Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Xiatian Zhu

Xiatian Zhu

SOFT: Softmax-free Transformer with Linear Complexity


Oct 29, 2021
Jiachen Lu, Jinghan Yao, Junge Zhang, Xiatian Zhu, Hang Xu, Weiguo Gao, Chunjing Xu, Tao Xiang, Li Zhang

Figure 1 for SOFT: Softmax-free Transformer with Linear Complexity
Figure 2 for SOFT: Softmax-free Transformer with Linear Complexity
Figure 3 for SOFT: Softmax-free Transformer with Linear Complexity
Figure 4 for SOFT: Softmax-free Transformer with Linear Complexity
* NeurIPS 2021 Spotlight. Project page at https://fudan-zvg.github.io/SOFT/ 
  Access Paper or Ask Questions

Few-Shot Temporal Action Localization with Query Adaptive Transformer


Oct 20, 2021
Sauradip Nag, Xiatian Zhu, Tao Xiang

Figure 1 for Few-Shot Temporal Action Localization with Query Adaptive Transformer
Figure 2 for Few-Shot Temporal Action Localization with Query Adaptive Transformer
Figure 3 for Few-Shot Temporal Action Localization with Query Adaptive Transformer
Figure 4 for Few-Shot Temporal Action Localization with Query Adaptive Transformer
* BMVC 2021 
  Access Paper or Ask Questions

Single Person Pose Estimation: A Survey


Sep 21, 2021
Feng Zhang, Xiatian Zhu, Chen Wang

Figure 1 for Single Person Pose Estimation: A Survey
Figure 2 for Single Person Pose Estimation: A Survey
Figure 3 for Single Person Pose Estimation: A Survey
Figure 4 for Single Person Pose Estimation: A Survey
* 16 pages, 3 figures 
  Access Paper or Ask Questions

Low-resolution Human Pose Estimation


Sep 19, 2021
Chen Wang, Feng Zhang, Xiatian Zhu, Shuzhi Sam Ge

Figure 1 for Low-resolution Human Pose Estimation
Figure 2 for Low-resolution Human Pose Estimation
Figure 3 for Low-resolution Human Pose Estimation
Figure 4 for Low-resolution Human Pose Estimation
* 29 pages, 6 figures, under review of Pattern Recognition 
  Access Paper or Ask Questions

Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer


Aug 12, 2021
Zhihe Lu, Sen He, Xiatian Zhu, Li Zhang, Yi-Zhe Song, Tao Xiang

Figure 1 for Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer
Figure 2 for Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer
Figure 3 for Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer
Figure 4 for Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer
* Accepted by ICCV2021. Code website:https://github.com/zhiheLu/CWT-for-FSS 
  Access Paper or Ask Questions

Global Aggregation then Local Distribution for Scene Parsing


Jul 28, 2021
Xiangtai Li, Li Zhang, Guangliang Cheng, Kuiyuan Yang, Yunhai Tong, Xiatian Zhu, Tao Xiang

Figure 1 for Global Aggregation then Local Distribution for Scene Parsing
Figure 2 for Global Aggregation then Local Distribution for Scene Parsing
Figure 3 for Global Aggregation then Local Distribution for Scene Parsing
Figure 4 for Global Aggregation then Local Distribution for Scene Parsing
* Accepted by IEEE-TIP-2021. arXiv admin note: text overlap with arXiv:1909.07229 
  Access Paper or Ask Questions

Long-term Person Re-identification: A Benchmark


May 31, 2021
Peng Xu, Xiatian Zhu

Figure 1 for Long-term Person Re-identification: A Benchmark
Figure 2 for Long-term Person Re-identification: A Benchmark
Figure 3 for Long-term Person Re-identification: A Benchmark
Figure 4 for Long-term Person Re-identification: A Benchmark

  Access Paper or Ask Questions

Low-Fidelity End-to-End Video Encoder Pre-training for Temporal Action Localization


Mar 30, 2021
Mengmeng Xu, Juan-Manuel Perez-Rua, Xiatian Zhu, Bernard Ghanem, Brais Martinez

