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 Wengang Zhou

Wengang Zhou

TransVG: End-to-End Visual Grounding with Transformers


Apr 17, 2021
Jiajun Deng, Zhengyuan Yang, Tianlang Chen, Wengang Zhou, Houqiang Li

Figure 1 for TransVG: End-to-End Visual Grounding with Transformers
Figure 2 for TransVG: End-to-End Visual Grounding with Transformers
Figure 3 for TransVG: End-to-End Visual Grounding with Transformers
Figure 4 for TransVG: End-to-End Visual Grounding with Transformers

  Access Paper or Ask Questions

Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking


Mar 24, 2021
Ning Wang, Wengang Zhou, Jie Wang, Houqaing Li

Figure 1 for Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking
Figure 2 for Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking
Figure 3 for Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking
Figure 4 for Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking
* To appear in CVPR 2021 (Oral) 
  Access Paper or Ask Questions

IOT: Instance-wise Layer Reordering for Transformer Structures


Mar 05, 2021
Jinhua Zhu, Lijun Wu, Yingce Xia, Shufang Xie, Tao Qin, Wengang Zhou, Houqiang Li, Tie-Yan Liu

Figure 1 for IOT: Instance-wise Layer Reordering for Transformer Structures
Figure 2 for IOT: Instance-wise Layer Reordering for Transformer Structures
Figure 3 for IOT: Instance-wise Layer Reordering for Transformer Structures
Figure 4 for IOT: Instance-wise Layer Reordering for Transformer Structures
* Accepted at ICLR-2021 
  Access Paper or Ask Questions

Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection


Feb 05, 2021
Jiajun Deng, Shaoshuai Shi, Peiwei Li, Wengang Zhou, Yanyong Zhang, Houqiang Li

Figure 1 for Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection
Figure 2 for Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection
Figure 3 for Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection
Figure 4 for Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection
* AAAI2021 
  Access Paper or Ask Questions

Contrastive Transformation for Self-supervised Correspondence Learning


Dec 09, 2020
Ning Wang, Wengang Zhou, Houqiang Li

Figure 1 for Contrastive Transformation for Self-supervised Correspondence Learning
Figure 2 for Contrastive Transformation for Self-supervised Correspondence Learning
Figure 3 for Contrastive Transformation for Self-supervised Correspondence Learning
Figure 4 for Contrastive Transformation for Self-supervised Correspondence Learning
* To appear in AAAI 2021 
  Access Paper or Ask Questions

Temporal-Channel Transformer for 3D Lidar-Based Video Object Detection in Autonomous Driving


Nov 27, 2020
Zhenxun Yuan, Xiao Song, Lei Bai, Wengang Zhou, Zhe Wang, Wanli Ouyang

Figure 1 for Temporal-Channel Transformer for 3D Lidar-Based Video Object Detection in Autonomous Driving
Figure 2 for Temporal-Channel Transformer for 3D Lidar-Based Video Object Detection in Autonomous Driving
Figure 3 for Temporal-Channel Transformer for 3D Lidar-Based Video Object Detection in Autonomous Driving
Figure 4 for Temporal-Channel Transformer for 3D Lidar-Based Video Object Detection in Autonomous Driving

  Access Paper or Ask Questions

Heterogeneous Contrastive Learning: Encoding Spatial Information for Compact Visual Representations


Nov 19, 2020
Xinyue Huo, Lingxi Xie, Longhui Wei, Xiaopeng Zhang, Hao Li, Zijie Yang, Wengang Zhou, Houqiang Li, Qi Tian

Figure 1 for Heterogeneous Contrastive Learning: Encoding Spatial Information for Compact Visual Representations
Figure 2 for Heterogeneous Contrastive Learning: Encoding Spatial Information for Compact Visual Representations
Figure 3 for Heterogeneous Contrastive Learning: Encoding Spatial Information for Compact Visual Representations
Figure 4 for Heterogeneous Contrastive Learning: Encoding Spatial Information for Compact Visual Representations
* 10 pages, 4 figures, 6 tables 
  Access Paper or Ask Questions

Can Semantic Labels Assist Self-Supervised Visual Representation Learning?


