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 Hao Tang

Hao Tang

On the Difficulty of Segmenting Words with Attention


Sep 21, 2021
Ramon Sanabria, Hao Tang, Sharon Goldwater

Figure 1 for On the Difficulty of Segmenting Words with Attention
Figure 2 for On the Difficulty of Segmenting Words with Attention
Figure 3 for On the Difficulty of Segmenting Words with Attention
Figure 4 for On the Difficulty of Segmenting Words with Attention
* Accepted at the "Workshop on Insights from Negative Results in NLP" (EMNLP 2021) 
  Access Paper or Ask Questions

Multi-Sample based Contrastive Loss for Top-k Recommendation


Sep 01, 2021
Hao Tang, Guoshuai Zhao, Yuxia Wu, Xueming Qian

Figure 1 for Multi-Sample based Contrastive Loss for Top-k Recommendation
Figure 2 for Multi-Sample based Contrastive Loss for Top-k Recommendation
Figure 3 for Multi-Sample based Contrastive Loss for Top-k Recommendation
Figure 4 for Multi-Sample based Contrastive Loss for Top-k Recommendation
* 12 pages,7 figures,6 tables 
  Access Paper or Ask Questions

Layout-to-Image Translation with Double Pooling Generative Adversarial Networks


Aug 29, 2021
Hao Tang, Nicu Sebe

Figure 1 for Layout-to-Image Translation with Double Pooling Generative Adversarial Networks
Figure 2 for Layout-to-Image Translation with Double Pooling Generative Adversarial Networks
Figure 3 for Layout-to-Image Translation with Double Pooling Generative Adversarial Networks
Figure 4 for Layout-to-Image Translation with Double Pooling Generative Adversarial Networks
* Accepted to TIP 
  Access Paper or Ask Questions

Intrinsic-Extrinsic Preserved GANs for Unsupervised 3D Pose Transfer


Aug 20, 2021
Haoyu Chen, Hao Tang, Henglin Shi, Wei Peng, Nicu Sebe, Guoying Zhao

Figure 1 for Intrinsic-Extrinsic Preserved GANs for Unsupervised 3D Pose Transfer
Figure 2 for Intrinsic-Extrinsic Preserved GANs for Unsupervised 3D Pose Transfer
Figure 3 for Intrinsic-Extrinsic Preserved GANs for Unsupervised 3D Pose Transfer
Figure 4 for Intrinsic-Extrinsic Preserved GANs for Unsupervised 3D Pose Transfer
* ICCV 2021 
  Access Paper or Ask Questions

Unsupervised Geodesic-preserved Generative Adversarial Networks for Unconstrained 3D Pose Transfer


Aug 17, 2021
Haoyu Chen, Hao Tang, Henglin Shi, Wei Peng, Nicu Sebe, Guoying Zhao

Figure 1 for Unsupervised Geodesic-preserved Generative Adversarial Networks for Unconstrained 3D Pose Transfer
Figure 2 for Unsupervised Geodesic-preserved Generative Adversarial Networks for Unconstrained 3D Pose Transfer
Figure 3 for Unsupervised Geodesic-preserved Generative Adversarial Networks for Unconstrained 3D Pose Transfer
Figure 4 for Unsupervised Geodesic-preserved Generative Adversarial Networks for Unconstrained 3D Pose Transfer
* ICCV 2021 
  Access Paper or Ask Questions

Recurrent Mask Refinement for Few-Shot Medical Image Segmentation


Aug 04, 2021
Hao Tang, Xingwei Liu, Shanlin Sun, Xiangyi Yan, Xiaohui Xie

Figure 1 for Recurrent Mask Refinement for Few-Shot Medical Image Segmentation
Figure 2 for Recurrent Mask Refinement for Few-Shot Medical Image Segmentation
Figure 3 for Recurrent Mask Refinement for Few-Shot Medical Image Segmentation
Figure 4 for Recurrent Mask Refinement for Few-Shot Medical Image Segmentation
* Accepted ICCV 2021 
  Access Paper or Ask Questions

Looking Outside the Window: Wide-Context Transformer for the Semantic Segmentation of High-Resolution Remote Sensing Images


Jul 14, 2021
Lei Ding, Dong Lin, Shaofu Lin, Jing Zhang, Xiaojie Cui, Yuebin Wang, Hao Tang, Lorenzo Bruzzone

