no code implementations • ECCV 2020 • Jibin Gao, Wei-Shi Zheng, Jia-Hui Pan, Chengying Gao, Yao-Wei Wang, Wei Zeng, Jian-Huang Lai
However, existing methods for action assessment are mostly limited to individual actions, especially lacking modeling of the asymmetric relations among agents (e. g., between persons and objects); and this limitation undermines their ability to assess actions containing asymmetrically interactive motion patterns, since there always exists subordination between agents in many interactive actions.
no code implementations • 15 Apr 2025 • Henghui Ding, Chang Liu, Nikhila Ravi, Shuting He, Yunchao Wei, Song Bai, Philip Torr, Kehuan Song, Xinglin Xie, Kexin Zhang, Licheng Jiao, Lingling Li, Shuyuan Yang, Xuqiang Cao, Linnan Zhao, Jiaxuan Zhao, Fang Liu, Mengjiao Wang, Junpei Zhang, Xu Liu, Yuting Yang, Mengru Ma, Hao Fang, Runmin Cong, Xiankai Lu, Zhiyang Chen, Wei zhang, Tianming Liang, Haichao Jiang, Wei-Shi Zheng, Jian-Fang Hu, Haobo Yuan, Xiangtai Li, Tao Zhang, Lu Qi, Ming-Hsuan Yang
This report provides a comprehensive overview of the 4th Pixel-level Video Understanding in the Wild (PVUW) Challenge, held in conjunction with CVPR 2025.
no code implementations • 31 Mar 2025 • Yu Zhou, Dian Zheng, Qijie Mo, Renjie Lu, Kun-Yu Lin, Wei-Shi Zheng
Through the theoretical framework, we point out that a class of previous methods could be mainly formulated as a loss that implicitly optimizes the forgetting term while lacking supervision for the retention term, disturbing the distribution of pre-trained model and struggling to adequately preserve knowledge of the remaining classes.
1 code implementation • 30 Mar 2025 • Tianming Liang, Haichao Jiang, Wei-Shi Zheng, Jian-Fang Hu
This task has attracted increasing attention in the field of computer vision due to its promising applications in video editing and human-agent interaction.
1 code implementation • 29 Mar 2025 • Guohong Huang, Ling-An Zeng, Zexin Zheng, Shengbo Gu, Wei-Shi Zheng
We propose a novel approach for generating text-guided human-object interactions (HOIs) that achieves explicit joint-level interaction modeling in a computationally efficient manner.
1 code implementation • 28 Mar 2025 • Wei-Jin Huang, Yuan-Ming Li, Zhi-Wei Xia, Yu-Ming Tang, Kun-Yu Lin, Jian-Fang Hu, Wei-Shi Zheng
Extensive experiments demonstrate that AMNAR achieves state-of-the-art performance, highlighting the effectiveness of AMNAR and the importance of modeling multiple valid next actions in error detection.
1 code implementation • 27 Mar 2025 • Dian Zheng, Ziqi Huang, Hongbo Liu, Kai Zou, Yinan He, Fan Zhang, Yuanhan Zhang, Jingwen He, Wei-Shi Zheng, Yu Qiao, Ziwei Liu
To bridge this gap, we introduce VBench-2. 0, a next-generation benchmark designed to automatically evaluate video generative models for their intrinsic faithfulness.
1 code implementation • 24 Mar 2025 • Dian Zheng, Cheng Zhang, Xiao-Ming Wu, Cao Li, Chengfei Lv, Jian-Fang Hu, Wei-Shi Zheng
To address the phenomenon, we propose \textbf{PanoDecouple}, a decoupled diffusion model framework, which decouples the panorama generation into distortion guidance and content completion, aiming to generate panoramas with both accurate distortion and visual appeal.
1 code implementation • 18 Mar 2025 • Junjin Xiao, Qing Zhang, Yonewei Nie, Lei Zhu, Wei-Shi Zheng
To account for possible misalignment between SMPL model and images, we propose to predict image-aligned 3D prior points by leveraging both pixel-level features and voxel-level features, from which we regress the coarse Gaussians.
1 code implementation • 17 Mar 2025 • Ling-An Zeng, Gaojie Wu, AnCong Wu, Jian-Fang Hu, Wei-Shi Zheng
Hence, we propose a novel Progressive Motion Generation (PMG) method to progressively generate a motion from the frames with low uncertainty to those with high uncertainty in multiple stages.
1 code implementation • 13 Mar 2025 • Shenghao Fu, Junkai Yan, Qize Yang, Xihan Wei, Xiaohua Xie, Wei-Shi Zheng
In this work, we propose a hierarchical semantic distillation framework named HD-OVD to construct a comprehensive distillation process, which exploits generalizable knowledge from the CLIP model in three aspects.
no code implementations • 12 Mar 2025 • Jian-Jian Jiang, Xiao-Ming Wu, Yi-Xiang He, Ling-An Zeng, Yi-Lin Wei, Dandan Zhang, Wei-Shi Zheng
Extensive experiments on seven tasks in the RoboTwin dataset demonstrate that: (1) Our framework achieves outstanding performance, with a 23. 5% boost over the SOTA method.
no code implementations • 24 Feb 2025 • An-Lan Wang, Nuo Chen, Kun-Yu Lin, Li Yuan-Ming, Wei-Shi Zheng
With an aim to get more general and practical grasp models, in this paper, we investigate the problem named Task-Oriented 6-DoF Grasp Pose Detection in Clutters (TO6DGC), which extends the task-oriented problem to a more general 6-DOF Grasp Pose Detection in Cluttered (multi-object) scenario.
no code implementations • 4 Feb 2025 • Shengbo Gu, Yu-Kun Qiu, Yu-Ming Tang, AnCong Wu, Wei-Shi Zheng
In this work, we propose a maintainable avatar (MaintaAvatar) based on neural radiance fields by continual learning, which resolves the issues by utilizing a Global-Local Joint Storage Module and a Pose Distillation Module.
1 code implementation • 31 Jan 2025 • Shenghao Fu, Qize Yang, Qijie Mo, Junkai Yan, Xihan Wei, Jingke Meng, Xiaohua Xie, Wei-Shi Zheng
In this work, we show that an open-vocabulary detector co-training with a large language model by generating image-level detailed captions for each image can further improve performance.
no code implementations • 24 Jan 2025 • Tianming Liang, Kun-Yu Lin, Chaolei Tan, JianGuo Zhang, Wei-Shi Zheng, Jian-Fang Hu
Referring video object segmentation (RVOS) aims to segment target objects throughout a video based on a text description.
no code implementations • 16 Dec 2024 • Delong Zhang, Qiwei Huang, Yuanliu liu, Yang Sun, Wei-Shi Zheng, Pengfei Xiong, Wei zhang
Image-based virtual try-on is challenging since the generated image should fit the garment to model images in various poses and keep the characteristics and details of the garment simultaneously.
