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 Xinchao Wang

Xinchao Wang

PONet: Robust 3D Human Pose Estimation via Learning Orientations Only


Dec 21, 2021
Jue Wang, Shaoli Huang, Xinchao Wang, Dacheng Tao

Figure 1 for PONet: Robust 3D Human Pose Estimation via Learning Orientations Only
Figure 2 for PONet: Robust 3D Human Pose Estimation via Learning Orientations Only
Figure 3 for PONet: Robust 3D Human Pose Estimation via Learning Orientations Only
Figure 4 for PONet: Robust 3D Human Pose Estimation via Learning Orientations Only

  Access Paper or Ask Questions

Up to 100x Faster Data-free Knowledge Distillation


Dec 12, 2021
Gongfan Fang, Kanya Mo, Xinchao Wang, Jie Song, Shitao Bei, Haofei Zhang, Mingli Song

Figure 1 for Up to 100x Faster Data-free Knowledge Distillation
Figure 2 for Up to 100x Faster Data-free Knowledge Distillation
Figure 3 for Up to 100x Faster Data-free Knowledge Distillation
Figure 4 for Up to 100x Faster Data-free Knowledge Distillation

  Access Paper or Ask Questions

Safe Distillation Box


Dec 05, 2021
Jingwen Ye, Yining Mao, Jie Song, Xinchao Wang, Cheng Jin, Mingli Song

Figure 1 for Safe Distillation Box
Figure 2 for Safe Distillation Box
Figure 3 for Safe Distillation Box
Figure 4 for Safe Distillation Box
* Accepted by AAAI2022 
  Access Paper or Ask Questions

Shunted Self-Attention via Multi-Scale Token Aggregation


Nov 30, 2021
Sucheng Ren, Daquan Zhou, Shengfeng He, Jiashi Feng, Xinchao Wang

Figure 1 for Shunted Self-Attention via Multi-Scale Token Aggregation
Figure 2 for Shunted Self-Attention via Multi-Scale Token Aggregation
Figure 3 for Shunted Self-Attention via Multi-Scale Token Aggregation
Figure 4 for Shunted Self-Attention via Multi-Scale Token Aggregation

  Access Paper or Ask Questions

MetaFormer is Actually What You Need for Vision


Nov 29, 2021
Weihao Yu, Mi Luo, Pan Zhou, Chenyang Si, Yichen Zhou, Xinchao Wang, Jiashi Feng, Shuicheng Yan

Figure 1 for MetaFormer is Actually What You Need for Vision
Figure 2 for MetaFormer is Actually What You Need for Vision
Figure 3 for MetaFormer is Actually What You Need for Vision
Figure 4 for MetaFormer is Actually What You Need for Vision
* Add "ResNet Strikes Back" results for comparison. Code: https://github.com/sail-sg/poolformer 
  Access Paper or Ask Questions

Meta Clustering Learning for Large-scale Unsupervised Person Re-identification


Nov 19, 2021
Xin Jin, Tianyu He, Zhiheng Yin, Xu Shen, Tongliang Liu, Xinchao Wang, Jianqiang Huang, Xian-Sheng Hua, Zhibo Chen

Figure 1 for Meta Clustering Learning for Large-scale Unsupervised Person Re-identification
Figure 2 for Meta Clustering Learning for Large-scale Unsupervised Person Re-identification
Figure 3 for Meta Clustering Learning for Large-scale Unsupervised Person Re-identification
Figure 4 for Meta Clustering Learning for Large-scale Unsupervised Person Re-identification

  Access Paper or Ask Questions

Mosaicking to Distill: Knowledge Distillation from Out-of-Domain Data


Oct 27, 2021
Gongfan Fang, Yifan Bao, Jie Song, Xinchao Wang, Donglin Xie, Chengchao Shen, Mingli Song

