Mu Chen (้™ˆ็‰ง)

I'm a Ph.D. student at University of Technology Sydney (UTS), affiliated with ReLER Lab, Australian Artificial Intelligence Institute (AAII,), advised by Prof. Yi Yang. I got my B.S. from Monash University in 2021. I am fortunate to be sequentially mentored by Prof. Zhedong Zheng, and Prof. Wenguan Wang during my PhD journey.

Email  /  Google Scholar  /  Github

profile photo

News

  • ๐Ÿ”ฅ2024.7: Our work DCF is accepted by ACM MM'24 as Oral!
  • ๐Ÿ”ฅ2024.7: Our work GvSeg is accepted by ECCV'24!
  • 2024.7: Our work UAHOI is accepted by CVIU'24!
  • 2023.7: Our work PiPa is accepted by ACM MM'23!

I have a broad interest in machine vision, including visual scene understanding, video segmentation and domain adaptation. Feel free to contact me about any questions.

Selected Publications
Transferring to Real-World Layouts: A Depth-aware Framework for Scene Adaptation
Mu Chen, Zhedong Zheng, Yi Yang †
ACM Multimedia, 2024   (Oral Presentation, 3.97% Accept Rate)
arXiv / code /  video (ๆžๅธ‚)

We observe that semantic categories, such as sidewalks, buildings, and sky, display relatively consistent depth distributions, and could be clearly distinguished in a depth map. Based on such observation, we propose a depth-aware framework to explicitly leverage depth estimation to mix the categories and facilitate the two complementary tasks, i.e., segmentation and depth learning in an end-to-end manner.
GvSeg: General and Task-Oriented Video Segmentation
Mu Chen, Liulei Li, Wenguan Wang, Ruijie Quan, Yi Yang †
ECCV, 2024
arXiv / code /  video (AI TIME)

We present GvSeg, a general and task-oriented video segmentation framework for addressing four different video segmentation tasks (i.e., instance, semantic, panoptic, and exemplar-guided) while maintain- ing an identical architectural design.
PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation
Mu Chen, Zhedong Zheng, Yi Yang, Tat-seng Chua †
ACM Multimedia, 2023
arXiv /  video (AI ๆ–ฐ้’ๅนด) / code

We propose a unified pixel- and patch-wise self-supervised learning framework, called PiPa, for domain adaptive semantic segmentation that facilitates intra-image pixel-wise correlations and patch-wise semantic consistency against different contexts.
UAHOI: Uncertainty-aware robust interaction learning for HOI detection
Mu Chen, Minghan Chen, Yi Yang †
Computer Vision and Image Understanding (CVIU), 2024
arXiv

We propose a novel approach UAHOI, Uncertainty-aware Robust Human-Object Interaction Learning that explicitly estimates prediction uncertainty during the training process to refine both detection and interaction predictions.
PiPa++: Towards Unification of Domain Adaptive Semantic Segmentation via Self-supervised Learning
Mu Chen, Zhedong Zheng †, Yi Yang
under IEEE TMM review, 2024
arXiv / code

An extension version of PiPa towards Video domain.
Selected Awards

  • Outstanding Reviewer, ACM Multimedia Main Conference, USA, 2024
  • UTS Post Thesis Award, Australia, 2024 (3,000 AUD)
  • ACM Travel Grants, USA, 2024 (1,000 USD)
  • Outstanding Reviewer, ACM Multimedia UAVM Workshop, USA, 2024
  • Outstanding Reviewer, ACM Multimedia UAVM Workshop, USA, 2023
  • First-Class Honour, Monash University, Australia, 2021
  • Summer Research Scholarship, Monash University, Australia, 2021 (3,200 AUD)
  • Tuition Fee Waiver Scholarship, Monash University, Australia, 2019-2021 (awarded four times, totaling 18,000 AUD)
  • Dean's Honour List, Monash University, Australia, 2019-2021
  • Undergraduate Student Support Grant, Monash University, Australia, 2018 (8,000 AUD)

    • Academic Service

  • Journal Reviewer:
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
    IEEE Transactions on Multimedia (TMM)
    IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
    IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
    Computer Vision and Image Understanding (CVIU)
    Pattern Recognition (PR)
    Neurocomputing
    Information Fusion
    The Visual Computer

  • Conference Reviewer:
    International Conference on Learning Representations (ICLR)
    IEEE Conference on Virtual Reality and 3D User Interfaces (IEEE VR)
    ACM International Conference on Multimedia (ACM MM)
    International Conference on Weblogs and Social Media (ICWSM)
    NeurIPS Workshop on Foundation Models for Science (FM4Science)
    NeurIPS Workshop on Bayesian Decision-making and Uncertainty (BDU)
    ACM Multimedia Workshop on UAVM 2023& 2024


    • Code stolen from Jon Barron 0v0.