1 code implementation • 15 Dec 2024 • Ling-An Zeng, Guohong Huang, Gaojie Wu, Wei-Shi Zheng
Despite the significant role text-to-motion (T2M) generation plays across various applications, current methods involve a large number of parameters and suffer from slow inference speeds, leading to high usage costs.
no code implementations • 26 Nov 2024 • Yuan-Ming Li, An-Lan Wang, Kun-Yu Lin, Yu-Ming Tang, Ling-An Zeng, Jian-Fang Hu, Wei-Shi Zheng
To bridge this gap, we investigate a new task termed Descriptive Action Coaching (DescCoach) which requires the model to provide detailed commentary on what is done well and what can be improved beyond a simple quality score for action execution.
1 code implementation • 25 Nov 2024 • Zuhao Liu, Aleksandar Yanev, Ahmad Mahmood, Ivan Nikolov, Saman Motamed, Wei-Shi Zheng, Xi Wang, Luc van Gool, Danda Pani Paudel
Advances in video generation have significantly improved the realism and quality of created scenes.
no code implementations • 25 Oct 2024 • Shenghao Fu, Junkai Yan, Qize Yang, Xihan Wei, Xiaohua Xie, Wei-Shi Zheng
First, the class token in foundation models provides an in-depth understanding of the complex scene, which facilitates decoding object queries in the detector's decoder by providing a compact context.
1 code implementation • 25 Aug 2024 • Jia-Run Du, Kun-Yu Lin, Jingke Meng, Wei-Shi Zheng
To address this problem, in this work, we propose a novel model named Generalizable Action Proposal generator (GAP), which can interface seamlessly with CLIP and generate action proposals in a holistic way.
1 code implementation • 23 Aug 2024 • An-Lan Wang, Bin Shan, Wei Shi, Kun-Yu Lin, Xiang Fei, Guozhi Tang, Lei Liao, Jingqun Tang, Can Huang, Wei-Shi Zheng
This work presents ParGo, a novel Partial-Global projector designed to connect the vision and language modalities for Multimodal Large Language Models (MLLMs).
1 code implementation • 10 Aug 2024 • Delong Zhang, Yi-Xing Peng, Xiao-Ming Wu, AnCong Wu, Wei-Shi Zheng
Previous privacy-preserving person re-identification methods are unable to resist recovery attacks and compromise accuracy.
no code implementations • 9 Aug 2024 • Huilin Tian, Jingke Meng, Wei-Shi Zheng, Yuan-Ming Li, Junkai Yan, Yunong Zhang
The main idea behind Loc4Plan is to perform the spatial localization before planning a decision action based on corresponding guidance, which comprises a block-aware spatial locating (BAL) module and a spatial-aware action planning (SAP) module.
no code implementations • 3 Aug 2024 • Chaolei Tan, Zihang Lin, Junfu Pu, Zhongang Qi, Wei-Yi Pei, Zhi Qu, Yexin Wang, Ying Shan, Wei-Shi Zheng, Jian-Fang Hu
Based on the dataset, we further introduce a more complex setting of video grounding dubbed Multi-Paragraph Video Grounding (MPVG), which takes as input multiple paragraphs and a long video for grounding each paragraph query to its temporal interval.
1 code implementation • 16 Jul 2024 • Qijie Mo, Yipeng Gao, Shenghao Fu, Junkai Yan, AnCong Wu, Wei-Shi Zheng
To overcome this problem, we propose a method called ``Bridge Past and Future'' (BPF), which aligns models across stages, ensuring consistent optimization directions.
1 code implementation • 16 Jul 2024 • Renjie Lu, Jingke Meng, Wei-Shi Zheng
In this work, we propose an alternative method that facilitates navigation planning by considering the alignment between instructions and directed fidelity trajectories, which refers to a path from the initial node to the candidate locations on a directed graph without detours.
no code implementations • 15 Jul 2024 • Kun-Yu Lin, Jiaming Zhou, Wei-Shi Zheng
However, existing methods are prone to losing human cues but prefer to exploit the correlation between non-human contexts and associated actions for recognition, and the contexts of interest agnostic to actions would reduce recognition performance in the target domain.
1 code implementation • 11 Jul 2024 • Xiao-Ming Wu, Jia-Feng Cai, Jian-Jian Jiang, Dian Zheng, Yi-Lin Wei, Wei-Shi Zheng
In this work, we propose an economic framework for 6-DoF grasp detection, aiming to economize the resource cost in training and meanwhile maintain effective grasp performance.
1 code implementation • 10 Jul 2024 • Yu-Ming Tang, Yi-Xing Peng, Jingke Meng, Wei-Shi Zheng
In this work, as a complement to existing metrics, we offer a new metric called generalized average accuracy (gAcc) which is designed to provide an extra equitable evaluation by incorporating different perspectives of the performance under the guidance of a parameter $\alpha$.
class-incremental learning
Few-Shot Class-Incremental Learning
+1
1 code implementation • 13 Jun 2024 • Yuan-Ming Li, Wei-Jin Huang, An-Lan Wang, Ling-An Zeng, Jing-Ke Meng, Wei-Shi Zheng
To facilitate research on egocentric and exocentric full-body action understanding, we construct benchmarks on a suite of tasks (i. e., action classification, action localization, cross-view sequence verification, cross-view skill determination, and a newly proposed task of guidance-based execution verification), together with detailed analysis.
no code implementations • CVPR 2024 • Yan-Kang Wang, Chengyi Xing, Yi-Lin Wei, Xiao-Ming Wu, Wei-Shi Zheng
Thus, we introduce S2HGrasp, a framework composed of two key modules: the Global Perception module that globally perceives partial object point clouds, and the DiffuGrasp module designed to generate high-quality human grasps based on complex inputs that include scene points.
1 code implementation • 9 Apr 2024 • Junkai Yan, Yipeng Gao, Qize Yang, Xihan Wei, Xuansong Xie, AnCong Wu, Wei-Shi Zheng
Text-to-3D generation, which synthesizes 3D assets according to an overall text description, has significantly progressed.