Figure 1 for Looking Outside the Window: Wide-Context Transformer for the Semantic Segmentation of High-Resolution Remote Sensing Images
Figure 2 for Looking Outside the Window: Wide-Context Transformer for the Semantic Segmentation of High-Resolution Remote Sensing Images
Figure 3 for Looking Outside the Window: Wide-Context Transformer for the Semantic Segmentation of High-Resolution Remote Sensing Images
Figure 4 for Looking Outside the Window: Wide-Context Transformer for the Semantic Segmentation of High-Resolution Remote Sensing Images

  Access Paper or Ask Questions

Cross-View Exocentric to Egocentric Video Synthesis


Jul 07, 2021
Gaowen Liu, Hao Tang, Hugo Latapie, Jason Corso, Yan Yan

Figure 1 for Cross-View Exocentric to Egocentric Video Synthesis
Figure 2 for Cross-View Exocentric to Egocentric Video Synthesis
Figure 3 for Cross-View Exocentric to Egocentric Video Synthesis
Figure 4 for Cross-View Exocentric to Egocentric Video Synthesis
* ACM MM 2021 
  Access Paper or Ask Questions

Looking Outside the Window: Wider-Context Transformer for the Semantic Segmentation of High-Resolution Remote Sensing Images


Jul 01, 2021
Lei Ding, Dong Lin, Shaofu Lin, Jing Zhang, Xiaojie Cui, Yuebin Wang, Hao Tang, Lorenzo Bruzzone

Figure 1 for Looking Outside the Window: Wider-Context Transformer for the Semantic Segmentation of High-Resolution Remote Sensing Images
Figure 2 for Looking Outside the Window: Wider-Context Transformer for the Semantic Segmentation of High-Resolution Remote Sensing Images
Figure 3 for Looking Outside the Window: Wider-Context Transformer for the Semantic Segmentation of High-Resolution Remote Sensing Images
Figure 4 for Looking Outside the Window: Wider-Context Transformer for the Semantic Segmentation of High-Resolution Remote Sensing Images

  Access Paper or Ask Questions

Total Generate: Cycle in Cycle Generative Adversarial Networks for Generating Human Faces, Hands, Bodies, and Natural Scenes


Jun 21, 2021
Hao Tang, Nicu Sebe

Figure 1 for Total Generate: Cycle in Cycle Generative Adversarial Networks for Generating Human Faces, Hands, Bodies, and Natural Scenes
Figure 2 for Total Generate: Cycle in Cycle Generative Adversarial Networks for Generating Human Faces, Hands, Bodies, and Natural Scenes
Figure 3 for Total Generate: Cycle in Cycle Generative Adversarial Networks for Generating Human Faces, Hands, Bodies, and Natural Scenes
Figure 4 for Total Generate: Cycle in Cycle Generative Adversarial Networks for Generating Human Faces, Hands, Bodies, and Natural Scenes
* Accepted to TMM, an extended version of a paper published in ACM MM 2019. arXiv admin note: substantial text overlap with arXiv:1908.00999 
  Access Paper or Ask Questions

Controllable Person Image Synthesis with Spatially-Adaptive Warped Normalization


Jun 03, 2021
Jichao Zhang, Aliaksandr Siarohin, Hao Tang, Jingjing Chen, Enver Sangineto, Wei Wang, Nicu Sebe

Figure 1 for Controllable Person Image Synthesis with Spatially-Adaptive Warped Normalization
Figure 2 for Controllable Person Image Synthesis with Spatially-Adaptive Warped Normalization
Figure 3 for Controllable Person Image Synthesis with Spatially-Adaptive Warped Normalization
Figure 4 for Controllable Person Image Synthesis with Spatially-Adaptive Warped Normalization
* 12 pages 
  Access Paper or Ask Questions

Transformer-Based Source-Free Domain Adaptation


May 28, 2021
Guanglei Yang, Hao Tang, Zhun Zhong, Mingli Ding, Ling Shao, Nicu Sebe, Elisa Ricci

Figure 1 for Transformer-Based Source-Free Domain Adaptation
Figure 2 for Transformer-Based Source-Free Domain Adaptation
Figure 3 for Transformer-Based Source-Free Domain Adaptation
Figure 4 for Transformer-Based Source-Free Domain Adaptation