Figure 1 for Mosaicking to Distill: Knowledge Distillation from Out-of-Domain Data
Figure 2 for Mosaicking to Distill: Knowledge Distillation from Out-of-Domain Data
Figure 3 for Mosaicking to Distill: Knowledge Distillation from Out-of-Domain Data
Figure 4 for Mosaicking to Distill: Knowledge Distillation from Out-of-Domain Data

  Access Paper or Ask Questions

MEmoBERT: Pre-training Model with Prompt-based Learning for Multimodal Emotion Recognition


Oct 27, 2021
Jinming Zhao, Ruichen Li, Qin Jin, Xinchao Wang, Haizhou Li

Figure 1 for MEmoBERT: Pre-training Model with Prompt-based Learning for Multimodal Emotion Recognition
Figure 2 for MEmoBERT: Pre-training Model with Prompt-based Learning for Multimodal Emotion Recognition
Figure 3 for MEmoBERT: Pre-training Model with Prompt-based Learning for Multimodal Emotion Recognition
Figure 4 for MEmoBERT: Pre-training Model with Prompt-based Learning for Multimodal Emotion Recognition
* 4 papges, 2 figures 
  Access Paper or Ask Questions

Meta-Aggregator: Learning to Aggregate for 1-bit Graph Neural Networks


Sep 27, 2021
Yongcheng Jing, Yiding Yang, Xinchao Wang, Mingli Song, Dacheng Tao

Figure 1 for Meta-Aggregator: Learning to Aggregate for 1-bit Graph Neural Networks
Figure 2 for Meta-Aggregator: Learning to Aggregate for 1-bit Graph Neural Networks
Figure 3 for Meta-Aggregator: Learning to Aggregate for 1-bit Graph Neural Networks
Figure 4 for Meta-Aggregator: Learning to Aggregate for 1-bit Graph Neural Networks
* Accepted to ICCV 2021 
  Access Paper or Ask Questions

Structure-Aware Feature Generation for Zero-Shot Learning


Aug 16, 2021
Lianbo Zhang, Shaoli Huang, Xinchao Wang, Wei Liu, Dacheng Tao

Figure 1 for Structure-Aware Feature Generation for Zero-Shot Learning
Figure 2 for Structure-Aware Feature Generation for Zero-Shot Learning
Figure 3 for Structure-Aware Feature Generation for Zero-Shot Learning
Figure 4 for Structure-Aware Feature Generation for Zero-Shot Learning

  Access Paper or Ask Questions

Boundary Knowledge Translation based Reference Semantic Segmentation


Aug 01, 2021
Lechao Cheng, Zunlei Feng, Xinchao Wang, Ya Jie Liu, Jie Lei, Mingli Song

Figure 1 for Boundary Knowledge Translation based Reference Semantic Segmentation
Figure 2 for Boundary Knowledge Translation based Reference Semantic Segmentation
Figure 3 for Boundary Knowledge Translation based Reference Semantic Segmentation
Figure 4 for Boundary Knowledge Translation based Reference Semantic Segmentation
* Accepted by IJCAI 2021. arXiv admin note: text overlap with arXiv:2108.00379 
  Access Paper or Ask Questions

Edge-competing Pathological Liver Vessel Segmentation with Limited Labels


Aug 01, 2021
Zunlei Feng, Zhonghua Wang, Xinchao Wang, Xiuming Zhang, Lechao Cheng, Jie Lei, Yuexuan Wang, Mingli Song

Figure 1 for Edge-competing Pathological Liver Vessel Segmentation with Limited Labels
Figure 2 for Edge-competing Pathological Liver Vessel Segmentation with Limited Labels
Figure 3 for Edge-competing Pathological Liver Vessel Segmentation with Limited Labels
Figure 4 for Edge-competing Pathological Liver Vessel Segmentation with Limited Labels
* Accepted by AAAI 2021 
  Access Paper or Ask Questions

Visual Boundary Knowledge Translation for Foreground Segmentation


Aug 01, 2021
Zunlei Feng, Lechao Cheng, Xinchao Wang, Xiang Wang, Yajie Liu, Xiangtong Du, Mingli Song