1 code implementation • CVPR 2024 • Angchi Xu, Wei-Shi Zheng
Weakly-supervised action segmentation is a task of learning to partition a long video into several action segments, where training videos are only accompanied by transcripts (ordered list of actions).
no code implementations • CVPR 2024 • Tianming Liang, Chaolei Tan, Beihao Xia, Wei-Shi Zheng, Jian-Fang Hu
This paper focuses on open-ended video question answering, which aims to find the correct answers from a large answer set in response to a video-related question.
no code implementations • CVPR 2024 • Chaolei Tan, JianHuang Lai, Wei-Shi Zheng, Jian-Fang Hu
Different from previous weakly-supervised grounding frameworks based on multiple instance learning or reconstruction learning for two-stage candidate ranking, we propose a novel siamese learning framework that jointly learns the cross-modal feature alignment and temporal coordinate regression without timestamp labels to achieve concise one-stage localization for WSVPG.
1 code implementation • 17 Mar 2024 • Wei-Shi Zheng, Junkai Yan, Yi-Xing Peng
To overcome significant variations between images across camera views, mountains of variants of ReID models were developed for solving a number of challenges, such as resolution change, clothing change, occlusion, modality change, and so on.
1 code implementation • CVPR 2024 • Dian Zheng, Xiao-Ming Wu, Shuzhou Yang, Jian Zhang, Jian-Fang Hu, Wei-Shi Zheng
Universal image restoration is a practical and potential computer vision task for real-world applications.
1 code implementation • CVPR 2024 • Junjin Xiao, Qing Zhang, Zhan Xu, Wei-Shi Zheng
The core of our approach is to represent humans in complementary dual spaces and predict disentangled neural fields of geometry, albedo, shadow, as well as an external lighting, from which we are able to derive realistic rendering with high-frequency details via volumetric rendering.
1 code implementation • 3 Mar 2024 • Kun-Yu Lin, Henghui Ding, Jiaming Zhou, Yu-Ming Tang, Yi-Xing Peng, Zhilin Zhao, Chen Change Loy, Wei-Shi Zheng
To answer this, we establish a CROSS-domain Open-Vocabulary Action recognition benchmark named XOV-Action, and conduct a comprehensive evaluation of five state-of-the-art CLIP-based video learners under various types of domain gaps.
1 code implementation • 31 Jan 2024 • Ling-An Zeng, Wei-Shi Zheng
To leverage multimodal information for AQA, i. e., RGB, optical flow and audio information, we propose a Progressive Adaptive Multimodal Fusion Network (PAMFN) that separately models modality-specific information and mixed-modality information.
no code implementations • 22 Jan 2024 • Jiaming Zhou, Junwei Liang, Kun-Yu Lin, Jinrui Yang, Wei-Shi Zheng
With the proposed ActionHub dataset, we further propose a novel Cross-modality and Cross-action Modeling (CoCo) framework for ZSAR, which consists of a Dual Cross-modality Alignment module and a Cross-action Invariance Mining module.
1 code implementation • 13 Jan 2024 • Mang Ye, Shuoyi Chen, Chenyue Li, Wei-Shi Zheng, David Crandall, Bo Du
Object Re-identification (Re-ID) aims to identify specific objects across different times and scenes, which is a widely researched task in computer vision.
no code implementations • 4 Dec 2023 • Dixuan Lin, Yixing Peng, Jingke Meng, Wei-Shi Zheng
In this work, we show the discrepancy between image-to-text association and text-to-image association and propose CADA: Cross-Modal Adaptive Dual Association that finely builds bidirectional image-text detailed associations.
Ranked #1 on
Text based Person Retrieval
on RSTPReid
(Rank-1 metric)
1 code implementation • 14 Nov 2023 • Zhilin Zhao, Longbing Cao, Yixuan Zhang, Kun-Yu Lin, Wei-Shi Zheng
This paper introduces OOD knowledge distillation, a pioneering learning framework applicable whether or not training ID data is available, given a standard network.
1 code implementation • CVPR 2024 • Yipeng Gao, Zeyu Wang, Wei-Shi Zheng, Cihang Xie, Yuyin Zhou
Contrastive learning has emerged as a promising paradigm for 3D open-world understanding, i. e., aligning point cloud representation to image and text embedding space individually.
Ranked #1 on
Zero-shot 3D classification
on Objaverse LVIS
(using extra training data)
1 code implementation • 29 Sep 2023 • Yuan-Ming Li, Ling-An Zeng, Jing-Ke Meng, Wei-Shi Zheng
Our idea for modeling Continual-AQA is to sequentially learn a task-consistent score-discriminative feature distribution, in which the latent features express a strong correlation with the score labels regardless of the task or action types. From this perspective, we aim to mitigate the forgetting in Continual-AQA from two aspects.
no code implementations • 30 Aug 2023 • Dian Zheng, Xiao-Ming Wu, Zuhao Liu, Jingke Meng, Wei-Shi Zheng
Our method, termed DiffuVolume, considers the diffusion model as a cost volume filter, which will recurrently remove the redundant information from the cost volume.
1 code implementation • ICCV 2023 • Yu-Ming Tang, Yi-Xing Peng, Wei-Shi Zheng
However, existing prompt-based methods heavily rely on strong pretraining (typically trained on ImageNet-21k), and we find that their models could be trapped if the potential gap between the pretraining task and unknown future tasks is large.
1 code implementation • ICCV 2023 • Shenghao Fu, Junkai Yan, Yipeng Gao, Xiaohua Xie, Wei-Shi Zheng
We find that the architecture discrepancy between dense and sparse detectors leads to feature conflict, hampering the performance of one-decoder-layer detectors.
no code implementations • ICCV 2023 • An-Lan Wang, Kun-Yu Lin, Jia-Run Du, Jingke Meng, Wei-Shi Zheng
In this work, we focus on the task of procedure planning from instructional videos with text supervision, where a model aims to predict an action sequence to transform the initial visual state into the goal visual state.
1 code implementation • ICCV 2023 • Xiao-Ming Wu, Dian Zheng, Zuhao Liu, Wei-Shi Zheng
The pioneering work BinaryConnect uses Straight Through Estimator (STE) to mimic the gradients of the sign function, but it also causes the crucial inconsistency problem.
no code implementations • 19 Jul 2023 • Jia-Xin Zhuang, Jiabin Cai, JianGuo Zhang, Wei-Shi Zheng, Ruixuan Wang
The CARE framework needs bounding boxes to represent the lesion regions of rare diseases.
no code implementations • 11 May 2023 • Qing Zhang, Hao Jiang, Yongwei Nie, Wei-Shi Zheng
We present a simple but effective technique to smooth out textures while preserving the prominent structures.
1 code implementation • 18 Apr 2023 • Wentao Zhang, Yujun Huang, Tong Zhang, Qingsong Zou, Wei-Shi Zheng, Ruixuan Wang
In particular, updating an intelligent diagnosis system with training data of new diseases would cause catastrophic forgetting of old disease knowledge.
