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 Hengshuang Zhao

Hengshuang Zhao

LAVT: Language-Aware Vision Transformer for Referring Image Segmentation


Dec 04, 2021
Zhao Yang, Jiaqi Wang, Yansong Tang, Kai Chen, Hengshuang Zhao, Philip H. S. Torr

Figure 1 for LAVT: Language-Aware Vision Transformer for Referring Image Segmentation
Figure 2 for LAVT: Language-Aware Vision Transformer for Referring Image Segmentation
Figure 3 for LAVT: Language-Aware Vision Transformer for Referring Image Segmentation
Figure 4 for LAVT: Language-Aware Vision Transformer for Referring Image Segmentation
* 10 pages, 8 figures 
  Access Paper or Ask Questions

PhysFormer: Facial Video-based Physiological Measurement with Temporal Difference Transformer


Nov 23, 2021
Zitong Yu, Yuming Shen, Jingang Shi, Hengshuang Zhao, Philip Torr, Guoying Zhao

Figure 1 for PhysFormer: Facial Video-based Physiological Measurement with Temporal Difference Transformer
Figure 2 for PhysFormer: Facial Video-based Physiological Measurement with Temporal Difference Transformer
Figure 3 for PhysFormer: Facial Video-based Physiological Measurement with Temporal Difference Transformer
Figure 4 for PhysFormer: Facial Video-based Physiological Measurement with Temporal Difference Transformer

  Access Paper or Ask Questions

Adversarial Examples on Segmentation Models Can be Easy to Transfer


Nov 22, 2021
Jindong Gu, Hengshuang Zhao, Volker Tresp, Philip Torr

Figure 1 for Adversarial Examples on Segmentation Models Can be Easy to Transfer
Figure 2 for Adversarial Examples on Segmentation Models Can be Easy to Transfer
Figure 3 for Adversarial Examples on Segmentation Models Can be Easy to Transfer
Figure 4 for Adversarial Examples on Segmentation Models Can be Easy to Transfer

  Access Paper or Ask Questions

Fully Convolutional Networks for Panoptic Segmentation with Point-based Supervision


Aug 18, 2021
Yanwei Li, Hengshuang Zhao, Xiaojuan Qi, Yukang Chen, Lu Qi, Liwei Wang, Zeming Li, Jian Sun, Jiaya Jia

Figure 1 for Fully Convolutional Networks for Panoptic Segmentation with Point-based Supervision
Figure 2 for Fully Convolutional Networks for Panoptic Segmentation with Point-based Supervision
Figure 3 for Fully Convolutional Networks for Panoptic Segmentation with Point-based Supervision
Figure 4 for Fully Convolutional Networks for Panoptic Segmentation with Point-based Supervision
* Extended version of arXiv:2012.00720 
  Access Paper or Ask Questions

Open-World Entity Segmentation


Jul 29, 2021
Lu Qi, Jason Kuen, Yi Wang, Jiuxiang Gu, Hengshuang Zhao, Zhe Lin, Philip Torr, Jiaya Jia

Figure 1 for Open-World Entity Segmentation
Figure 2 for Open-World Entity Segmentation
Figure 3 for Open-World Entity Segmentation
Figure 4 for Open-World Entity Segmentation
* Project page: http://luqi.info/Entity_Web 
  Access Paper or Ask Questions

Do Different Tracking Tasks Require Different Appearance Models?


Jul 05, 2021
Zhongdao Wang, Hengshuang Zhao, Ya-Li Li, Shengjin Wang, Philip H. S. Torr, Luca Bertinetto

Figure 1 for Do Different Tracking Tasks Require Different Appearance Models?
Figure 2 for Do Different Tracking Tasks Require Different Appearance Models?
Figure 3 for Do Different Tracking Tasks Require Different Appearance Models?
Figure 4 for Do Different Tracking Tasks Require Different Appearance Models?

  Access Paper or Ask Questions

Semi-supervised Semantic Segmentation with Directional Context-aware Consistency


Jun 27, 2021
Xin Lai, Zhuotao Tian, Li Jiang, Shu Liu, Hengshuang Zhao, Liwei Wang, Jiaya Jia

Figure 1 for Semi-supervised Semantic Segmentation with Directional Context-aware Consistency
Figure 2 for Semi-supervised Semantic Segmentation with Directional Context-aware Consistency
Figure 3 for Semi-supervised Semantic Segmentation with Directional Context-aware Consistency
Figure 4 for Semi-supervised Semantic Segmentation with Directional Context-aware Consistency
* Accepted to CVPR 2021. Code is available at https://github.com/dvlab-research/Context-Aware-Consistency 
  Access Paper or Ask Questions