  Access Paper or Ask Questions

Cloth Interactive Transformer for Virtual Try-On


Apr 12, 2021
Bin Ren, Hao Tang, Fanyang Meng, Runwei Ding, Ling Shao, Philip H. S. Torr, Nicu Sebe

* 11 pages, 6 figures, 
  Access Paper or Ask Questions

Transformers Solve the Limited Receptive Field for Monocular Depth Prediction


Mar 22, 2021
Guanglei Yang, Hao Tang, Mingli Ding, Nicu Sebe, Elisa Ricci

Figure 1 for Transformers Solve the Limited Receptive Field for Monocular Depth Prediction
Figure 2 for Transformers Solve the Limited Receptive Field for Monocular Depth Prediction
Figure 3 for Transformers Solve the Limited Receptive Field for Monocular Depth Prediction
Figure 4 for Transformers Solve the Limited Receptive Field for Monocular Depth Prediction

  Access Paper or Ask Questions

Adversarial Shape Learning for Building Extraction in VHR Remote Sensing Images


Mar 17, 2021
Lei Ding, Hao Tang, Yahui Liu, Yilei Shi, Lorenzo Bruzzone

Figure 1 for Adversarial Shape Learning for Building Extraction in VHR Remote Sensing Images
Figure 2 for Adversarial Shape Learning for Building Extraction in VHR Remote Sensing Images
Figure 3 for Adversarial Shape Learning for Building Extraction in VHR Remote Sensing Images
Figure 4 for Adversarial Shape Learning for Building Extraction in VHR Remote Sensing Images

  Access Paper or Ask Questions

Spatial Context-Aware Self-Attention Model For Multi-Organ Segmentation


Dec 16, 2020
Hao Tang, Xingwei Liu, Kun Han, Shanlin Sun, Narisu Bai, Xuming Chen, Huang Qian, Yong Liu, Xiaohui Xie

Figure 1 for Spatial Context-Aware Self-Attention Model For Multi-Organ Segmentation
Figure 2 for Spatial Context-Aware Self-Attention Model For Multi-Organ Segmentation
Figure 3 for Spatial Context-Aware Self-Attention Model For Multi-Organ Segmentation
Figure 4 for Spatial Context-Aware Self-Attention Model For Multi-Organ Segmentation
* Accepted WACV 2021 
  Access Paper or Ask Questions

Refactoring Policy for Compositional Generalizability using Self-Supervised Object Proposals


Oct 26, 2020
Tongzhou Mu, Jiayuan Gu, Zhiwei Jia, Hao Tang, Hao Su

Figure 1 for Refactoring Policy for Compositional Generalizability using Self-Supervised Object Proposals
Figure 2 for Refactoring Policy for Compositional Generalizability using Self-Supervised Object Proposals
Figure 3 for Refactoring Policy for Compositional Generalizability using Self-Supervised Object Proposals
Figure 4 for Refactoring Policy for Compositional Generalizability using Self-Supervised Object Proposals
* 34th Conference on Neural Information Processing Systems (NeurIPS 2020), Vancouver, Canada 
  Access Paper or Ask Questions

Towards Scale-Invariant Graph-related Problem Solving by Iterative Homogeneous Graph Neural Networks


Oct 26, 2020
Hao Tang, Zhiao Huang, Jiayuan Gu, Bao-Liang Lu, Hao Su

Figure 1 for Towards Scale-Invariant Graph-related Problem Solving by Iterative Homogeneous Graph Neural Networks
Figure 2 for Towards Scale-Invariant Graph-related Problem Solving by Iterative Homogeneous Graph Neural Networks
Figure 3 for Towards Scale-Invariant Graph-related Problem Solving by Iterative Homogeneous Graph Neural Networks
Figure 4 for Towards Scale-Invariant Graph-related Problem Solving by Iterative Homogeneous Graph Neural Networks
* To appear at NeurIPS 2020 
  Access Paper or Ask Questions