1 code implementation • CVPR 2023 • Jiawei Feng, AnCong Wu, Wei-Shi Zheng
To this end, we propose shape-erased feature learning paradigm that decorrelates modality-shared features in two orthogonal subspaces.
no code implementations • 7 Apr 2023 • Gaojie Wu, Wei-Shi Zheng, Yutong Lu, Qi Tian
In this work, we propose a ladder self-attention block with multiple branches and a progressive shift mechanism to develop a light-weight transformer backbone that requires less computing resources (e. g. a relatively small number of parameters and FLOPs), termed Progressive Shift Ladder Transformer (PSLT).
1 code implementation • 3 Feb 2023 • Jiayu Jiao, Yu-Ming Tang, Kun-Yu Lin, Yipeng Gao, Jinhua Ma, YaoWei Wang, Wei-Shi Zheng
In this work, we explore effective Vision Transformers to pursue a preferable trade-off between the computational complexity and size of the attended receptive field.
no code implementations • 18 Jan 2023 • Kanghao Chen, Sijia Liu, Ruixuan Wang, Wei-Shi Zheng
The first one is to adaptively integrate multiple levels of old knowledge and transfer it to each block level in the new model.
no code implementations • CVPR 2023 • Chaolei Tan, Zihang Lin, Jian-Fang Hu, Wei-Shi Zheng, JianHuang Lai
Specifically, we develop a hierarchical encoder that encodes the multi-modal inputs into semantics-aligned representations at different levels.
no code implementations • CVPR 2023 • Zihang Lin, Chaolei Tan, Jian-Fang Hu, Zhi Jin, Tiancai Ye, Wei-Shi Zheng
The static stream performs cross-modal understanding in a single frame and learns to attend to the target object spatially according to intra-frame visual cues like object appearances.
1 code implementation • CVPR 2023 • Yipeng Gao, Kun-Yu Lin, Junkai Yan, YaoWei Wang, Wei-Shi Zheng
Critically, in FSDAOD, the data-scarcity in the target domain leads to an extreme data imbalance between the source and target domains, which potentially causes over-adaptation in traditional feature alignment.
no code implementations • CVPR 2023 • Zuhao Liu, Xiao-Ming Wu, Dian Zheng, Kun-Yu Lin, Wei-Shi Zheng
There also exists a scene gap between virtual and real scenarios, including scene-specific anomalies (events that are abnormal in one scene but normal in another) and scene-specific attributes, such as the viewpoint of the surveillance camera.
Anomaly Detection In Surveillance Videos
Video Anomaly Detection
1 code implementation • ICCV 2023 • Xiaoyuan Guan, Zhouwu Liu, Wei-Shi Zheng, Yuren Zhou, Ruixuan Wang
Out-of-distribution (OOD) detection is a desired ability to ensure the reliability and safety of intelligent systems.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
1 code implementation • IEEE Transactions on Image Processing 2022 • Shuguang Dou, Cairong Zhao, Xinyang Jiang, Shanshan Zhang, Wei-Shi Zheng, WangMeng Zuo
Most supervised methods propose to train an extra human parsing model aside from the ReID model with cross-domain human parts annotation, suffering from expensive annotation cost and domain gap; Unsupervised methods integrate a feature clustering-based human parsing process into the ReID model, but lacking supervision signals brings less satisfactory segmentation results.
Ranked #9 on
Person Re-Identification
on Occluded-DukeMTMC
no code implementations • 27 Sep 2022 • Chengzhi Lin, AnCong Wu, Junwei Liang, Jun Zhang, Wenhang Ge, Wei-Shi Zheng, Chunhua Shen
To address this problem, we propose a Text-Adaptive Multiple Visual Prototype Matching model, which automatically captures multiple prototypes to describe a video by adaptive aggregation of video token features.
1 code implementation • 22 Sep 2022 • Yipeng Gao, Lingxiao Yang, Yunmu Huang, Song Xie, Shiyong Li, Wei-Shi Zheng
Under the domain shift, cross-domain few-shot object detection aims to adapt object detectors in the target domain with a few annotated target data.
Cross-Domain Few-Shot
Cross-Domain Few-Shot Object Detection
+3
no code implementations • 14 Jul 2022 • Chenghua Zeng, Huijuan Lu, Kanghao Chen, Ruixuan Wang, Wei-Shi Zheng
Data imbalance between common and rare diseases during model training often causes intelligent diagnosis systems to have biased predictions towards common diseases.
no code implementations • 11 Jul 2022 • Kanghao Chen, Weixian Lei, Rong Zhang, Shen Zhao, Wei-Shi Zheng, Ruixuan Wang
For the class-center involved triplet loss, the positive and negative samples in each triplet are replaced by their corresponding class centers, which enforces data representations of the same class closer to the class center.
no code implementations • 6 Jul 2022 • Zihang Lin, Chaolei Tan, Jian-Fang Hu, Zhi Jin, Tiancai Ye, Wei-Shi Zheng
The static branch performs cross-modal understanding in a single frame and learns to localize the target object spatially according to intra-frame visual cues like object appearances.
Ranked #3 on
Spatio-Temporal Video Grounding
on HC-STVG2
1 code implementation • 4 Jul 2022 • Yaojia Zheng, Zhouwu Liu, Rong Mo, Ziyi Chen, Wei-Shi Zheng, Ruixuan Wang
Compared to supervised learning with labelled disease EEG data which can train a model to analyze specific diseases but would fail to monitor previously unseen statuses, anomaly detection based on only normal EEGs can detect any potential anomaly in new EEGs.
2 code implementations • 22 Jun 2022 • Jia-Run Du, Jia-Chang Feng, Kun-Yu Lin, Fa-Ting Hong, Xiao-Ming Wu, Zhongang Qi, Ying Shan, Wei-Shi Zheng
Accordingly, we first exclude these surely non-existent categories by a complementary learning loss.
Ranked #1 on
Weakly Supervised Action Localization
on THUMOS' 14
1 code implementation • 19 Jun 2022 • Jianxiong Tang, JianHuang Lai, Xiaohua Xie, Lingxiao Yang, Wei-Shi Zheng
The SNN2ANN consists of 2 components: a) a weight sharing architecture between ANN and SNN and b) spiking mapping units.
no code implementations • 28 Apr 2022 • Yang Yang, Zhiying Cui, Junjie Xu, Changhong Zhong, Wei-Shi Zheng, Ruixuan Wang
In this case, updating the intelligent system with data of new diseases would inevitably downgrade its performance on previously learned diseases.
1 code implementation • 27 Apr 2022 • Xin Zhang, Xiaohua Xie, JianHuang Lai, Wei-Shi Zheng
To address this issue, we propose a pedestrian retrieval framework based on cross-camera trajectory generation, which integrates both temporal and spatial information.