Nov 17, 2020
Longhui Wei, Lingxi Xie, Jianzhong He, Jianlong Chang, Xiaopeng Zhang, Wengang Zhou, Houqiang Li, Qi Tian

Figure 1 for Can Semantic Labels Assist Self-Supervised Visual Representation Learning?
Figure 2 for Can Semantic Labels Assist Self-Supervised Visual Representation Learning?
Figure 3 for Can Semantic Labels Assist Self-Supervised Visual Representation Learning?
Figure 4 for Can Semantic Labels Assist Self-Supervised Visual Representation Learning?
* 10 pages, 4 figures, 8 tables 
  Access Paper or Ask Questions

Masked Contrastive Representation Learning for Reinforcement Learning


Oct 15, 2020
Jinhua Zhu, Yingce Xia, Lijun Wu, Jiajun Deng, Wengang Zhou, Tao Qin, Houqiang Li

Figure 1 for Masked Contrastive Representation Learning for Reinforcement Learning
Figure 2 for Masked Contrastive Representation Learning for Reinforcement Learning
Figure 3 for Masked Contrastive Representation Learning for Reinforcement Learning
Figure 4 for Masked Contrastive Representation Learning for Reinforcement Learning
* Work in progress 
  Access Paper or Ask Questions

Boosting Continuous Sign Language Recognition via Cross Modality Augmentation


Oct 11, 2020
Junfu Pu, Wengang Zhou, Hezhen Hu, Houqiang Li

Figure 1 for Boosting Continuous Sign Language Recognition via Cross Modality Augmentation
Figure 2 for Boosting Continuous Sign Language Recognition via Cross Modality Augmentation
Figure 3 for Boosting Continuous Sign Language Recognition via Cross Modality Augmentation
Figure 4 for Boosting Continuous Sign Language Recognition via Cross Modality Augmentation
* Accepted to ACM Multimedia 2020 
  Access Paper or Ask Questions

Vision Meets Wireless Positioning: Effective Person Re-identification with Recurrent Context Propagation


Sep 04, 2020
Yiheng Liu, Wengang Zhou, Mao Xi, Sanjing Shen, Houqiang Li

Figure 1 for Vision Meets Wireless Positioning: Effective Person Re-identification with Recurrent Context Propagation
Figure 2 for Vision Meets Wireless Positioning: Effective Person Re-identification with Recurrent Context Propagation
Figure 3 for Vision Meets Wireless Positioning: Effective Person Re-identification with Recurrent Context Propagation
Figure 4 for Vision Meets Wireless Positioning: Effective Person Re-identification with Recurrent Context Propagation
* Accepted by ACM MM 2020 as Oral paper 
  Access Paper or Ask Questions

Global-local Enhancement Network for NMFs-aware Sign Language Recognition


Aug 24, 2020
Hezhen Hu, Wengang Zhou, Junfu Pu, Houqiang Li

Figure 1 for Global-local Enhancement Network for NMFs-aware Sign Language Recognition
Figure 2 for Global-local Enhancement Network for NMFs-aware Sign Language Recognition
Figure 3 for Global-local Enhancement Network for NMFs-aware Sign Language Recognition
Figure 4 for Global-local Enhancement Network for NMFs-aware Sign Language Recognition
* Under Review 
  Access Paper or Ask Questions

Unsupervised Deep Representation Learning for Real-Time Tracking


Jul 22, 2020
Ning Wang, Wengang Zhou, Yibing Song, Chao Ma, Wei Liu, Houqiang Li

Figure 1 for Unsupervised Deep Representation Learning for Real-Time Tracking
Figure 2 for Unsupervised Deep Representation Learning for Real-Time Tracking
Figure 3 for Unsupervised Deep Representation Learning for Real-Time Tracking
Figure 4 for Unsupervised Deep Representation Learning for Real-Time Tracking
* Journal version of the CVPR2019 paper "Unsupervised Deep Tracking". Accepted by IJCV. arXiv admin note: text overlap with arXiv:1904.01828 
  Access Paper or Ask Questions

Wavelet-Based Dual-Branch Network for Image Demoireing


Jul 17, 2020
Lin Liu, Jianzhuang Liu, Shanxin Yuan, Gregory Slabaugh, Ales Leonardis, Wengang Zhou, Qi Tian

Figure 1 for Wavelet-Based Dual-Branch Network for Image Demoireing
Figure 2 for Wavelet-Based Dual-Branch Network for Image Demoireing
Figure 3 for Wavelet-Based Dual-Branch Network for Image Demoireing
Figure 4 for Wavelet-Based Dual-Branch Network for Image Demoireing
* Accepted to ECCV 2020 
  Access Paper or Ask Questions

