I am a Professor at the Beijing Institute of Technology (BIT), China.
Prior to that, I was a researcher in the BMIC Group
at ETH Zurich (Swiss),
closely working with Prof. Ender
Konukoglu, and Inception Institute of Artificial Intelligence (UAE).
My primary research interests are in the fields of Computer Vision, Machine Learning, and Artificial
Intelligence,
with broader interests in Robotics and Digital Humanities. Currently, my work focuses on creating
intelligent models
capable of percepting, reasoning, and making decisions in real visual world, to address real-world
applications across
domains such as healthcare, industry, and scientific discovery.
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.
Prospective Students:
I am always looking for highly-motivated students to join my group.
If you are interested to work with me (for intern, master, PhD, Postdoc),
please shoot me an email (tfzhou [at] bit.edu.cn)
News
- 2025/08: DAPT is accepted to IEEE Trans. PAMI!
Preprints
Image Segmentation in Foundation Model Era: A Survey
VideoRFT: Incentivizing Video Reasoning Capability in MLLMs via Reinforced Fine-Tuning
Publications
Decouple before Align: Visual Disentanglement Enhances Prompt Tuning
LAVA: Language Driven Scalable and Versatile Traffic Video Analytics
Seeing What Matters: Empowering CLIP with Patch Generation-to-Selection
Prompt Tuning In a Compact Attribute Space
Nonverbal Interaction Detection
On-Road Object Importance Estimation: A New Dataset and A Model with Multi-Fold Top-Down
Guidance
nsDB: Architecting the Next Generation Database by Integrating Neural and Symbolic Systems (Vision)
-
Ye Yuan, Bo Tang, Tianfei Zhou, Zhiwei Zhang, Jianbin Qin
VLDB, 2024 [Paper]
GeneSegNet: a deep learning framework for cell segmentation by integrating gene expression and
imaging
Uncovering Prototypical Knowledge for Weakly Open-Vocabulary Semantic Segmentation
Cascaded Parsing of Human-Object Interaction Recognition
A Survey on Deep Learning Technique for Video Segmentation
Volumetric Memory Network for Interactive Medical Image Segmentation
Rethinking Semantic Segmentation: A Prototype View
Exploring Cross-Image Pixel Contrast for Semantic Segmentation