1 code implementation • CVPR 2022 • Yu-Ming Tang, Yi-Xing Peng, Wei-Shi Zheng
The diverse generated samples could effectively prevent DNN from forgetting when learning new tasks.
1 code implementation • CVPR 2022 • Hanjun Li, Xingjia Pan, Ke Yan, Fan Tang, Wei-Shi Zheng
Object detection under imperfect data receives great attention recently.
no code implementations • 7 Mar 2022 • Peipei Zhu, Xiao Wang, Yong Luo, Zhenglong Sun, Wei-Shi Zheng, YaoWei Wang, Changwen Chen
The image-level labels are utilized to train a weakly-supervised object recognition model to extract object information (e. g., instance) in an image, and the extracted instances are adopted to infer the relationships among different objects based on an enhanced graph neural network (GNN).
no code implementations • CVPR 2022 • Angchi Xu, Ling-An Zeng, Wei-Shi Zheng
Long-term action quality assessment is a task of evaluating how well an action is performed, namely, estimating a quality score from a long video.
Ranked #1 on
Action Quality Assessment
on Rhythmic Gymnastic
no code implementations • 6 Dec 2021 • Zelin Chen, Hong-Xing Yu, AnCong Wu, Wei-Shi Zheng
To make the application of writer-id more practical (e. g., on mobile devices), we focus on a novel problem, letter-level online writer-id, which requires only a few trajectories of written letters as identification cues.
no code implementations • NeurIPS 2021 • Jiangxin Sun, Zihang Lin, Xintong Han, Jian-Fang Hu, Jia Xu, Wei-Shi Zheng
The ability of forecasting future human motion is important for human-machine interaction systems to understand human behaviors and make interaction.
1 code implementation • 25 Aug 2021 • Jia-Xin Zhuang, Wanying Tao, Jianfei Xing, Wei Shi, Ruixuan Wang, Wei-Shi Zheng
In this paper, a simple yet effective optimization method is proposed to interpret the activation of any kernel of interest in CNN models.
no code implementations • 11 Aug 2021 • Changhong Zhong, Zhiying Cui, Ruixuan Wang, Wei-Shi Zheng
Successful continual learning of new knowledge would enable intelligent systems to recognize more and more classes of objects.
1 code implementation • 29 Jul 2021 • Wenhang Ge, Chunyan Pan, AnCong Wu, Hongwei Zheng, Wei-Shi Zheng
To learn camera-invariant representation from cross-camera unpaired training data, we propose a cross-camera feature prediction method to mine cross-camera self supervision information from camera-specific feature distribution by transforming fake cross-camera positive feature pairs and minimize the distances of the fake pairs.
1 code implementation • Proceedings of the 29th ACM International Conference on Multimedia 2021 • Fa-Ting Hong, Jia-Chang Feng, Dan Xu, Ying Shan, Wei-Shi Zheng
In this work, we argue that the features extracted from the pretrained extractor, e. g., I3D, are not the WS-TALtask-specific features, thus the feature re-calibration is needed for reducing the task-irrelevant information redundancy.
Weakly-supervised Temporal Action Localization
Weakly Supervised Temporal Action Localization
2 code implementations • 27 Jul 2021 • Fa-Ting Hong, Jia-Chang Feng, Dan Xu, Ying Shan, Wei-Shi Zheng
In this work, we argue that the features extracted from the pretrained extractor, e. g., I3D, are not the WS-TALtask-specific features, thus the feature re-calibration is needed for reducing the task-irrelevant information redundancy.
Weakly Supervised Action Localization
Weakly-supervised Temporal Action Localization
+1
1 code implementation • 20 Jul 2021 • ShaoHao Lu, Yuqiao Xian, Ke Yan, Yi Hu, Xing Sun, Xiaowei Guo, Feiyue Huang, Wei-Shi Zheng
The Deep Neural Networks are vulnerable toadversarial exam-ples(Figure 1), making the DNNs-based systems collapsed byadding the inconspicuous perturbations to the images.
no code implementations • 20 Jun 2021 • Chaolei Tan, Zihang Lin, Jian-Fang Hu, Xiang Li, Wei-Shi Zheng
We propose an effective two-stage approach to tackle the problem of language-based Human-centric Spatio-Temporal Video Grounding (HC-STVG) task.
no code implementations • CVPR 2021 • Jiaming Zhou, Kun-Yu Lin, Haoxin Li, Wei-Shi Zheng
In this paper, we propose a Graph-based High-order Relation Modeling (GHRM) module to exploit the high-order relations in the long-term actions for long-term action recognition.
Ranked #5 on
Long-video Activity Recognition
on Breakfast
1 code implementation • CVPR 2021 • Jiaxing Chen, Xinyang Jiang, Fudong Wang, Jun Zhang, Feng Zheng, Xing Sun, Wei-Shi Zheng
In this paper, rather than relying on texture based information, we propose to improve the robustness of person ReID against clothing texture by exploiting the information of a person's 3D shape.
Ranked #4 on
Person Re-Identification
on VC-Clothes
no code implementations • CVPR 2021 • Peixian Hong, Tao Wu, AnCong Wu, Xintong Han, Wei-Shi Zheng
Recently, person re-identification (Re-ID) has achieved great progress.
Ranked #5 on
Person Re-Identification
on VC-Clothes
1 code implementation • 29 Apr 2021 • Yichao Yan, Jie Qin, Bingbing Ni, Jiaxin Chen, Li Liu, Fan Zhu, Wei-Shi Zheng, Xiaokang Yang, Ling Shao
Extensive experiments on the novel dataset as well as three existing datasets clearly demonstrate the effectiveness of the proposed framework for both group-based re-id tasks.
no code implementations • 28 Apr 2021 • Zhuoyun Li, Changhong Zhong, Sijia Liu, Ruixuan Wang, Wei-Shi Zheng
In order to reduce the forgetting of particularly earlier learned old knowledge and improve the overall continual learning performance, we propose a simple yet effective fusion mechanism by including all the previously learned feature extractors into the intelligent model.
1 code implementation • CVPR 2021 • Hanjun Li, Gaojie Wu, Wei-Shi Zheng
We propose a novel search space called Combined Depth Space (CDS), based on which we search for an efficient network architecture, which we call CDNet, via a differentiable architecture search algorithm.
1 code implementation • CVPR 2021 • Jia-Chang Feng, Fa-Ting Hong, Wei-Shi Zheng
Weakly supervised video anomaly detection (WS-VAD) is to distinguish anomalies from normal events based on discriminative representations.
