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 Qi Tian

Qi Tian

Location-Sensitive Visual Recognition with Cross-IOU Loss


Apr 11, 2021
Kaiwen Duan, Lingxi Xie, Honggang Qi, Song Bai, Qingming Huang, Qi Tian

* 13 pages, 7 figures and 5 tables 
  Access Paper or Ask Questions

CondenseNet V2: Sparse Feature Reactivation for Deep Networks


Apr 09, 2021
Le Yang, Haojun Jiang, Ruojin Cai, Yulin Wang, Shiji Song, Gao Huang, Qi Tian

* CVPR 2021 
  Access Paper or Ask Questions

Adaptive Mutual Supervision for Weakly-Supervised Temporal Action Localization


Apr 06, 2021
Chen Ju, Peisen Zhao, Siheng Chen, Ya Zhang, Xiaoyun Zhang, Qi Tian

Figure 1 for Adaptive Mutual Supervision for Weakly-Supervised Temporal Action Localization
Figure 2 for Adaptive Mutual Supervision for Weakly-Supervised Temporal Action Localization
Figure 3 for Adaptive Mutual Supervision for Weakly-Supervised Temporal Action Localization
Figure 4 for Adaptive Mutual Supervision for Weakly-Supervised Temporal Action Localization

  Access Paper or Ask Questions

Spatiotemporal Transformer for Video-based Person Re-identification


Mar 30, 2021
Tianyu Zhang, Longhui Wei, Lingxi Xie, Zijie Zhuang, Yongfei Zhang, Bo Li, Qi Tian

Figure 1 for Spatiotemporal Transformer for Video-based Person Re-identification
Figure 2 for Spatiotemporal Transformer for Video-based Person Re-identification
Figure 3 for Spatiotemporal Transformer for Video-based Person Re-identification
Figure 4 for Spatiotemporal Transformer for Video-based Person Re-identification
* 10 pages, 7 figures 
  Access Paper or Ask Questions

TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization


Mar 27, 2021
Wei Gao, Fang Wan, Xingjia Pan, Zhiliang Peng, Qi Tian, Zhenjun Han, Bolei Zhou, Qixiang Ye

Figure 1 for TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization
Figure 2 for TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization
Figure 3 for TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization
Figure 4 for TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization
* 10 pages, 9 figures. For appendix, 6 pages, 4 figures 
  Access Paper or Ask Questions

Unsupervised Domain Adaptation for Image Classification via Structure-Conditioned Adversarial Learning


Mar 04, 2021
Hui Wang, Jian Tian, Songyuan Li, Hanbin Zhao, Qi Tian, Fei Wu, Xi Li

Figure 1 for Unsupervised Domain Adaptation for Image Classification via Structure-Conditioned Adversarial Learning
Figure 2 for Unsupervised Domain Adaptation for Image Classification via Structure-Conditioned Adversarial Learning
Figure 3 for Unsupervised Domain Adaptation for Image Classification via Structure-Conditioned Adversarial Learning
Figure 4 for Unsupervised Domain Adaptation for Image Classification via Structure-Conditioned Adversarial Learning

  Access Paper or Ask Questions

Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss


Jan 28, 2021
Xue Yang, Junchi Yan, Qi Ming, Wentao Wang, Xiaopeng Zhang, Qi Tian

Figure 1 for Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss
Figure 2 for Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss
Figure 3 for Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss
Figure 4 for Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss
* 15 pages, 6 figures, 9 tables, codes are available at https://github.com/yangxue0827/RotationDetection 
  Access Paper or Ask Questions

Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses


Dec 15, 2020
Chen Ju, Peisen Zhao, Ya Zhang, Yanfeng Wang, Qi Tian

Figure 1 for Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses
Figure 2 for Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses
Figure 3 for Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses
Figure 4 for Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses

  Access Paper or Ask Questions

UnrealPerson: An Adaptive Pipeline towards Costless Person Re-identification


Dec 09, 2020
Tianyu Zhang, Lingxi Xie, Longhui Wei, Zijie Zhuang, Yongfei Zhang, Bo Li, Qi Tian

Figure 1 for UnrealPerson: An Adaptive Pipeline towards Costless Person Re-identification
Figure 2 for UnrealPerson: An Adaptive Pipeline towards Costless Person Re-identification
Figure 3 for UnrealPerson: An Adaptive Pipeline towards Costless Person Re-identification
Figure 4 for UnrealPerson: An Adaptive Pipeline towards Costless Person Re-identification
* 10 pages, 5 figure 
  Access Paper or Ask Questions

ESAD: End-to-end Deep Semi-supervised Anomaly Detection


Dec 09, 2020
Chaoqin Huang, Fei Ye, Ya Zhang, Yan-Feng Wang, Qi Tian

Figure 1 for ESAD: End-to-end Deep Semi-supervised Anomaly Detection
Figure 2 for ESAD: End-to-end Deep Semi-supervised Anomaly Detection
Figure 3 for ESAD: End-to-end Deep Semi-supervised Anomaly Detection
Figure 4 for ESAD: End-to-end Deep Semi-supervised Anomaly Detection