Figure 1 for Visual Boundary Knowledge Translation for Foreground Segmentation
Figure 2 for Visual Boundary Knowledge Translation for Foreground Segmentation
Figure 3 for Visual Boundary Knowledge Translation for Foreground Segmentation
Figure 4 for Visual Boundary Knowledge Translation for Foreground Segmentation
* Accepted by AAAI 2021 
  Access Paper or Ask Questions

Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Tracking


Jun 07, 2021
Yiding Yang, Zhou Ren, Haoxiang Li, Chunluan Zhou, Xinchao Wang, Gang Hua

Figure 1 for Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Tracking
Figure 2 for Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Tracking
Figure 3 for Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Tracking
Figure 4 for Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Tracking
* Accepted by CVPR 2021 
  Access Paper or Ask Questions

Contrastive Model Inversion for Data-Free Knowledge Distillation


May 18, 2021
Gongfan Fang, Jie Song, Xinchao Wang, Chengchao Shen, Xingen Wang, Mingli Song

Figure 1 for Contrastive Model Inversion for Data-Free Knowledge Distillation
Figure 2 for Contrastive Model Inversion for Data-Free Knowledge Distillation
Figure 3 for Contrastive Model Inversion for Data-Free Knowledge Distillation
Figure 4 for Contrastive Model Inversion for Data-Free Knowledge Distillation

  Access Paper or Ask Questions

KDExplainer: A Task-oriented Attention Model for Explaining Knowledge Distillation


May 12, 2021
Mengqi Xue, Jie Song, Xinchao Wang, Ying Chen, Xingen Wang, Mingli Song

Figure 1 for KDExplainer: A Task-oriented Attention Model for Explaining Knowledge Distillation
Figure 2 for KDExplainer: A Task-oriented Attention Model for Explaining Knowledge Distillation
Figure 3 for KDExplainer: A Task-oriented Attention Model for Explaining Knowledge Distillation
Figure 4 for KDExplainer: A Task-oriented Attention Model for Explaining Knowledge Distillation
* 7 pages, 4 figures, accepted to IJCAI 2021 
  Access Paper or Ask Questions

Online Multiple Object Tracking with Cross-Task Synergy


Apr 01, 2021
Song Guo, Jingya Wang, Xinchao Wang, Dacheng Tao

Figure 1 for Online Multiple Object Tracking with Cross-Task Synergy
Figure 2 for Online Multiple Object Tracking with Cross-Task Synergy
Figure 3 for Online Multiple Object Tracking with Cross-Task Synergy
Figure 4 for Online Multiple Object Tracking with Cross-Task Synergy
* accepted by CVPR 2021 
  Access Paper or Ask Questions

Training Generative Adversarial Networks in One Stage


Mar 04, 2021
Chengchao Shen, Youtan Yin, Xinchao Wang, Xubin LI, Jie Song, Mingli Song

Figure 1 for Training Generative Adversarial Networks in One Stage
Figure 2 for Training Generative Adversarial Networks in One Stage
Figure 3 for Training Generative Adversarial Networks in One Stage
Figure 4 for Training Generative Adversarial Networks in One Stage
* Accepted to CVPR 2021 
  Access Paper or Ask Questions

SPAGAN: Shortest Path Graph Attention Network


Jan 10, 2021
Yiding Yang, Xinchao Wang, Mingli Song, Junsong Yuan, Dacheng Tao

Figure 1 for SPAGAN: Shortest Path Graph Attention Network
Figure 2 for SPAGAN: Shortest Path Graph Attention Network
Figure 3 for SPAGAN: Shortest Path Graph Attention Network
Figure 4 for SPAGAN: Shortest Path Graph Attention Network
* Accepted by IJCAI 2019 
  Access Paper or Ask Questions

Progressive Network Grafting for Few-Shot Knowledge Distillation


Dec 11, 2020
Chengchao Shen, Xinchao Wang, Youtan Yin, Jie Song, Sihui Luo, Mingli Song