1 code implementation • 1 Mar 2021 • Yang Yang, Jiancong Chen, Ruixuan Wang, Ting Ma, Lingwei Wang, Jie Chen, Wei-Shi Zheng, Tong Zhang
Despite tremendous efforts, it is very challenging to generate a robust model to assist in the accurate quantification assessment of COVID-19 on chest CT images.
1 code implementation • ICCV 2021 • Shizhen Zhao, Changxin Gao, Yuanjie Shao, Wei-Shi Zheng, Nong Sang
Specifically, to alleviate the intra-class variations, a clustering method is utilized to generate pseudo labels for both visual and textual instances.
no code implementations • ICCV 2021 • Zihang Lin, Jiangxin Sun, Jian-Fang Hu, QiZhi Yu, Jian-Huang Lai, Wei-Shi Zheng
In the latent feature learned by the autoencoder, global structures are enhanced and local details are suppressed so that it is more predictive.
no code implementations • ICCV 2021 • Jinrui Yang, Jiawei Zhang, Fufu Yu, Xinyang Jiang, Mengdan Zhang, Xing Sun, Ying-Cong Chen, Wei-Shi Zheng
Several mainstream methods utilize extra cues (e. g., human pose information) to distinguish human parts from obstacles to alleviate the occlusion problem.
Ranked #24 on
Person Re-Identification
on Occluded-DukeMTMC
1 code implementation • 10 Dec 2020 • Enwei Zhang, Xinyang Jiang, Hao Cheng, AnCong Wu, Fufu Yu, Ke Li, Xiaowei Guo, Feng Zheng, Wei-Shi Zheng, Xing Sun
Current training objectives of existing person Re-IDentification (ReID) models only ensure that the loss of the model decreases on selected training batch, with no regards to the performance on samples outside the batch.
no code implementations • ECCV 2020 • Hai Wang, Wei-Shi Zheng, Ling Yingbiao
However, previous graph models regard human and object as the same kind of nodes and do not consider that the messages are not equally the same between different entities.
1 code implementation • 11 Sep 2020 • Fufu Yu, Xinyang Jiang, Yifei Gong, Shizhen Zhao, Xiaowei Guo, Wei-Shi Zheng, Feng Zheng, Xing Sun
Secondly, the Conditional Feature Embedding requires the overall feature of a query image to be dynamically adjusted based on the gallery image it matches, while most of the existing methods ignore the reference images.
Ranked #1 on
Person Re-Identification
on CUHK03-C
1 code implementation • ECCV 2020 • Shizhen Zhao, Changxin Gao, Jun Zhang, Hao Cheng, Chuchu Han, Xinyang Jiang, Xiaowei Guo, Wei-Shi Zheng, Nong Sang, Xing Sun
In the conventional person Re-ID setting, it is widely assumed that cropped person images are for each individual.
2 code implementations • 13 Aug 2020 • Ling-An Zeng, Fa-Ting Hong, Wei-Shi Zheng, Qi-Zhi Yu, Wei Zeng, Yao-Wei Wang, Jian-Huang Lai
However, most existing works focus only on video dynamic information (i. e., motion information) but ignore the specific postures that an athlete is performing in a video, which is important for action assessment in long videos.
Ranked #2 on
Action Quality Assessment
on Rhythmic Gymnastic
no code implementations • ECCV 2020 • Fa-Ting Hong, Xuanteng Huang, Wei-Hong Li, Wei-Shi Zheng
We address the weakly supervised video highlight detection problem for learning to detect segments that are more attractive in training videos given their video event label but without expensive supervision of manually annotating highlight segments.
1 code implementation • CVPR 2020 • Haoxin Li, Wei-Shi Zheng, Yu Tao, Haifeng Hu, Jian-Huang Lai
We propose to search the network structures with differentiable architecture search mechanism, which learns to construct adaptive structures for different videos to facilitate adaptive interaction modeling.
1 code implementation • CVPR 2020 • Fa-Ting Hong, Wei-Hong Li, Wei-Shi Zheng
Important people detection is to automatically detect the individuals who play the most important roles in a social event image, which requires the designed model to understand a high-level pattern.
2 code implementations • CVPR 2020 • Hong-Xing Yu, Wei-Shi Zheng
We evaluate our model on unsupervised person re-identification and pose-invariant face recognition.
2 code implementations • 6 Feb 2020 • Qize Yang, An-Cong Wu, Wei-Shi Zheng
Substantial development of re-id has recently been observed, and the majority of existing models are largely dependent on color appearance and assume that pedestrians do not change their clothes across camera views.
1 code implementation • 3 Dec 2019 • Zhihui Zhu, Xinyang Jiang, Feng Zheng, Xiaowei Guo, Feiyue Huang, Wei-Shi Zheng, Xing Sun
Instead of one subspace for each viewpoint, our method projects the feature from different viewpoints into a unified hypersphere and effectively models the feature distribution on both the identity-level and the viewpoint-level.
Ranked #7 on
Person Re-Identification
on DukeMTMC-reID
(using extra training data)
2 code implementations • 28 Nov 2019 • Xinyang Jiang, Yifei Gong, Xiaowei Guo, Qize Yang, Feiyue Huang, Wei-Shi Zheng, Feng Zheng, Xing Sun
Recently, the research interest of person re-identification (ReID) has gradually turned to video-based methods, which acquire a person representation by aggregating frame features of an entire video.
no code implementations • 31 Oct 2019 • Zhirui Chen, Jianheng Li, Wei-Shi Zheng
The scalability problem caused by the difficulty in annotating Person Re-identification(Re-ID) datasets has become a crucial bottleneck in the development of Re-ID. To address this problem, many unsupervised Re-ID methods have recently been proposed. Nevertheless, most of these models require transfer from another auxiliary fully supervised dataset, which is still expensive to obtain. In this work, we propose a Re-ID model based on Weakly Supervised Tracklets(WST) data from various camera views, which can be inexpensively acquired by combining the fragmented tracklets of the same person in the same camera view over a period of time. We formulate our weakly supervised tracklets Re-ID model by a novel method, named deep feature-wise mutual learning(DFML), which consists of Mutual Learning on Feature Extractors (MLFE) and Mutual Learning on Feature Classifiers (MLFC). We propose MLFE by leveraging two feature extractors to learn from each other to extract more robust and discriminative features. On the other hand, we propose MLFC by adapting discriminative features from various camera views to each classifier.
2 code implementations • 30 Oct 2019 • Qing Zhang, Yongwei Nie, Wei-Shi Zheng
By performing dual illumination estimation, we obtain two intermediate exposure correction results for the input image, with one fixes the underexposed regions and the other one restores the overexposed regions.
no code implementations • 21 Oct 2019 • Jiabo Huang, Xiaohua Xie, Wei-Shi Zheng
This paper studies the problem of aligning a set of face images of the same individual into a normalized image while removing the outliers like partial occlusion, extreme facial expression as well as significant illumination variation.
no code implementations • 30 Sep 2019 • Guang-Yuan Hao, Hong-Xing Yu, Wei-Shi Zheng
We focus on explicitly learning disentangled representation for natural image generation, where the underlying spatial structure and the rendering on the structure can be independently controlled respectively, yet using no tuple supervision.
