Tianfei Zhou (周天飞)


Postdoctoral Scholar
BMIC Group, Computer Vision Laboratory
ETH Zurich, Switzerland


Email: ztfei.debug[at]gmail.com, tianfei.zhou[at]vision.ee.ethz.ch
[Google Scholar] [Github]

Currently, I am a postdoctoral scholar in Computer Vision Laboratory at ETH Zurich, working with Prof. Ender Konukoglu. Before that, I was a researcher at Inception Institute of Artificial Intelligence, Abu Dhabi, UAE. I got my Ph.D. degree from Beijing Laboratory of Intelligent Information Technology, Beijing Institute of Technology in 2017, under the supervision of Prof. Yao Lu.



Recent News

  • 03/2021 – Three papers are accepted in CVPR'21!

  • 01/2021 – One paper is accepted in IEEE TPAMI!

  • 12/2020 – One paper is accepted in IEEE TPAMI!

  • 12/2020 – Two papers are accepted in AAAI'21!

  • 12/2020 – I join CVL@ETH Zurich as a postdoc! Super!



Research Interests

  • Medical Image Analysis: radiotherapy / x-ray / CT diagnosis

  • Vision & Language: referring segmentation / vision-language navigation

  • Image and Video Understanding: semantic segmentation / video segmentation / deepfake detection

  • Human-Centric Visual Analysis: human-object interaction recognition / human semantic parsing / human pose estimation

  • Machine Learning: weakly supervised learning / contrastive learning / graph neural networks



Selected Publications (* equal contribution, # corresponding author)

Preprint

Exploring Cross-Image Pixel Contrast for Semantic Segmentation
Wenguan Wang*, Tianfei Zhou*, Fisher Yu, Jifeng Dai, Ender Konukoglu and Luc Van Gool.
Novel paradigm for fully supervised semantic segmentation by exploring cross-image pixel contrast
arXiv | code | 机器之心 (Chinese Media)

2021

Face Forensics in the Wild
Tianfei Zhou, Wenguan Wang, Zhiyuan Liang and Jianbing Shen.
Computer Vision and Pattern Recognition (CVPR), 2021 [ORAL]
arXiv | code | dataset

Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic Parsing
Tianfei Zhou, Wenguan Wang, Si Liu, Yi Yang and Luc Van Gool.
Computer Vision and Pattern Recognition (CVPR), 2021 [ORAL]
arXiv | code

Target-Aware Object Discovery and Association for Unsupervised Video Multi-Object Segmentation
Tianfei Zhou, Jianwu Li, Xueyi Li and Ling Shao.
Computer Vision and Pattern Recognition (CVPR), 2021
arXiv | code

Hierarchical Human Semantic Parsing with Comprehensive Part-Relation Modeling
Wenguan Wang, Tianfei Zhou, Siyuan Qi, Jianbing Shen and Song-Chun Zhu.
IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2021
paper | code

Cascaded Parsing of Human-Object Interaction Recognition
Tianfei Zhou, Siyuan Qi, Wenguan Wang, Jianbing Shen and Song-Chun Zhu.
IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2021
paper | code

Group-Wise Semantic Mining for Weakly Supervised Semantic Segmentation
Xueyi Li, Tianfei Zhou#, Jianwu Li, Yi Zhou and Zhaoxiang Zhang.
The AAAI Conference on Artificial Intelligence (AAAI), 2021
Novel framework to improve pseudo ground-truth generation in WSSS
arXiv | code

Many-to-One Distribution Learning and K-Nearest Neighbor Smoothing for Thoracic Disease Identification
Yi Zhou, Lei Huang, Tianfei Zhou and Ling Shao.
The AAAI Conference on Artificial Intelligence (AAAI), 2021
arXiv

2020

MATNet: Motion-Attentive Transition Network for Zero-Shot Video Object Segmentation
Tianfei Zhou, Jianwu Li, Shunzhou Wang, Ran Tao and Jianbing Shen.
IEEE Transactions on Image Processing (TIP), 2020
paper | code

Weakly Supervised 3D Object Detection from Lidar Point Cloud
Qinghao Meng, Wenguan Wang, Tianfei Zhou, Jianbing Shen, Luc Van Gool and Dengxin Dai.
European Conference on Computer Vision (ECCV), 2020
arXiv | code

Video Object Segmentation with Episodic Graph Memory Networks
Xiankai Lu, Wenguan Wang, Martin Danelljan, Tianfei Zhou, Jianbing Shen and Luc Van Gool.
European Conference on Computer Vision (ECCV), 2020 [SPOTLIGHT]
arXiv | code

Cascaded Human-Object Interaction Recognition
Tianfei Zhou, Wenguan Wang, Siyuan Qi, Haibin Ling and Jianbing Shen.
Computer Vision and Pattern Recognition (CVPR), 2020
Winner of the Person in Context Challenge at ICCV'19.
arXiv | code

Motion-Attentive Transition for Zero-Shot Video Object Segmentation
Tianfei Zhou, Shunzhou Wang, Yi Zhou, Yazhou Yao, Jianwu Li and Ling Shao.
The AAAI Conference on Artificial Intelligence (AAAI), 2020
Ranked 1st for unsupervised video object segmentation at DAVIS 2016 Leaderboard.
arXiv | code

Web-Supervised Network with Softly Update-Drop Training for Fine-Grained Visual Classification
Chuanyi Zhang, Yazhou Yao, Huafeng Liu, Guo-Sen Xie, Xiangbo Shu, Tianfei Zhou, Zheng Zhang, Fumin Shen and Zhenmin Tang.
The AAAI Conference on Artificial Intelligence (AAAI), 2020
paper | code

before 2020

Locality-Constrained Collaborative Model for Robust Visual Tracking
Tianfei Zhou, Yao Lu, Huijun Di.
IEEE Transactions on Circuits and Systems for Video Technology (T-CSVT), 2017.
paper

Learning to Generate Video Object Segment Proposals
Jianwu Li, Tianfei Zhou, Yao Lu.
International Conference on Multimedia & Expo (ICME), 2017. [ORAL]
paper

Video Object Segmentation Aggregation
Tianfei Zhou, Yao Lu, Huijun Di and Jian Zhang.
International Conference on Multimedia & Expo (ICME), 2016. [ORAL]
paper

Abrupt Motion Tracking via Nearest Neighbor Field Driven Stochastic Sampling
Tianfei Zhou, Yao Lu, Feng Lv, Huijun Di, Qingjie Zhao and Jian Zhang.
Neurocomputing, 2015
paper

Nearest Neighbor Field Driven Stochastic Sampling for Abrupt Motion Tracking
Tianfei Zhou, Yao Lu, Huijun Di.
International Conference on Multimedia & Expo (ICME), 2014.
paper



Awards



Talks

  • 2021-04-29 - 智东西公开课 "Structured Human Semantic Parsing" [video]



Professional activities

  • Reviewer for ICCV'21, CVPR'21, ECCV'20, AAAI'20-21, MICCAI'21, ICME'20-21

  • Regular Reviewer for TPAMI, TIP, TNNLS, TMM, TCSVT, TGRS

  • Regular Reviewer for CVIU, PR, Neurocomputing



Links