Dual-Cross Central Difference Network for Face Anti-Spoofing


May 04, 2021
Zitong Yu, Yunxiao Qin, Hengshuang Zhao, Xiaobai Li, Guoying Zhao

Figure 1 for Dual-Cross Central Difference Network for Face Anti-Spoofing
Figure 2 for Dual-Cross Central Difference Network for Face Anti-Spoofing
Figure 3 for Dual-Cross Central Difference Network for Face Anti-Spoofing
Figure 4 for Dual-Cross Central Difference Network for Face Anti-Spoofing
* Accepted by IJCAI2021 
  Access Paper or Ask Questions

PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds


Apr 26, 2021
Mutian Xu, Runyu Ding, Hengshuang Zhao, Xiaojuan Qi

Figure 1 for PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds
Figure 2 for PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds
Figure 3 for PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds
Figure 4 for PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds
* To be appear in CVPR2021 
  Access Paper or Ask Questions

Distilling Knowledge via Knowledge Review


Apr 19, 2021
Pengguang Chen, Shu Liu, Hengshuang Zhao, Jiaya Jia

Figure 1 for Distilling Knowledge via Knowledge Review
Figure 2 for Distilling Knowledge via Knowledge Review
Figure 3 for Distilling Knowledge via Knowledge Review
Figure 4 for Distilling Knowledge via Knowledge Review
* CVPR 2021 
  Access Paper or Ask Questions

Bidirectional Projection Network for Cross Dimension Scene Understanding


Mar 26, 2021
Wenbo Hu, Hengshuang Zhao, Li Jiang, Jiaya Jia, Tien-Tsin Wong

Figure 1 for Bidirectional Projection Network for Cross Dimension Scene Understanding
Figure 2 for Bidirectional Projection Network for Cross Dimension Scene Understanding
Figure 3 for Bidirectional Projection Network for Cross Dimension Scene Understanding
Figure 4 for Bidirectional Projection Network for Cross Dimension Scene Understanding
* CVPR 2021 
 * CVPR 2021 (Oral) 
  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

Point Transformer


Dec 16, 2020
Hengshuang Zhao, Li Jiang, Jiaya Jia, Philip Torr, Vladlen Koltun

Figure 1 for Point Transformer
Figure 2 for Point Transformer
Figure 3 for Point Transformer
Figure 4 for Point Transformer

  Access Paper or Ask Questions

Fully Convolutional Networks for Panoptic Segmentation


Dec 01, 2020
Yanwei Li, Hengshuang Zhao, Xiaojuan Qi, Liwei Wang, Zeming Li, Jian Sun, Jiaya Jia

Figure 1 for Fully Convolutional Networks for Panoptic Segmentation
Figure 2 for Fully Convolutional Networks for Panoptic Segmentation
Figure 3 for Fully Convolutional Networks for Panoptic Segmentation
Figure 4 for Fully Convolutional Networks for Panoptic Segmentation

  Access Paper or Ask Questions

Generalized Few-Shot Semantic Segmentation


Oct 11, 2020
Zhuotao Tian, Xin Lai, Li Jiang, Michelle Shu, Hengshuang Zhao, Jiaya Jia

Figure 1 for Generalized Few-Shot Semantic Segmentation
Figure 2 for Generalized Few-Shot Semantic Segmentation
Figure 3 for Generalized Few-Shot Semantic Segmentation
Figure 4 for Generalized Few-Shot Semantic Segmentation
* 8 pages 
  Access Paper or Ask Questions

Prior Guided Feature Enrichment Network for Few-Shot Segmentation


Aug 04, 2020
Zhuotao Tian, Hengshuang Zhao, Michelle Shu, Zhicheng Yang, Ruiyu Li, Jiaya Jia

Figure 1 for Prior Guided Feature Enrichment Network for Few-Shot Segmentation
Figure 2 for Prior Guided Feature Enrichment Network for Few-Shot Segmentation
Figure 3 for Prior Guided Feature Enrichment Network for Few-Shot Segmentation
Figure 4 for Prior Guided Feature Enrichment Network for Few-Shot Segmentation
* 16 pages. To appear in TPAMI 
  Access Paper or Ask Questions

Exploring Self-attention for Image Recognition


Apr 28, 2020
Hengshuang Zhao, Jiaya Jia, Vladlen Koltun

Figure 1 for Exploring Self-attention for Image Recognition
Figure 2 for Exploring Self-attention for Image Recognition
Figure 3 for Exploring Self-attention for Image Recognition
Figure 4 for Exploring Self-attention for Image Recognition
* CVPR 2020, Code available at https://github.com/hszhao/SAN 
  Access Paper or Ask Questions

PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation


Apr 03, 2020
Li Jiang, Hengshuang Zhao, Shaoshuai Shi, Shu Liu, Chi-Wing Fu, Jiaya Jia

Figure 1 for PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation
Figure 2 for PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation
Figure 3 for PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation
Figure 4 for PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation
* CVPR 2020 
  Access Paper or Ask Questions