Single Shot Video Object Detector


Jul 07, 2020
Jiajun Deng, Yingwei Pan, Ting Yao, Wengang Zhou, Houqiang Li, Tao Mei

Figure 1 for Single Shot Video Object Detector
Figure 2 for Single Shot Video Object Detector
Figure 3 for Single Shot Video Object Detector
Figure 4 for Single Shot Video Object Detector
* Accepted by IEEE Transactions on Multimedia; The code is available at \url{https://github.com/ddjiajun/SSVD} 
  Access Paper or Ask Questions

Cascaded Regression Tracking: Towards Online Hard Distractor Discrimination


Jun 18, 2020
Ning Wang, Wengang Zhou, Qi Tian, Houqiang Li

Figure 1 for Cascaded Regression Tracking: Towards Online Hard Distractor Discrimination
Figure 2 for Cascaded Regression Tracking: Towards Online Hard Distractor Discrimination
Figure 3 for Cascaded Regression Tracking: Towards Online Hard Distractor Discrimination
Figure 4 for Cascaded Regression Tracking: Towards Online Hard Distractor Discrimination
* Accepted by IEEE TCSVT 
  Access Paper or Ask Questions

Incorporating BERT into Neural Machine Translation


Feb 17, 2020
Jinhua Zhu, Yingce Xia, Lijun Wu, Di He, Tao Qin, Wengang Zhou, Houqiang Li, Tie-Yan Liu

Figure 1 for Incorporating BERT into Neural Machine Translation
Figure 2 for Incorporating BERT into Neural Machine Translation
Figure 3 for Incorporating BERT into Neural Machine Translation
Figure 4 for Incorporating BERT into Neural Machine Translation
* Accepted to ICLR-2020 
  Access Paper or Ask Questions

Spatial-Temporal Multi-Cue Network for Continuous Sign Language Recognition


Feb 08, 2020
Hao Zhou, Wengang Zhou, Yun Zhou, Houqiang Li

Figure 1 for Spatial-Temporal Multi-Cue Network for Continuous Sign Language Recognition
Figure 2 for Spatial-Temporal Multi-Cue Network for Continuous Sign Language Recognition
Figure 3 for Spatial-Temporal Multi-Cue Network for Continuous Sign Language Recognition
Figure 4 for Spatial-Temporal Multi-Cue Network for Continuous Sign Language Recognition
* Accepted as an oral presentation paper at AAAI 2020. (To appear in Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence) 
  Access Paper or Ask Questions

Progressive Unsupervised Person Re-identification by Tracklet Association with Spatio-Temporal Regularization


Oct 25, 2019
Qiaokang Xie, Wengang Zhou, Guo-Jun Qi, Qi Tian, Houqiang Li

Figure 1 for Progressive Unsupervised Person Re-identification by Tracklet Association with Spatio-Temporal Regularization
Figure 2 for Progressive Unsupervised Person Re-identification by Tracklet Association with Spatio-Temporal Regularization
Figure 3 for Progressive Unsupervised Person Re-identification by Tracklet Association with Spatio-Temporal Regularization
Figure 4 for Progressive Unsupervised Person Re-identification by Tracklet Association with Spatio-Temporal Regularization
* 12 pages, 10 figures 
  Access Paper or Ask Questions

An End-to-End Foreground-Aware Network for Person Re-Identification


Oct 25, 2019
Yiheng Liu, Wengang Zhou, Jianzhuang Liu, Guojun Qi, Qi Tian, Houqiang Li

Figure 1 for An End-to-End Foreground-Aware Network for Person Re-Identification
Figure 2 for An End-to-End Foreground-Aware Network for Person Re-Identification
Figure 3 for An End-to-End Foreground-Aware Network for Person Re-Identification
Figure 4 for An End-to-End Foreground-Aware Network for Person Re-Identification
* TIP Under Review 
  Access Paper or Ask Questions

Relation Distillation Networks for Video Object Detection


Aug 26, 2019
Jiajun Deng, Yingwei Pan, Ting Yao, Wengang Zhou, Houqiang Li, Tao Mei

Figure 1 for Relation Distillation Networks for Video Object Detection
Figure 2 for Relation Distillation Networks for Video Object Detection
Figure 3 for Relation Distillation Networks for Video Object Detection
Figure 4 for Relation Distillation Networks for Video Object Detection
* ICCV 2019 
  Access Paper or Ask Questions