4 code implementations • CVPR 2020 • Zilong Zhong, Zhong Qiu Lin, Rene Bidart, Xiaodan Hu, Ibrahim Ben Daya, Zhifeng Li, Wei-Shi Zheng, Jonathan Li, Alexander Wong
The recent integration of attention mechanisms into segmentation networks improves their representational capabilities through a great emphasis on more informative features.
Ranked #6 on
Semantic Segmentation
on PASCAL VOC 2012 test
1 code implementation • 26 Jul 2019 • Shuosen Guan, Haoxin Li, Wei-Shi Zheng
Most of current Convolution Neural Network (CNN) based methods for optical flow estimation focus on learning optical flow on synthetic datasets with groundtruth, which is not practical.
no code implementations • 25 Jul 2019 • Qing Zhang, Yongwei Nie, Lei Zhu, Chunxia Xiao, Wei-Shi Zheng
To obtain high-quality results free of these artifacts, we present a novel underexposed photo enhancement approach that is able to maintain the perceptual consistency.
no code implementations • 1 Jul 2019 • Jiechao Ma, Sen Liang, Xiang Li, Hongwei Li, Bjoern H. Menze, Rongguo Zhang, Wei-Shi Zheng
Mammogram is the most effective imaging modality for the mass lesion detection of breast cancer at the early stage.
no code implementations • CVPR 2019 • Haoxin Li, Yijun Cai, Wei-Shi Zheng
To exploit the strong relations for egocentric interaction recognition, we introduce a dual relation modeling framework which learns to model the relations between the camera wearer and the interactor based on the individual action representations of the two persons.
no code implementations • 30 May 2019 • Xiang Li, Chan Lu, Danni Cheng, Wei-Hong Li, Mei Cao, Bo Liu, Jiechao Ma, Wei-Shi Zheng
Visible watermark plays an important role in image copyright protection and the robustness of a visible watermark to an attack is shown to be essential.
no code implementations • CVPR 2019 • Shuhan Tan, Jiening Jiao, Wei-Shi Zheng
Thus, it is meaningful to let partially labeled domains learn from each other to classify all the unlabeled samples in each domain under an open-set setting.
no code implementations • 24 Apr 2019 • Yanli Ji, Feixiang Xu, Yang Yang, Fumin Shen, Heng Tao Shen, Wei-Shi Zheng
Besides, we propose a View-guided Skeleton CNN (VS-CNN) to tackle the problem of arbitrary-view action recognition.
no code implementations • CVPR 2019 • Jingke Meng, Sheng Wu, Wei-Shi Zheng
In the conventional person re-id setting, it is assumed that the labeled images are the person images within the bounding box for each individual; this labeling across multiple nonoverlapping camera views from raw video surveillance is costly and time-consuming.
1 code implementation • CVPR 2019 • Wei-Hong Li, Fa-Ting Hong, Wei-Shi Zheng
In this work, we propose a deep imPOrtance relatIon NeTwork (POINT) that combines both relation modeling and feature learning.
no code implementations • 31 Mar 2019 • Hui Li, Meng Yang, Zhihui Lai, Wei-Shi Zheng, Zitong Yu
Deep part-based methods in recent literature have revealed the great potential of learning local part-level representation for pedestrian image in the task of person re-identification.
1 code implementation • CVPR 2019 • Hong-Xing Yu, Wei-Shi Zheng, An-Cong Wu, Xiaowei Guo, Shaogang Gong, Jian-Huang Lai
To overcome this problem, we propose a deep model for the soft multilabel learning for unsupervised RE-ID.
Ranked #84 on
Person Re-Identification
on DukeMTMC-reID
1 code implementation • 29 Jan 2019 • Hong-Xing Yu, An-Cong Wu, Wei-Shi Zheng
In such a way, DECAMEL jointly learns the feature representation and the unsupervised asymmetric metric.
no code implementations • 18 Dec 2018 • Jiechao Ma, Xiang Li, Hongwei Li, Bjoern H. Menze, Sen Liang, Rongguo Zhang, Wei-Shi Zheng
In this paper, we propose a novel and effective abnormality detector implementing the attention mechanism and group convolution on 3D single-shot detector (SSD) called group-attention SSD (GA-SSD).
Computed Tomography (CT)
Finding Pulmonary Nodules In Large-Scale Ct Images
no code implementations • 3 Dec 2018 • Minghan Li, Tanli Zuo, Ruicheng Li, Martha White, Wei-Shi Zheng
Knowledge distillation is an effective technique that transfers knowledge from a large teacher model to a shallow student.
no code implementations • 19 Oct 2018 • Jiafeng Xie, Bing Shuai, Jian-Fang Hu, Jingyang Lin, Wei-Shi Zheng
Recently, segmentation neural networks have been significantly improved by demonstrating very promising accuracies on public benchmarks.
no code implementations • ECCV 2018 • Jian-Fang Hu, Wei-Shi Zheng, Jia-Hui Pan, Jian-Huang Lai, Jian-Guo Zhang
In this paper, we focus on exploring modality-temporal mutual information for RGB-D action recognition.
no code implementations • IEEE Transactions on Pattern Analysis and Machine Intelligence 2018 • Jian-Fang Hu, Wei-Shi Zheng, Lianyang Ma, Gang Wang, Jian-Huang Lai, Jian-Guo Zhang
Our formulation of soft regression framework 1) overcomes a usual assumption in existing early action prediction systems that the progress level of on-going sequence is given in the testing stage; and 2) presents a theoretical framework to better resolve the ambiguity and uncertainty of subsequences at early performing stage.
Ranked #82 on
Skeleton Based Action Recognition
on NTU RGB+D 120
no code implementations • ECCV 2018 • Xiang Li, An-Cong Wu, Wei-Shi Zheng
The main idea is learning to attack feature extractor on the target people by using GAN to generate very target-like images (imposters), and in the meantime the model will make the feature extractor learn to tolerate the attack by discriminative learning so as to realize group-based verification.
