Chen Liang (梁琛)

I'm a third-year PhD student at ZJU, advised by Prof.Wenguan Wang and Prof.Yi Yang. I got my B.S. from SSE, Tongji Univ. in 2020.

Email  /  Google Scholar  /  Github

profile photo
Research

I'm interested in Machine Vision and Embodied AI. Feel free to contact me if there is any question on my research.

Logic-induced Diagnostic Reasoning for Semi-supervised Semantic Segmentation
Chen Liang, Wenguan Wang, Jiaxu Miao, Yi Yang
ICCV, 2023
arXiv / video / code

LogicDiag identifies conflicts in pseudo labels using symbolic knowledge and resolves them through logic-induced diagnoses. This approach improves performance by correcting erroneous labels and reducing error accumulation.

Local-Global Context Aware Transformer for Language-Guided Video Segmentation
Chen Liang, Wenguan Wang, Tianfei Zhou, Jiaxu Miao, Yawei Luo, Yi Yang
TPAMI, 2023
arXiv / dataset / code

A new model that incorporates finite memory to align both the short-term and long-term video context with the language expression in an efficient manner.

GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Models
Chen Liang, Wenguan Wang, Jiaxu Miao, Yi Yang
NeurIPS, 2022   (Spotlight)
arXiv / OpenReview / video (1min) / video (5min) / code

We propose GMMSeg, a new family of segmentation models that rely on a dense generative classifier. GMMSeg is the first semantic segmentation method that reports promising results on both closed-set and open-world scenarios by using a single model instance.

Visual Abductive Reasoning
Chen Liang, Wenguan Wang, Tianfei Zhou, Yi Yang
CVPR, 2022
arXiv / dataset / video / code

A pilot work towards reasoning-beyond-observation in visual machine intelligence.

Rethinking Cross-modal Interaction from a Top-down Perspective for Referring Video Object Segmentation
Chen Liang, Yu Wu, Tianfei Zhou, Wenguan Wang, Zongxin Yang, Yunchao Wei, Yi Yang
CVPR workshop, 2021   (Short Technical Report)
arXiv / video

Champion solution in The 3rd Large-scale Video Object Segmentation Challenge: Referring Video Object Segmentation Track.

VSPW: A Large-scale Dataset for Video Scene Parsing in the Wild
Jiaxu Miao, Yunchao Wei, Yu Wu, Chen Liang, Guangrui Li, Yi Yang
CVPR, 2021
pdf / dataset / video / code

A new large-scale dataset for practical video scene parsing.


Code stolen from Jon Barron 0v0.