Real-Time Correlation Tracking via Joint Model Compression and Transfer


Jul 23, 2019
Ning Wang, Wengang Zhou, Yibing Song, Chao Ma, Houqiang Li

Figure 1 for Real-Time Correlation Tracking via Joint Model Compression and Transfer
Figure 2 for Real-Time Correlation Tracking via Joint Model Compression and Transfer
Figure 3 for Real-Time Correlation Tracking via Joint Model Compression and Transfer
Figure 4 for Real-Time Correlation Tracking via Joint Model Compression and Transfer
* 12 pages, 12 figures, submitted to IEEE Transactions on Image Processing 
  Access Paper or Ask Questions

Online Filter Clustering and Pruning for Efficient Convnets


May 28, 2019
Zhengguang Zhou, Wengang Zhou, Richang Hong, Houqiang Li

Figure 1 for Online Filter Clustering and Pruning for Efficient Convnets
Figure 2 for Online Filter Clustering and Pruning for Efficient Convnets
Figure 3 for Online Filter Clustering and Pruning for Efficient Convnets
Figure 4 for Online Filter Clustering and Pruning for Efficient Convnets
* 2018 IEEE International Conference on Image Processing 
 * 5 pages, 4 figures 
  Access Paper or Ask Questions

Progressive Learning of Low-Precision Networks


May 28, 2019
Zhengguang Zhou, Wengang Zhou, Xutao Lv, Xuan Huang, Xiaoyu Wang, Houqiang Li

Figure 1 for Progressive Learning of Low-Precision Networks
Figure 2 for Progressive Learning of Low-Precision Networks
Figure 3 for Progressive Learning of Low-Precision Networks
Figure 4 for Progressive Learning of Low-Precision Networks
* 10 pages, 8 figures 
  Access Paper or Ask Questions

Soft Contextual Data Augmentation for Neural Machine Translation


May 25, 2019
Jinhua Zhu, Fei Gao, Lijun Wu, Yingce Xia, Tao Qin, Wengang Zhou, Xueqi Cheng, Tie-Yan Liu

Figure 1 for Soft Contextual Data Augmentation for Neural Machine Translation
Figure 2 for Soft Contextual Data Augmentation for Neural Machine Translation
Figure 3 for Soft Contextual Data Augmentation for Neural Machine Translation
* Accepted by ACL 2019 as short paper 
  Access Paper or Ask Questions

Unsupervised Deep Tracking


Apr 03, 2019
Ning Wang, Yibing Song, Chao Ma, Wengang Zhou, Wei Liu, Houqiang Li

Figure 1 for Unsupervised Deep Tracking
Figure 2 for Unsupervised Deep Tracking
Figure 3 for Unsupervised Deep Tracking
Figure 4 for Unsupervised Deep Tracking
* to appear in CVPR 2019 
  Access Paper or Ask Questions

WIDER Face and Pedestrian Challenge 2018: Methods and Results


Feb 19, 2019
Chen Change Loy, Dahua Lin, Wanli Ouyang, Yuanjun Xiong, Shuo Yang, Qingqiu Huang, Dongzhan Zhou, Wei Xia, Quanquan Li, Ping Luo, Junjie Yan, Jianfeng Wang, Zuoxin Li, Ye Yuan, Boxun Li, Shuai Shao, Gang Yu, Fangyun Wei, Xiang Ming, Dong Chen, Shifeng Zhang, Cheng Chi, Zhen Lei, Stan Z. Li, Hongkai Zhang, Bingpeng Ma, Hong Chang, Shiguang Shan, Xilin Chen, Wu Liu, Boyan Zhou, Huaxiong Li, Peng Cheng, Tao Mei, Artem Kukharenko, Artem Vasenin, Nikolay Sergievskiy, Hua Yang, Liangqi Li, Qiling Xu, Yuan Hong, Lin Chen, Mingjun Sun, Yirong Mao, Shiying Luo, Yongjun Li, Ruiping Wang, Qiaokang Xie, Ziyang Wu, Lei Lu, Yiheng Liu, Wengang Zhou

Figure 1 for WIDER Face and Pedestrian Challenge 2018: Methods and Results
Figure 2 for WIDER Face and Pedestrian Challenge 2018: Methods and Results
Figure 3 for WIDER Face and Pedestrian Challenge 2018: Methods and Results
Figure 4 for WIDER Face and Pedestrian Challenge 2018: Methods and Results
* Report of ECCV 2018 workshop: WIDER Face and Pedestrian Challenge 
  Access Paper or Ask Questions