Figure 1 for Low-Fidelity End-to-End Video Encoder Pre-training for Temporal Action Localization
Figure 2 for Low-Fidelity End-to-End Video Encoder Pre-training for Temporal Action Localization
Figure 3 for Low-Fidelity End-to-End Video Encoder Pre-training for Temporal Action Localization
Figure 4 for Low-Fidelity End-to-End Video Encoder Pre-training for Temporal Action Localization
* 10 pages, 2 figures 
  Access Paper or Ask Questions

Few-shot Action Recognition with Prototype-centered Attentive Learning


Feb 03, 2021
Xiatian Zhu, Antoine Toisoul, Juan-Manuel Prez-Ra, Li Zhang, Brais Martinez, Tao Xiang

Figure 1 for Few-shot Action Recognition with Prototype-centered Attentive Learning
Figure 2 for Few-shot Action Recognition with Prototype-centered Attentive Learning
Figure 3 for Few-shot Action Recognition with Prototype-centered Attentive Learning
Figure 4 for Few-shot Action Recognition with Prototype-centered Attentive Learning
* 10 pages, 4 figures 
  Access Paper or Ask Questions

Unsupervised Noisy Tracklet Person Re-identification


Jan 16, 2021
Minxian Li, Xiatian Zhu, Shaogang Gong

Figure 1 for Unsupervised Noisy Tracklet Person Re-identification
Figure 2 for Unsupervised Noisy Tracklet Person Re-identification
Figure 3 for Unsupervised Noisy Tracklet Person Re-identification
Figure 4 for Unsupervised Noisy Tracklet Person Re-identification
* was submitted to ICCV2019 
  Access Paper or Ask Questions

Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers


Dec 31, 2020
Sixiao Zheng, Jiachen Lu, Hengshuang Zhao, Xiatian Zhu, Zekun Luo, Yabiao Wang, Yanwei Fu, Jianfeng Feng, Tao Xiang, Philip H. S. Torr, Li Zhang

Figure 1 for Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers
Figure 2 for Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers
Figure 3 for Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers
Figure 4 for Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers
* project page at https://fudan-zvg.github.io/SETR/ 
  Access Paper or Ask Questions

Towards Uncovering the Intrinsic Data Structures for Unsupervised Domain Adaptation using Structurally Regularized Deep Clustering


Dec 08, 2020
Hui Tang, Xiatian Zhu, Ke Chen, Kui Jia, C. L. Philip Chen

Figure 1 for Towards Uncovering the Intrinsic Data Structures for Unsupervised Domain Adaptation using Structurally Regularized Deep Clustering
Figure 2 for Towards Uncovering the Intrinsic Data Structures for Unsupervised Domain Adaptation using Structurally Regularized Deep Clustering
Figure 3 for Towards Uncovering the Intrinsic Data Structures for Unsupervised Domain Adaptation using Structurally Regularized Deep Clustering
Figure 4 for Towards Uncovering the Intrinsic Data Structures for Unsupervised Domain Adaptation using Structurally Regularized Deep Clustering
* Journal extension of our preliminary CVPR conference paper, under review, 16 pages, 8 figures, 12 tables 
  Access Paper or Ask Questions

Boundary-sensitive Pre-training for Temporal Localization in Videos


Nov 24, 2020
Mengmeng Xu, Juan-Manuel Perez-Rua, Victor Escorcia, Brais Martinez, Xiatian Zhu, Li Zhang, Bernard Ghanem, Tao Xiang

Figure 1 for Boundary-sensitive Pre-training for Temporal Localization in Videos
Figure 2 for Boundary-sensitive Pre-training for Temporal Localization in Videos
Figure 3 for Boundary-sensitive Pre-training for Temporal Localization in Videos
Figure 4 for Boundary-sensitive Pre-training for Temporal Localization in Videos
* 11 pages, 4 figures 
  Access Paper or Ask Questions

