Publications

2024

  1. arXiv
    Open-Vocabulary SAM: Segment and Recognize Twenty-thousand Classes Interactively
    Haobo YuanXiangtai LiChong Zhou, Yining Li, Kai Chen, and Chen Change Loy
    arXiv preprint, 2024.
  2. arXiv
    RAP-SAM:Towards Real-Time All-Purpose Segment Anything
    Shilin XuHaobo Yuan, Qingyu Shi, Lu Qi, Jingbo Wang, Yibo Yang, Yining Li, Kai Chen, Yunhai Tong, Bernard Ghanem, Xiangtai Li, and Ming-Hsuan Yang
    arXiv preprint, 2024.
  3. OMG-Seg: Is One Model Good Enough For All Segmentation?
    Xiangtai LiHaobo Yuan, Wei Li, Henghui Ding, Size Wu, Wenwei Zhang, Yining Li, Kai Chen, and Chen Change Loy
    In CVPR, 2024. Seattle, WA, USA.
  4. Towards Open Vocabulary Learning: A Survey
    Jianzong Wu, Xiangtai LiShilin XuHaobo Yuan, Henghui Ding, Yibo Yang, Xia Li, Jiangning Zhang, Yunhai Tong, Xudong Jiang, Bernard Ghanem, and Dacheng Tao
    IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024.
  5. arXiv
    Point Could Mamba: Point Cloud Learning via State Space Model
    Tao Zhang, Xiangtai LiHaobo Yuan, Shunping Ji, and Shuicheng Yan
    arXiv pre-print, 2024.

2023

  1. Tube-Link: A Flexible Cross Tube Baseline for Universal Video Segmentation
    Xiangtai LiHaobo YuanWenwei Zhang, Guangliang Cheng, Jiangmiao Pang, and Chen Change Loy
    In ICCV, 2023. Paris, France.
  2. Monocular Road Planar Parallax Estimation
    Haobo Yuan, Teng Chen, Wei Sui, Jiafeng Xie, Lefei Zhang, Yuan Li, and Qian Zhang
    IEEE Transactions on Image Processing, 2023.
  3. Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class-Incremental Learning
    Yibo YangHaobo YuanXiangtai Li, Zhouchen Lin, Philip Torr, and Dacheng Tao
    In ICLR, 2023. Kigali, Rwanda. Spotlight.
  4. Multi-Task Learning with Multi-query Transformer for Dense Prediction
    Yangyang Xu, Xiangtai LiHaobo YuanYibo Yang, and Lefei Zhang
    IEEE Transactions on Circuits and Systems for Video Technology, 2023.
  5. arXiv
    Neural Collapse Terminus: A Unified Solution for Class Incremental Learning and Its Variants
    Yibo YangHaobo YuanXiangtai Li, Jianlong Wu, Lefei Zhang, Zhouchen Lin, Philip TorrDacheng Tao, and Bernard Ghanem
    arXiv pre-print, 2023.
  6. arXiv
    Transformer-based Visual Segmentation: A Survey
    Xiangtai Li, Henghui Ding, Wenwei ZhangHaobo Yuan, Jiangmiao Pang, Guangliang Cheng, Kai Chen, Ziwei Liu, and Chen Change Loy
    arXiv pre-print, 2023.
  7. arXiv
    PanopticPartFormer++: A Unified and Decoupled View for Panoptic Part Segmentation
    Xiangtai LiShilin XuYibo YangHaobo Yuan, Guangliang Cheng, Yunhai Tong, Zhouchen Lin, Ming-Hsuan Yang, and Dacheng Tao
    arXiv pre-print, 2023.

2022

  1. PolyphonicFormer: Unified Query Learning for Depth-aware Video Panoptic Segmentation
    Haobo YuanXiangtai LiYibo Yang, Guangliang Cheng, Jing Zhang, Yunhai Tong, Lefei Zhang, and Dacheng Tao
    In ECCV, 2022. Tel Aviv, Israel.
    Winner method of the ICCV-2021 SemKITTI-DVPS Challenge.
  2. Towards Theoretically Inspired Neural Initialization Optimization
    Yibo Yang, Hong Wang, Haobo Yuan, and Zhouchen Lin
    In NeurIPS, 2022. New Orleans, LA, USA.

2021

  1. BOSSA: a decentralized system for proofs of data retrievability and replication
    Dian Chen, Haobo Yuan, Shengshan Hu, Qian Wang, and Cong Wang
    IEEE Transactions on Parallel and Distributed Systems, 2021.