  Access Paper or Ask Questions

Hierarchical Semantic Aggregation for Contrastive Representation Learning


Dec 04, 2020
Haohang Xu, Xiaopeng Zhang, Hao Li, Lingxi Xie, Hongkai Xiong, Qi Tian

Figure 1 for Hierarchical Semantic Aggregation for Contrastive Representation Learning
Figure 2 for Hierarchical Semantic Aggregation for Contrastive Representation Learning
Figure 3 for Hierarchical Semantic Aggregation for Contrastive Representation Learning
Figure 4 for Hierarchical Semantic Aggregation for Contrastive Representation Learning

  Access Paper or Ask Questions

Privileged Knowledge Distillation for Online Action Detection


Dec 03, 2020
Peisen Zhao, Lingxi Xie, Ya Zhang, Yanfeng Wang, Qi Tian

Figure 1 for Privileged Knowledge Distillation for Online Action Detection
Figure 2 for Privileged Knowledge Distillation for Online Action Detection
Figure 3 for Privileged Knowledge Distillation for Online Action Detection
Figure 4 for Privileged Knowledge Distillation for Online Action Detection

  Access Paper or Ask Questions

Omni-GAN: On the Secrets of cGANs and Beyond


Nov 26, 2020
Peng Zhou, Lingxi Xie, Bingbing Ni, Qi Tian

Figure 1 for Omni-GAN: On the Secrets of cGANs and Beyond
Figure 2 for Omni-GAN: On the Secrets of cGANs and Beyond
Figure 3 for Omni-GAN: On the Secrets of cGANs and Beyond
Figure 4 for Omni-GAN: On the Secrets of cGANs and Beyond
* Code is available at https://github.com/PeterouZh/Omni-GAN-PyTorch 
  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

Self-Adaptively Learning to Demoire from Focused and Defocused Image Pairs


Nov 05, 2020
Lin Liu, Shanxin Yuan, Jianzhuang Liu, Liping Bao, Gregory Slabaugh, Qi Tian

Figure 1 for Self-Adaptively Learning to Demoire from Focused and Defocused Image Pairs
Figure 2 for Self-Adaptively Learning to Demoire from Focused and Defocused Image Pairs
Figure 3 for Self-Adaptively Learning to Demoire from Focused and Defocused Image Pairs
Figure 4 for Self-Adaptively Learning to Demoire from Focused and Defocused Image Pairs
* Accepted to NeurIPS 2020. Project page: "http://home.ustc.edu.cn/~ll0825/project_FDNet.html" 
  Access Paper or Ask Questions

Center-wise Local Image Mixture For Contrastive Representation Learning


Nov 05, 2020
Hao Li, Xiaopeng Zhang, Ruoyu Sun, Hongkai Xiong, Qi Tian

Figure 1 for Center-wise Local Image Mixture For Contrastive Representation Learning
Figure 2 for Center-wise Local Image Mixture For Contrastive Representation Learning
Figure 3 for Center-wise Local Image Mixture For Contrastive Representation Learning
Figure 4 for Center-wise Local Image Mixture For Contrastive Representation Learning

  Access Paper or Ask Questions

CooGAN: A Memory-Efficient Framework for High-Resolution Facial Attribute Editing


Nov 03, 2020
Xuanhong Chen, Bingbing Ni, Naiyuan Liu, Ziang Liu, Yiliu Jiang, Loc Truong, Qi Tian

Figure 1 for CooGAN: A Memory-Efficient Framework for High-Resolution Facial Attribute Editing
Figure 2 for CooGAN: A Memory-Efficient Framework for High-Resolution Facial Attribute Editing
Figure 3 for CooGAN: A Memory-Efficient Framework for High-Resolution Facial Attribute Editing
Figure 4 for CooGAN: A Memory-Efficient Framework for High-Resolution Facial Attribute Editing
* European Conference on Computer Vision(ECCV) 2020 
  Access Paper or Ask Questions

Loss-rescaling VQA: Revisiting Language Prior Problem from a Class-imbalance View


Oct 30, 2020
Yangyang Guo, Liqiang Nie, Zhiyong Cheng, Qi Tian

Figure 1 for Loss-rescaling VQA: Revisiting Language Prior Problem from a Class-imbalance View
Figure 2 for Loss-rescaling VQA: Revisiting Language Prior Problem from a Class-imbalance View
Figure 3 for Loss-rescaling VQA: Revisiting Language Prior Problem from a Class-imbalance View
Figure 4 for Loss-rescaling VQA: Revisiting Language Prior Problem from a Class-imbalance View

