Tianfei Zhou


I am Tianfei Zhou (周天飞 in Chinese), a postdoctoral scholar in Computer Vision Laboratory at ETH Zurich, working with Prof. Ender Konukoglu in the BMIC Group.

My research interests have revolved around human-centered visual computing, with the aim to build a machine that (1) technically reflect the depth characterized by human vision, (2) operate transparently, act equitably, respect the privacy, and (3) eventually amplify and augment human capabilities in diverse social challenges, e.g., healthcare.

I have received 1 Best Paper and 1 Outstanding Paper Nomination Awards. The research results in leading algorithms that won several international academic challenges held in conjunction with CVPR, ICCV, and industry challenges held by Alibaba.

Me elsewhere: Google Scholar   Email   GitHub   Twitter  

New! Call for paper: Label-Efficient Learning on Video Data, Special Issue in IEEE Transactions on Circuits and Systems for Video Technology (T-CSVT), 2022 (submission deadline: Apr. 1, 2023)

a portrait of tianfei zhou

Selected Publications

A Survey on Deep Learning Technique for Video Segmentation

Tianfei Zhou, Fatih Porikli, David Crandall, Luc Van Gool, Wenguan Wang
IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI), 2022, in press
[Paper] [Code]


Cascaded Parsing of Human-Object Interaction Recognition

Tianfei Zhou, Siyuan Qi, Wenguan Wang, Jianbing Shen, and Song-Chun Zhu
IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI), 2021
[Paper] [Code]

WAIC Youth Outstanding Paper Nomination Award, 2021.
Champions on two tracks ([HOI] [PIC]) in ICCV 2019 Person-in-Context challenge.

Volumetric Memory Network for Interactive Medical Image Segmentation

Tianfei Zhou, Liulei Li, Gustav Bredell, Jianwu Li, Jan Unkelbach and Ender Konukoglu
Medical Image Analysis (MedIA), 2022
[Paper] [Code]

MedIA-MICCAI Best Paper Award, 2022.

Rethinking Semantic Segmentation: A Prototype View

Tianfei Zhou, Wenguan Wang, Ender Konukoglu, and Luc Van Gool
CVPR 2022, Oral Presentation
[Paper] [Code]


Exploring Cross-Image Pixel Contrast for Semantic Segmentation

Wenguan Wang*, Tianfei Zhou*, Fisher Yu, Jifeng Dai, Ender Konukoglu, and Luc Van Gool (*equal contribution)
ICCV 2021, Oral Presentation
[Paper] [Code]


Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic Parsing

Tianfei Zhou, Wenguan Wang, Si Liu, Yi Yang, and Luc Van Gool
CVPR 2021, Oral Presentation
[Paper] [Code]


Motion-Attentive Transition for Zero-Shot Video Object Segmentation

Tianfei Zhou, Shunzhou Wang, Yi Zhou, Yazhou Yao, Jianwu Li, and Shao Ling
AAAI 2020
[Paper] [Code]


Address

Computer Vision Laboratory
Biomedical Image Computing
Sternwartstrasse 7
ETF E 112
8092 Zürich
Switzerland

Latest News

  • [21/01/2023, 除夕] Two papers accepted to ICLR 2023, including one spotlight (notable-top-25%)
  • [11/2022] A survey paper on Deep Video Segmentation accepted to IEEE TPAMI.
  • [09/2022] Won Medical Image Analysis-MICCAI Best Paper Award.

Awards

  • Medical Image Analysis-MICCAI Best Paper Award, 2022 [MedIA] [MICCAI]
  • WAIC Youth Outstanding Paper Nomination Award, 2021
  • 1st Place in CVPR2021 AutoNUE 2021 Challenge: Semantic Segmentation Track [Link]
  • 1st Place in CVPR2021 L2ID Challenge: High-resolution Human Parsing Track [Link]
  • 1st Place in CVPR2021 Large-scale Video Object Segmentation Challenge: Referring Video Object Segmentation Track [Link]
  • 1st Place in ICCV2019 Person in Context (PIC): Relation Segmentation Track [Link] and Human-Object-Interaction Detection Track [Link]

Talks

  • Human-Centric Scene Parsing
    at Hohai University, 12/2022. (Invited by Prof. Xiaofeng Liu)
  • Deep Learning based Semantic Segmentation
    at BMIC Group, ETH Zurich, 06/2022.
    at Align Technology, 10/2022. (Invited by Alexander Okupnik)
  • Structured Human Semantic Parsing at TechBeat and 智东西公开课, 2021.

Service

Senior Program Committee: AAAI'22
Guest Editor: IEEE TCSVT, Electronics
Conference Review: ICLR'22-23, NeurIPS'21-'23, ICML'22-23, CVPR, ICCV, ECCV, MICCAI, MIDL
Journal Review: IEEE TPAMI, IEEE TIP, MedIA, IEEE TMI, IJCV