Publications

2026

  1. cvpr25_grouprevision_page_1.png
    CVPR’26
    From Failure to Feedback: Group Revision Unlocks Hard Cases in Object-Level Grounding
    Yuyuan Liu , Yiping Ji, Anjie Le, Jiayuan Zhu, Jiazhen Pan, Can Peng, Jiajun Deng, Fengbei Liu, and Junde Wu
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2026
    arXiv Code
  2. cvprf25_auralsam2_page_1.png
    CVPRF’26
    AuralSAM2: Enabling SAM2 Hear Through Pyramid Audio-Visual Feature Prompting
    Yuyuan Liu , Yuanhong Chen, Chong Wang, Junlin Han, Junde Wu, Can Peng, Jingkun Chen, Yu Tian, and Gustavo Carneiro
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Findings Track, 2026
    (# denotes corresponding author)
    arXiv Code

2025

  1. arxiv26_ct_appearance_page_1.png
    Arxiv’26
    Segmentation, Detection and Explanation: A Unified Framework for CT Appearance Reasoning
    Yuyuan Liu* , Can Peng*, Yingyu Yang, Qianye Yang, Cheng Ouyang, and J. Alison Noble
    Submit to IEEE Transactions on Medical Imaging, April 2026
    (* denotes equal contribution)
    arXiv
  2. TMI25_tracoco_page_1.png
    TMI’25
    Translation consistent semi-supervised segmentation for 3D medical images
    Yuyuan Liu , Yu Tian, Chong Wang, Yuanhong Chen, Fengbei Liu, Vasileios Belagiannis, and Gustavo Carneiro
    IEEE Transactions on Medical Imaging, 2025
    (* represents the equal contribution)
    arXiv Code

2024

  1. cvpr24_unraveling_page_1.png
    CVPR’24
    Unraveling Instance Associations: A Closer Look for Audio-Visual Segmentation
    Yuanhong Chen*,  Yuyuan Liu* , Hu Wang, Fengbei Liu, Chong Wang, Helen Frazer, and Gustavo Carneiro
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
    (* denotes equal contribution)
    arXiv Code
  2. eccv24_it2_page_1.png
    ECCV’24
    ItTakesTwo: Leveraging Peer Representations for Semi-supervised LiDAR Semantic Segmentation
    Yuyuan Liu , Yuanhong Chen, Hu Wang, Vasileios Belagiannis, Ian Reid, and Gustavo Carneiro
    In European Conference on Computer Vision, 2024
    (* represents the equal contribution)
    arXiv Code Poster

2023

  1. iccv23_rpl_page_1.jpg
    ICCV’23
    Residual pattern learning for pixel-wise out-of-distribution detection in semantic segmentation
    Yuyuan Liu , Choubo Ding, Yu Tian, Guansong Pang, Vasileios Belagiannis, Ian Reid, and Gustavo Carneiro
    In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023
    (* represents the equal contribution)
    arXiv Code Poster
  2. ICCV’23
    Learning support and trivial prototypes for interpretable image classification
    Chong Wang,  Yuyuan Liu , Yuanhong Chen, Fengbei Liu, Yu Tian, Davis McCarthy, Helen Frazer, and Gustavo Carneiro
    In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023
    arXiv Code
  3. ICCV’23
    Bomd: bag of multi-label descriptors for noisy chest x-ray classification
    Yuanhong Chen, Fengbei Liu, Hu Wang, Chong Wang,  Yuyuan Liu , Yu Tian, and Gustavo Carneiro
    In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023
    arXiv Code
  4. MICCAI’23
    Unsupervised anomaly detection in medical images with a memory-augmented multi-level cross-attentional masked autoencoder
    Yu Tian, Guansong Pang,  Yuyuan Liu , Chong Wang, Yuanhong Chen, Fengbei Liu, Rajvinder Singh, Johan W Verjans, Mengyu Wang, and Gustavo Carneiro
    In International Workshop on Machine Learning in Medical Imaging, 2023
    HTML

2022

  1. eccv22_pebal_page_1.jpg
    ECCV’22
    Pixel-wise energy-biased abstention learning for anomaly segmentation on complex urban driving scenes
    Yu Tian*,  Yuyuan Liu* , Guansong Pang, Fengbei Liu, Yuanhong Chen, and Gustavo Carneiro
    In European Conference on Computer Vision (oral), 2022
    (* represents the equal contribution)
    arXiv Code
  2. MICCAI’22
    Knowledge distillation to ensemble global and interpretable prototype-based mammogram classification models
    Chong Wang, Yuanhong Chen,  Yuyuan Liu , Yu Tian, Fengbei Liu, Davis J McCarthy, Michael Elliott, Helen Frazer, and Gustavo Carneiro
    In International Conference on Medical Image Computing and Computer-Assisted Intervention, 2022
    HTML
  3. MICCAI’22
    Contrastive transformer-based multiple instance learning for weakly supervised polyp frame detection
    Yu Tian, Guansong Pang, Fengbei Liu,  Yuyuan Liu , Chong Wang, Yuanhong Chen, Johan Verjans, and Gustavo Carneiro
    In International Conference on Medical Image Computing and Computer-Assisted Intervention, 2022
    HTML Code
  4. MICCAI’22
    Multi-view local co-occurrence and global consistency learning improve mammogram classification generalisation
    Yuanhong Chen, Hu Wang, Chong Wang, Yu Tian, Fengbei Liu,  Yuyuan Liu , Michael Elliott, Davis J McCarthy, Helen Frazer, and Gustavo Carneiro
    In International Conference on Medical Image Computing and Computer-Assisted Intervention, 2022
    HTML
  5. cvpr22_psmt_page_1.png
    CVPR’22
    Perturbed and strict mean teachers for semi-supervised semantic segmentation
    Yuyuan Liu , Yu Tian, Yuanhong Chen, Fengbei Liu, Vasileios Belagiannis, and Gustavo Carneiro
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022
    arXiv Code Poster
  6. CVPR’22
    ACPL: Anti-curriculum pseudo-labelling for semi-supervised medical image classification
    Fengbei Liu, Yu Tian, Yuanhong Chen,  Yuyuan Liu , Vasileios Belagiannis, and Gustavo Carneiro
    In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2022
    arXiv Code