  Access Paper or Ask Questions

One-bit Supervision for Image Classification


Sep 16, 2020
Hengtong Hu, Lingxi Xie, Zewei Du, Richang Hong, Qi Tian

Figure 1 for One-bit Supervision for Image Classification
Figure 2 for One-bit Supervision for Image Classification
Figure 3 for One-bit Supervision for Image Classification
Figure 4 for One-bit Supervision for Image Classification

  Access Paper or Ask Questions

Reinforced Axial Refinement Network for Monocular 3D Object Detection


Aug 31, 2020
Lijie Liu, Chufan Wu, Jiwen Lu, Lingxi Xie, Jie Zhou, Qi Tian

Figure 1 for Reinforced Axial Refinement Network for Monocular 3D Object Detection
Figure 2 for Reinforced Axial Refinement Network for Monocular 3D Object Detection
Figure 3 for Reinforced Axial Refinement Network for Monocular 3D Object Detection
Figure 4 for Reinforced Axial Refinement Network for Monocular 3D Object Detection
* Accepted by ECCV 2020 
  Access Paper or Ask Questions

Label Decoupling Framework for Salient Object Detection


Aug 25, 2020
Jun Wei, Shuhui Wang, Zhe Wu, Chi Su, Qingming Huang, Qi Tian

Figure 1 for Label Decoupling Framework for Salient Object Detection
Figure 2 for Label Decoupling Framework for Salient Object Detection
Figure 3 for Label Decoupling Framework for Salient Object Detection
Figure 4 for Label Decoupling Framework for Salient Object Detection
* Accepted by CVPR2020, https://github.com/weijun88/LDF 
  Access Paper or Ask Questions

Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap


Aug 05, 2020
Lingxi Xie, Xin Chen, Kaifeng Bi, Longhui Wei, Yuhui Xu, Zhengsu Chen, Lanfei Wang, An Xiao, Jianlong Chang, Xiaopeng Zhang, Qi Tian

Figure 1 for Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap
Figure 2 for Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap
Figure 3 for Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap
Figure 4 for Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap
* 24 pages, 3 figures, 2 tables, meta data updated 
  Access Paper or Ask Questions

Video Super-Resolution with Recurrent Structure-Detail Network


Aug 02, 2020
Takashi Isobe, Xu Jia, Shuhang Gu, Songjiang Li, Shengjin Wang, Qi Tian

Figure 1 for Video Super-Resolution with Recurrent Structure-Detail Network
Figure 2 for Video Super-Resolution with Recurrent Structure-Detail Network
Figure 3 for Video Super-Resolution with Recurrent Structure-Detail Network
Figure 4 for Video Super-Resolution with Recurrent Structure-Detail Network
* ECCV 2020 
  Access Paper or Ask Questions

Corner Proposal Network for Anchor-free, Two-stage Object Detection


Jul 27, 2020
Kaiwen Duan, Lingxi Xie, Honggang Qi, Song Bai, Qingming Huang, Qi Tian

Figure 1 for Corner Proposal Network for Anchor-free, Two-stage Object Detection
Figure 2 for Corner Proposal Network for Anchor-free, Two-stage Object Detection
Figure 3 for Corner Proposal Network for Anchor-free, Two-stage Object Detection
Figure 4 for Corner Proposal Network for Anchor-free, Two-stage Object Detection
* 18 pages (including 3 pages of References), 3 figures, 7 tables, accepted by ECCV 2020 
  Access Paper or Ask Questions

Learning Task-oriented Disentangled Representations for Unsupervised Domain Adaptation


Jul 27, 2020
Pingyang Dai, Peixian Chen, Qiong Wu, Xiaopeng Hong, Qixiang Ye, Qi Tian, Rongrong Ji

Figure 1 for Learning Task-oriented Disentangled Representations for Unsupervised Domain Adaptation
Figure 2 for Learning Task-oriented Disentangled Representations for Unsupervised Domain Adaptation
Figure 3 for Learning Task-oriented Disentangled Representations for Unsupervised Domain Adaptation
Figure 4 for Learning Task-oriented Disentangled Representations for Unsupervised Domain Adaptation
* 9 pages, 6 figures 
  Access Paper or Ask Questions

Dual Distribution Alignment Network for Generalizable Person Re-Identification


Jul 27, 2020
Peixian Chen, Pingyang Dai, Jianzhuang Liu, Feng Zheng, Qi Tian, Rongrong Ji

Figure 1 for Dual Distribution Alignment Network for Generalizable Person Re-Identification
Figure 2 for Dual Distribution Alignment Network for Generalizable Person Re-Identification
Figure 3 for Dual Distribution Alignment Network for Generalizable Person Re-Identification
Figure 4 for Dual Distribution Alignment Network for Generalizable Person Re-Identification
* 8 pages, 3 figures 
  Access Paper or Ask Questions