framework -- Stacked Multichannel Autoencoder (SMCAE) that enables bridging the synthetic gap and learning from synthetic data more efficiently. In particular, we show that our SMCAE can not only transform and use synthetic data on the challenging face-sketch recognition task, but that it can also help simulate real images, which can be used for training classifiers for recognition. Preliminary experiments validate the effectiveness of the framework.

Most existing zero-shot learning approaches exploit transfer learning via an intermediate semantic representation shared between an annotated auxiliary dataset and a target dataset with different classes and no annotation. A projection from a low-level feature space to the semantic representation space is learned from the auxiliary dataset and applied without adaptation to the target dataset. In this paper we identify two inherent limitations with these approaches. First, due to having disjoint and potentially unrelated classes, the projection functions learned from the auxiliary dataset/domain are biased when applied directly to the target dataset/domain. We call this problem the projection domain shift problem and propose a novel framework, transductive multi-view embedding, to solve it. The second limitation is the prototype sparsity problem which refers to the fact that for each target class, only a single prototype is available for zero-shot learning given a semantic representation. To overcome this problem, a novel heterogeneous multi-view hypergraph label propagation method is formulated for zero-shot learning in the transductive embedding space. It effectively exploits the complementary information offered by different semantic representations and takes advantage of the manifold structures of multiple representation spaces in a coherent manner. We demonstrate through extensive experiments that the proposed approach (1) rectifies the projection shift between the auxiliary and target domains, (2) exploits the complementarity of multiple semantic representations, (3) significantly outperforms existing methods for both zero-shot and N-shot recognition on three image and video benchmark datasets, and (4) enables novel cross-view annotation tasks.

The rapid development of social media sharing has created a huge demand for automatic media classification and annotation techniques. Attribute learning has emerged as a promising paradigm for bridging the semantic gap and addressing data sparsity via transferring attribute knowledge in object recognition and relatively simple action classification. In this paper, we address the task of attribute learning for understanding multimedia data with sparse and incomplete labels. In particular, we focus on videos of social group activities, which are particularly challenging and topical examples of this task because of their multimodal content and complex and unstructured nature relative to the density of annotations. To solve this problem, we 1) introduce a concept of semilatent attribute space, expressing user-defined and latent attributes in a unified framework, and 2) propose a novel scalable probabilistic topic model for learning multimodal semilatent attributes, which dramatically reduces requirements for an exhaustive accurate attribute ontology and expensive annotation effort. We show that our framework is able to exploit latent attributes to outperform contemporary approaches for addressing a variety of realistic multimedia sparse data learning tasks including: multitask learning, learning with label noise, N-shot transfer learning, and importantly zero-shot learning.

Interactive segmentation methods have greatly simplified the task of object cutout from an image. However, segmenting a large number of images in a collection is still a tedious task. In this paper, we present a content-sensitive group segmentation method that iteratively segments the images in a collection and incrementally refines the results. With our method, a user only provides a small number of strokes to segment and refine a few sample images. For each of the rest of images, our method finds relevant sample images and applies the corresponding appearance models to guide the segmentation. To improve the segmentation results using the user strokes on a few images with unsatisfactory segmentation results, our method calculates the relevance map that measures the probability that a stroke can be appropriately applied at each pixel/region of an image, and applies it accordingly. Our experiments show that our method can effectively segment an image collection with a wide variety of image content and significantly reduce user input.

Previous video summarization studies focused on monocular videos, and the results would not be good if they were applied to multi-view videos directly, due to problems such as the redundancy in multiple views. In this paper, we present a method for summarizing multi-view videos. We construct a spatio-temporal shot graph and formulate the summarization problem as a graph labeling task. The spatio-temporal shot graph is derived from a hypergraph, which encodes the correlations with different attributes among multi-view video shots in hyperedges. We then partition the shot graph and identify clusters of event-centered shots with similar contents via random walks. The summarization result is generated through solving a multi-objective optimization problem based on shot importance evaluated using a Gaussian entropy fusion scheme. Different summarization objectives, such as minimum summary length and maximum information coverage, can be accomplished in the framework. Moreover, multi-level summarization can be achieved easily by configuring the optimization parameters. We also propose the multi-view storyboard and event board for presenting multi-view summaries. The storyboard naturally reflects correlations among multi-view summarized shots that describe the same important event. The event-board serially assembles event-centered multi-view shots in temporal order. Single video summary which facilitates quick browsing of the summarized multi-view video can be easily generated based on the event board representation.