Egocentric Action Recognition by Video Attention and Temporal Context


Jul 03, 2020
Juan-Manuel Perez-Rua, Antoine Toisoul, Brais Martinez, Victor Escorcia, Li Zhang, Xiatian Zhu, Tao Xiang

Figure 1 for Egocentric Action Recognition by Video Attention and Temporal Context
Figure 2 for Egocentric Action Recognition by Video Attention and Temporal Context
Figure 3 for Egocentric Action Recognition by Video Attention and Temporal Context
Figure 4 for Egocentric Action Recognition by Video Attention and Temporal Context
* EPIC-Kitchens [email protected] 2020 
  Access Paper or Ask Questions

Knowing What, Where and When to Look: Efficient Video Action Modeling with Attention


Apr 02, 2020
Juan-Manuel Perez-Rua, Brais Martinez, Xiatian Zhu, Antoine Toisoul, Victor Escorcia, Tao Xiang

Figure 1 for Knowing What, Where and When to Look: Efficient Video Action Modeling with Attention
Figure 2 for Knowing What, Where and When to Look: Efficient Video Action Modeling with Attention
Figure 3 for Knowing What, Where and When to Look: Efficient Video Action Modeling with Attention
Figure 4 for Knowing What, Where and When to Look: Efficient Video Action Modeling with Attention

  Access Paper or Ask Questions

Joint COCO and Mapillary Workshop at ICCV 2019 Keypoint Detection Challenge Track Technical Report: Distribution-Aware Coordinate Representation for Human Pose Estimation


Mar 13, 2020
Hanbin Dai, Liangbo Zhou, Feng Zhang, Zhengyu Zhang, Hong Hu, Xiatian Zhu, Mao Ye

Figure 1 for Joint COCO and Mapillary Workshop at ICCV 2019 Keypoint Detection Challenge Track Technical Report: Distribution-Aware Coordinate Representation for Human Pose Estimation
Figure 2 for Joint COCO and Mapillary Workshop at ICCV 2019 Keypoint Detection Challenge Track Technical Report: Distribution-Aware Coordinate Representation for Human Pose Estimation
Figure 3 for Joint COCO and Mapillary Workshop at ICCV 2019 Keypoint Detection Challenge Track Technical Report: Distribution-Aware Coordinate Representation for Human Pose Estimation
Figure 4 for Joint COCO and Mapillary Workshop at ICCV 2019 Keypoint Detection Challenge Track Technical Report: Distribution-Aware Coordinate Representation for Human Pose Estimation
* arXiv admin note: substantial text overlap with arXiv:1910.06278 
  Access Paper or Ask Questions

Incremental Few-Shot Object Detection


Mar 12, 2020
Juan-Manuel Perez-Rua, Xiatian Zhu, Timothy Hospedales, Tao Xiang

Figure 1 for Incremental Few-Shot Object Detection
Figure 2 for Incremental Few-Shot Object Detection
Figure 3 for Incremental Few-Shot Object Detection
Figure 4 for Incremental Few-Shot Object Detection
* CVPR 2020 
  Access Paper or Ask Questions

Intra-Camera Supervised Person Re-Identification


Feb 12, 2020
Xiangping Zhu, Xiatian Zhu, Minxian Li, Pietro Morerio, Vittorio Murino, Shaogang Gong

Figure 1 for Intra-Camera Supervised Person Re-Identification
Figure 2 for Intra-Camera Supervised Person Re-Identification
Figure 3 for Intra-Camera Supervised Person Re-Identification
Figure 4 for Intra-Camera Supervised Person Re-Identification
* 16 pages 
  Access Paper or Ask Questions

Characteristic Regularisation for Super-Resolving Face Images


Dec 30, 2019
Zhiyi Cheng, Xiatian Zhu, Shaogang Gong

Figure 1 for Characteristic Regularisation for Super-Resolving Face Images
Figure 2 for Characteristic Regularisation for Super-Resolving Face Images
Figure 3 for Characteristic Regularisation for Super-Resolving Face Images
Figure 4 for Characteristic Regularisation for Super-Resolving Face Images
* Accepted by WACV2020 
  Access Paper or Ask Questions