1 code implementation • 4 Jul 2018 • Guang-Yuan Hao, Hong-Xing Yu, Wei-Shi Zheng
In this work, we present an interesting attempt on mixture generation: absorbing different image concepts (e. g., content and style) from different domains and thus generating a new domain with learned concepts.
no code implementations • 7 May 2018 • Yongyi Tang, Lin Ma, Wei Liu, Wei-Shi Zheng
Human motion prediction aims at generating future frames of human motion based on an observed sequence of skeletons.
no code implementations • CVPR 2019 • Ganzhao Yuan, Li Shen, Wei-Shi Zheng
The sparse generalized eigenvalue problem arises in a number of standard and modern statistical learning models, including sparse principal component analysis, sparse Fisher discriminant analysis, and sparse canonical correlation analysis.
Numerical Analysis
2 code implementations • 14 Feb 2018 • Hongwei Li, Gongfa Jiang, Jian-Guo Zhang, Ruixuan Wang, Zhaolei Wang, Wei-Shi Zheng, Bjoern Menze
In this paper, we present a study using deep fully convolutional network and ensemble models to automatically detect such WMH using fluid attenuation inversion recovery (FLAIR) and T1 magnetic resonance (MR) scans.
no code implementations • 5 Dec 2017 • Zhou Yin, Wei-Shi Zheng, An-Cong Wu, Hong-Xing Yu, Hai Wan, Xiaowei Guo, Feiyue Huang, Jian-Huang Lai
While attributes have been widely used for person re-identification (Re-ID) which aims at matching the same person images across disjoint camera views, they are used either as extra features or for performing multi-task learning to assist the image-image matching task.
no code implementations • 19 Nov 2017 • Ganzhao Yuan, Haoxian Tan, Wei-Shi Zheng
Sparse inverse covariance selection is a fundamental problem for analyzing dependencies in high dimensional data.
no code implementations • 9 Nov 2017 • Wei-Hong Li, Zhuowei Zhong, Wei-Shi Zheng
While there is a few work on discussing online re-id, most of them require considerable storage of all passed data samples that have been ever observed, and this could be unrealistic for processing data from a large camera network.
no code implementations • 6 Nov 2017 • Wei-Hong Li, Benchao Li, Wei-Shi Zheng
Always, some individuals in images are more important/attractive than others in some events such as presentation, basketball game or speech.
no code implementations • ICCV 2017 • Ancong Wu, Wei-Shi Zheng, Hong-Xing Yu, Shaogang Gong, Jian-Huang Lai
To that end, matching RGB images with infrared images is required, which are heterogeneous with very different visual characteristics.
Cross-Modality Person Re-identification
Cross-Modal Person Re-Identification
no code implementations • 20 Sep 2017 • Yongyi Tang, Peizhen Zhang, Jian-Fang Hu, Wei-Shi Zheng
Rather than simply recognizing the action of a person individually, collective activity recognition aims to find out what a group of people is acting in a collective scene.
1 code implementation • ICCV 2017 • Hong-Xing Yu, An-Cong Wu, Wei-Shi Zheng
While metric learning is important for Person re-identification (RE-ID), a significant problem in visual surveillance for cross-view pedestrian matching, existing metric models for RE-ID are mostly based on supervised learning that requires quantities of labeled samples in all pairs of camera views for training.
Ranked #121 on
Person Re-Identification
on Market-1501
no code implementations • CVPR 2017 • Ganzhao Yuan, Wei-Shi Zheng, Bernard Ghanem
Incorporating a new Gaussian elimination procedure, the matrix splitting method achieves state-of-the-art performance.
no code implementations • 6 Apr 2017 • Long-Kai Huang, Qiang Yang, Wei-Shi Zheng
Specifically, a new loss function is proposed to measure the similarity loss between a pair of data samples in hamming space.
no code implementations • 28 Mar 2017 • Ancong Wu, Wei-Shi Zheng, Jian-Huang Lai
More specifically, we exploit depth voxel covariance descriptor and further propose a locally rotation invariant depth shape descriptor called Eigen-depth feature to describe pedestrian body shape.
no code implementations • 26 Mar 2017 • Ying-Cong Chen, Xiatian Zhu, Wei-Shi Zheng, Jian-Huang Lai
The challenge of person re-identification (re-id) is to match individual images of the same person captured by different non-overlapping camera views against significant and unknown cross-view feature distortion.
no code implementations • IEEE Transactions on Pattern Analysis and Machine Intelligence ( Volume: 39 , Issue: 11 , Nov. 1 2017 ) 2016 • Jian-Fang Hu, Wei-Shi Zheng, Jian-Huang Lai, Jian-Guo Zhang
The proposed model formed in a unified framework is capable of: 1) jointly mining a set of subspaces with the same dimensionality to exploit latent shared features across different feature channels, 2) meanwhile, quantifying the shared and feature-specific components of features in the subspaces, and 3) transferring feature-specific intermediate transforms (i-transforms) for learning fusion of heterogeneous features across datasets.
Ranked #8 on
Skeleton Based Action Recognition
on SYSU 3D
no code implementations • 1 Nov 2016 • Hailin Shi, Yang Yang, Xiangyu Zhu, Shengcai Liao, Zhen Lei, Wei-Shi Zheng, Stan Z. Li
From this point of view, selecting suitable positive i. e. intra-class) training samples within a local range is critical for training the CNN embedding, especially when the data has large intra-class variations.
no code implementations • CVPR 2016 • Jin-Jie You, An-Cong Wu, Xiang Li, Wei-Shi Zheng
Since only limited information can be exploited from still images, it is hard (if not impossible) to overcome the occlusion, pose and camera-view change, and lighting variation problems.
no code implementations • 26 Apr 2016 • Shangxuan Wu, Ying-Cong Chen, Xiang Li, An-Cong Wu, Jin-Jie You, Wei-Shi Zheng
In this paper, we focus on the feature representation and claim that hand-crafted histogram features can be complementary to Convolutional Neural Network (CNN) features.
no code implementations • 20 Apr 2016 • Hongwei Li, Wei-Shi Zheng, JianGuo Zhang
Automatic classification of Human Epithelial Type-2 (HEp-2) cells staining patterns is an important and yet a challenging problem.
no code implementations • ICCV 2015 • Wei-Shi Zheng, Xiang Li, Tao Xiang, Shengcai Liao, Jian-Huang Lai, Shaogang Gong
We address a new partial person re-identification (re-id) problem, where only a partial observation of a person is available for matching across different non-overlapping camera views.
no code implementations • ICCV 2015 • Xiang Li, Wei-Shi Zheng, Xiaojuan Wang, Tao Xiang, Shaogang Gong
In real world person re-identification (re-id), images of people captured at very different resolutions from different locations need be matched.
no code implementations • 1 Feb 2015 • Yuanlu Xu, Liang Lin, Wei-Shi Zheng, Xiaobai Liu
This paper aims at a newly raising task in visual surveillance: re-identifying people at a distance by matching body information, given several reference examples.