Dynamic Divide-and-Conquer Adversarial Training for Robust Semantic Segmentation


Mar 14, 2020
Xiaogang Xu, Hengshuang Zhao, Jiaya Jia

Figure 1 for Dynamic Divide-and-Conquer Adversarial Training for Robust Semantic Segmentation
Figure 2 for Dynamic Divide-and-Conquer Adversarial Training for Robust Semantic Segmentation
Figure 3 for Dynamic Divide-and-Conquer Adversarial Training for Robust Semantic Segmentation
Figure 4 for Dynamic Divide-and-Conquer Adversarial Training for Robust Semantic Segmentation
* in submission 
  Access Paper or Ask Questions

GridMask Data Augmentation


Jan 14, 2020
Pengguang Chen, Shu Liu, Hengshuang Zhao, Jiaya Jia

Figure 1 for GridMask Data Augmentation
Figure 2 for GridMask Data Augmentation
Figure 3 for GridMask Data Augmentation
Figure 4 for GridMask Data Augmentation

  Access Paper or Ask Questions

Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentation


Sep 23, 2019
Li Jiang, Hengshuang Zhao, Shu Liu, Xiaoyong Shen, Chi-Wing Fu, Jiaya Jia

Figure 1 for Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentation
Figure 2 for Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentation
Figure 3 for Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentation
Figure 4 for Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentation
* Accepted by ICCV 2019 
  Access Paper or Ask Questions

Region Refinement Network for Salient Object Detection


Jun 27, 2019
Zhuotao Tian, Hengshuang Zhao, Michelle Shu, Jiaze Wang, Ruiyu Li, Xiaoyong Shen, Jiaya Jia

Figure 1 for Region Refinement Network for Salient Object Detection
Figure 2 for Region Refinement Network for Salient Object Detection
Figure 3 for Region Refinement Network for Salient Object Detection
Figure 4 for Region Refinement Network for Salient Object Detection

  Access Paper or Ask Questions

UPSNet: A Unified Panoptic Segmentation Network


Jan 12, 2019
Yuwen Xiong, Renjie Liao, Hengshuang Zhao, Rui Hu, Min Bai, Ersin Yumer, Raquel Urtasun

Figure 1 for UPSNet: A Unified Panoptic Segmentation Network
Figure 2 for UPSNet: A Unified Panoptic Segmentation Network
Figure 3 for UPSNet: A Unified Panoptic Segmentation Network
Figure 4 for UPSNet: A Unified Panoptic Segmentation Network
* Technical report 
  Access Paper or Ask Questions

ICNet for Real-Time Semantic Segmentation on High-Resolution Images


Aug 20, 2018
Hengshuang Zhao, Xiaojuan Qi, Xiaoyong Shen, Jianping Shi, Jiaya Jia

Figure 1 for ICNet for Real-Time Semantic Segmentation on High-Resolution Images
Figure 2 for ICNet for Real-Time Semantic Segmentation on High-Resolution Images
Figure 3 for ICNet for Real-Time Semantic Segmentation on High-Resolution Images
Figure 4 for ICNet for Real-Time Semantic Segmentation on High-Resolution Images
* ECCV 2018 
  Access Paper or Ask Questions

SegStereo: Exploiting Semantic Information for Disparity Estimation


Jul 31, 2018
Guorun Yang, Hengshuang Zhao, Jianping Shi, Zhidong Deng, Jiaya Jia

Figure 1 for SegStereo: Exploiting Semantic Information for Disparity Estimation
Figure 2 for SegStereo: Exploiting Semantic Information for Disparity Estimation
Figure 3 for SegStereo: Exploiting Semantic Information for Disparity Estimation
Figure 4 for SegStereo: Exploiting Semantic Information for Disparity Estimation
* Accepted to ECCV 2018 
  Access Paper or Ask Questions

Automatic Real-time Background Cut for Portrait Videos


Apr 28, 2017
Xiaoyong Shen, Ruixing Wang, Hengshuang Zhao, Jiaya Jia

Figure 1 for Automatic Real-time Background Cut for Portrait Videos
Figure 2 for Automatic Real-time Background Cut for Portrait Videos
Figure 3 for Automatic Real-time Background Cut for Portrait Videos
Figure 4 for Automatic Real-time Background Cut for Portrait Videos

  Access Paper or Ask Questions

Pyramid Scene Parsing Network


Apr 27, 2017
Hengshuang Zhao, Jianping Shi, Xiaojuan Qi, Xiaogang Wang, Jiaya Jia

Figure 1 for Pyramid Scene Parsing Network
Figure 2 for Pyramid Scene Parsing Network
Figure 3 for Pyramid Scene Parsing Network
Figure 4 for Pyramid Scene Parsing Network
* CVPR 2017 
  Access Paper or Ask Questions