Dual Attention GANs for Semantic Image Synthesis


Aug 29, 2020
Hao Tang, Song Bai, Nicu Sebe

Figure 1 for Dual Attention GANs for Semantic Image Synthesis
Figure 2 for Dual Attention GANs for Semantic Image Synthesis
Figure 3 for Dual Attention GANs for Semantic Image Synthesis
Figure 4 for Dual Attention GANs for Semantic Image Synthesis
* Accepted to ACM MM 2020, camera ready (9 pages) + supplementary (10 pages) 
  Access Paper or Ask Questions

Bipartite Graph Reasoning GANs for Person Image Generation


Aug 20, 2020
Hao Tang, Song Bai, Philip H. S. Torr, Nicu Sebe

Figure 1 for Bipartite Graph Reasoning GANs for Person Image Generation
Figure 2 for Bipartite Graph Reasoning GANs for Person Image Generation
Figure 3 for Bipartite Graph Reasoning GANs for Person Image Generation
Figure 4 for Bipartite Graph Reasoning GANs for Person Image Generation
* 13 pages, 6 figures, accepted to BMVC 2020 as an oral paper, fix typos 
  Access Paper or Ask Questions

Audio-Visual Event Localization via Recursive Fusion by Joint Co-Attention


Aug 14, 2020
Bin Duan, Hao Tang, Wei Wang, Ziliang Zong, Guowei Yang, Yan Yan

Figure 1 for Audio-Visual Event Localization via Recursive Fusion by Joint Co-Attention
Figure 2 for Audio-Visual Event Localization via Recursive Fusion by Joint Co-Attention
Figure 3 for Audio-Visual Event Localization via Recursive Fusion by Joint Co-Attention
Figure 4 for Audio-Visual Event Localization via Recursive Fusion by Joint Co-Attention

  Access Paper or Ask Questions

DF-GAN: Deep Fusion Generative Adversarial Networks for Text-to-Image Synthesis


Aug 13, 2020
Ming Tao, Hao Tang, Songsong Wu, Nicu Sebe, Fei Wu, Xiao-Yuan Jing

Figure 1 for DF-GAN: Deep Fusion Generative Adversarial Networks for Text-to-Image Synthesis
Figure 2 for DF-GAN: Deep Fusion Generative Adversarial Networks for Text-to-Image Synthesis
Figure 3 for DF-GAN: Deep Fusion Generative Adversarial Networks for Text-to-Image Synthesis
Figure 4 for DF-GAN: Deep Fusion Generative Adversarial Networks for Text-to-Image Synthesis

  Access Paper or Ask Questions

Dual In-painting Model for Unsupervised Gaze Correction and Animation in the Wild


Aug 09, 2020
Jichao Zhang, Jingjing Chen, Hao Tang, Wei Wang, Yan Yan, Enver Sangineto, Nicu Sebe

Figure 1 for Dual In-painting Model for Unsupervised Gaze Correction and Animation in the Wild
Figure 2 for Dual In-painting Model for Unsupervised Gaze Correction and Animation in the Wild
Figure 3 for Dual In-painting Model for Unsupervised Gaze Correction and Animation in the Wild
Figure 4 for Dual In-painting Model for Unsupervised Gaze Correction and Animation in the Wild
* Accepted By ACMMM 2020 
  Access Paper or Ask Questions

Cross-View Image Synthesis with Deformable Convolution and Attention Mechanism


Jul 20, 2020
Hao Ding, Songsong Wu, Hao Tang, Fei Wu, Guangwei Gao, Xiao-Yuan Jing

Figure 1 for Cross-View Image Synthesis with Deformable Convolution and Attention Mechanism
Figure 2 for Cross-View Image Synthesis with Deformable Convolution and Attention Mechanism
Figure 3 for Cross-View Image Synthesis with Deformable Convolution and Attention Mechanism
Figure 4 for Cross-View Image Synthesis with Deformable Convolution and Attention Mechanism

  Access Paper or Ask Questions

XingGAN for Person Image Generation


Jul 17, 2020
Hao Tang, Song Bai, Li Zhang, Philip H. S. Torr, Nicu Sebe

Figure 1 for XingGAN for Person Image Generation
Figure 2 for XingGAN for Person Image Generation
Figure 3 for XingGAN for Person Image Generation
Figure 4 for XingGAN for Person Image Generation
* Accepted to ECCV 2020, camera ready (16 pages) + supplementary (6 pages) 
  Access Paper or Ask Questions