Figure 1 for Progressive Network Grafting for Few-Shot Knowledge Distillation
Figure 2 for Progressive Network Grafting for Few-Shot Knowledge Distillation
Figure 3 for Progressive Network Grafting for Few-Shot Knowledge Distillation
Figure 4 for Progressive Network Grafting for Few-Shot Knowledge Distillation
* Accepted to AAAI 2021 
  Access Paper or Ask Questions

Overcoming Catastrophic Forgetting in Graph Neural Networks


Dec 10, 2020
Huihui Liu, Yiding Yang, Xinchao Wang

Figure 1 for Overcoming Catastrophic Forgetting in Graph Neural Networks
Figure 2 for Overcoming Catastrophic Forgetting in Graph Neural Networks
Figure 3 for Overcoming Catastrophic Forgetting in Graph Neural Networks
Figure 4 for Overcoming Catastrophic Forgetting in Graph Neural Networks
* Accepted by AAAI 2021 
  Access Paper or Ask Questions

SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data


Dec 09, 2020
Shaoli Huang, Xinchao Wang, Dacheng Tao

Figure 1 for SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data
Figure 2 for SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data
Figure 3 for SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data
Figure 4 for SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data
* Accepted by AAAI2021 
  Access Paper or Ask Questions

Learning Propagation Rules for Attribution Map Generation


Oct 14, 2020
Yiding Yang, Jiayan Qiu, Mingli Song, Dacheng Tao, Xinchao Wang

Figure 1 for Learning Propagation Rules for Attribution Map Generation
Figure 2 for Learning Propagation Rules for Attribution Map Generation
Figure 3 for Learning Propagation Rules for Attribution Map Generation
Figure 4 for Learning Propagation Rules for Attribution Map Generation
* Accepted by ECCV 2020 
  Access Paper or Ask Questions

Factorizable Graph Convolutional Networks


Oct 12, 2020
Yiding Yang, Zunlei Feng, Mingli Song, Xinchao Wang

Figure 1 for Factorizable Graph Convolutional Networks
Figure 2 for Factorizable Graph Convolutional Networks
Figure 3 for Factorizable Graph Convolutional Networks
Figure 4 for Factorizable Graph Convolutional Networks
* Accepted by NeurIPS 2020 
  Access Paper or Ask Questions

Tracking-by-Counting: Using Network Flows on Crowd Density Maps for Tracking Multiple Targets


Jul 18, 2020
Weihong Ren, Xinchao Wang, Jiandong Tian, Yandong Tang, Antoni B. Chan

Figure 1 for Tracking-by-Counting: Using Network Flows on Crowd Density Maps for Tracking Multiple Targets
Figure 2 for Tracking-by-Counting: Using Network Flows on Crowd Density Maps for Tracking Multiple Targets
Figure 3 for Tracking-by-Counting: Using Network Flows on Crowd Density Maps for Tracking Multiple Targets
Figure 4 for Tracking-by-Counting: Using Network Flows on Crowd Density Maps for Tracking Multiple Targets
* 14 pages 
  Access Paper or Ask Questions

Impression Space from Deep Template Network


Jul 10, 2020
Gongfan Fang, Xinchao Wang, Haofei Zhang, Jie Song, Mingli Song

Figure 1 for Impression Space from Deep Template Network
Figure 2 for Impression Space from Deep Template Network
Figure 3 for Impression Space from Deep Template Network
Figure 4 for Impression Space from Deep Template Network

  Access Paper or Ask Questions

Disassembling Object Representations without Labels


Apr 03, 2020
Zunlei Feng, Xinchao Wang, Yongming He, Yike Yuan, Xin Gao, Mingli Song

Figure 1 for Disassembling Object Representations without Labels
Figure 2 for Disassembling Object Representations without Labels
Figure 3 for Disassembling Object Representations without Labels
Figure 4 for Disassembling Object Representations without Labels

  Access Paper or Ask Questions