Guanhong Wang is a PhD Candidate at Zhejiang University, with CVNext Lab advised by Prof. Gaoang Wang. His research interests include video understanding, multi-modality learning and vision and language.

Selected Publications:

  • Temporal-Aware Dynamic Memory Modulation for Audio-Visual Segmentation
    Guanhong Wang, Pengyu Li, Jenq-Neng Hwang, Xi Li, Gaoang Wang✉
    IEEE Transactions on Multimedia (TMM)
    [Paper]
    A temporal-aware dynamic memory modulation approach for audio-visual segmentation, enabling adaptive fusion of temporal and cross-modal information.

  • MovieChat: From Dense Token to Sparse Memory in Long Video Understanding
    Enxin Song*, Wenhao Chai*♡, Guanhong Wang*,Yucheng Zhang, Haoyang Zhou, Feiyang Wu, Tian Ye, Jenq-Neng Hwang, Gaoang Wang✉
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024
    [Website] [Paper] [Dataset] [Code] NPM
    MovieChat achieves state-of-the-art performace in long video understanding by introducing memory mechanism.

  • Human-centered Prior-guided and Task-dependent Multi-task Representation Learning for Action Recognition Pre-training
    Guanhong Wang, Keyu Lu, Yang Zhou, Zhanhao He, Gaoang Wang✉
    IEEE International Conference on Multimedia and Expo (ICME), 2022
    We distill knowledge from a human parsing model to enrich the semantic capability of representation.

Updates:

  • Jul. 2026: One papers are accepted by ACM MM 2026.
  • Mar. 2026: One papers are accepted by TMM.
  • Mar. 2025: One papers are accepted by TVCG.
  • Feb. 2024: Our two papers are accepted by CVPR 2024.

  • Dec. 2023: Our paper Knowledge-guided Pre-training and Fine-tuning: Video Representation Learning for Action Recognition accepted by Neurocomputing.

  • Aug. 2023: Our paper User-Aware Prefix-Tuning is a Good Learner for Personalized Image Captioning accepted by PRCV 2023.

  • July 2023: Our project MovieChat: From Dense Token to Sparse Memory in Long Video Understanding is released at website.

  • July 2023: Attend CVPR 2023 virtually.

  • June 2023: Attend VALSE 2023 in Wuxi.

  • Sep 2022: Our paper Missing Modality meets Meta Sampling (M3S): An Efficient Universal Approach for Multimodal Sentiment Analysis with Missing Modality accepted by AACL-IJCNLP 2022.

  • July 2022: Attend ICME 2022 virtually, and give a Special Session Report.

  • June 2022: Attend CVPR 2022 virtually.

  • March 2022: Our paper Human-centered Prior-guided and Task-dependent Multi-task Representation Learning for Action Recognition Pre-training accepted by ICME 2022.

  • Oct 2021: Attend VALSE 2021 in Hangzhou.

  • June 2021: Start my Phd research on Video Action Recognition task, advised by Professor Gaoang Wang.