Learning Generalisable Omni-Scale Representations for Person Re-Identification


Oct 15, 2019
Kaiyang Zhou, Xiatian Zhu, Yongxin Yang, Andrea Cavallaro, Tao Xiang

Figure 1 for Learning Generalisable Omni-Scale Representations for Person Re-Identification
Figure 2 for Learning Generalisable Omni-Scale Representations for Person Re-Identification
Figure 3 for Learning Generalisable Omni-Scale Representations for Person Re-Identification
Figure 4 for Learning Generalisable Omni-Scale Representations for Person Re-Identification
* Extension of conference version: arXiv:1905.00953. Source code: https://github.com/KaiyangZhou/deep-person-reid 
  Access Paper or Ask Questions

Distribution-Aware Coordinate Representation for Human Pose Estimation


Oct 14, 2019
Feng Zhang, Xiatian Zhu, Hanbin Dai, Mao Ye, Ce Zhu

Figure 1 for Distribution-Aware Coordinate Representation for Human Pose Estimation
Figure 2 for Distribution-Aware Coordinate Representation for Human Pose Estimation
Figure 3 for Distribution-Aware Coordinate Representation for Human Pose Estimation
Figure 4 for Distribution-Aware Coordinate Representation for Human Pose Estimation
* Results on the COCO keypoint detection challenge: 78.9% AP on the test-dev set (Top-1 in the leaderbord by 12 Oct 2019) and 76.4% AP on the test-challenge set. Project page: https://ilovepose.github.io/coco 
  Access Paper or Ask Questions

Intra-Camera Supervised Person Re-Identification: A New Benchmark


Aug 27, 2019
Xiangping Zhu, Xiatian Zhu, Minxian Li, Vittorio Murino, Shaogang Gong

Figure 1 for Intra-Camera Supervised Person Re-Identification: A New Benchmark
Figure 2 for Intra-Camera Supervised Person Re-Identification: A New Benchmark
Figure 3 for Intra-Camera Supervised Person Re-Identification: A New Benchmark
Figure 4 for Intra-Camera Supervised Person Re-Identification: A New Benchmark
* 9 pages, 3 figures, accepted by ICCV Workshop on Real-World Recognition from Low-Quality Images and Videos, 2019 
  Access Paper or Ask Questions

Universal Person Re-Identification


Jul 22, 2019
Xu Lan, Xiatian Zhu, Shaogang Gong

Figure 1 for Universal Person Re-Identification
Figure 2 for Universal Person Re-Identification
Figure 3 for Universal Person Re-Identification
Figure 4 for Universal Person Re-Identification

  Access Paper or Ask Questions

Unsupervised Deep Learning by Neighbourhood Discovery


May 30, 2019
Jiabo Huang, Qi Dong, Shaogang Gong, Xiatian Zhu

Figure 1 for Unsupervised Deep Learning by Neighbourhood Discovery
Figure 2 for Unsupervised Deep Learning by Neighbourhood Discovery
Figure 3 for Unsupervised Deep Learning by Neighbourhood Discovery
Figure 4 for Unsupervised Deep Learning by Neighbourhood Discovery
* 36th International Conference on Machine Learning (ICML'19). Code is available at https://github.com/Raymond-sci/AND 
  Access Paper or Ask Questions

Unsupervised Tracklet Person Re-Identification


Mar 01, 2019
Minxian Li, Xiatian Zhu, Shaogang Gong

Figure 1 for Unsupervised Tracklet Person Re-Identification
Figure 2 for Unsupervised Tracklet Person Re-Identification
Figure 3 for Unsupervised Tracklet Person Re-Identification
Figure 4 for Unsupervised Tracklet Person Re-Identification
* Accepted to appear in IEEE Transactions on Pattern Analysis and Machine Intelligence. The new dataset is publicly available at https://github.com/liminxian/DukeMTMC-SI-Tracklet 
  Access Paper or Ask Questions