PUBLICATION

publications by categories in reversed chronological order.

2026

  1. Emotionhallucer: Evaluating Emotion Hallucinations in Multimodal Large Language Models
    Bohao Xing, Xin Liu, Guoying Zhao, and 3 more authors
    In Proceedings of The Fourteenth International Conference on Learning Representations (ICLR), 2026
  2. MSF-Mamba: Motion-aware State Fusion Mamba for Efficient Micro-Gesture Recognition
    Deng Li, Jun Shao, Bohao Xing, and 4 more authors
    IEEE Transactions on Multimedia, 2026
  3. Identity-Free Artificial Emotional Intelligence via Micro-Gesture Understanding
    Rong Gao, Xin Liu, Bohao Xing, and 3 more authors
    IEEE Transactions on Affective Computing, 2026
    DOI
  4. Multi-granularity Facial Emotional Representation with Unlabeled Data and Textual Supervision
    Kaishen Yuan, Zitong Yu, Xin Liu, and 5 more authors
    IEEE Transactions on Image Processing, 2026

2025

  1. DEEMO: De-identity Multimodal Emotion Recognition and Reasoning
    Deng Li*, Bohao Xing*, Xin Liu, and 3 more authors
    In Proceedings of the 33rd ACM International Conference on Multimedia (ACM MM), 2025
    DOI
  2. AU-TTT: Vision Test-Time Training model for Facial Action Unit Detection
    Bohao Xing, Kaishen Yuan, Zitong Yu, and 2 more authors
    In 2025 IEEE International Conference on Multimedia and Expo (ICME), 2025
    DOI
  3. FSBench: A Figure Skating Benchmark for Advancing Artistic Sports Understanding
    Rong Gao, Xin Liu, Zhuozhao Hu, and 4 more authors
    In 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
    DOI

2024

  1. Emo-llama: Enhancing facial emotion understanding with instruction tuning
    Bohao Xing, Zitong Yu, Xin Liu, and 6 more authors
    arXiv preprint arXiv:2408.11424, 2024
  2. Enhancing Micro Gesture Recognition for Emotion Understanding via Context-Aware Visual-Text Contrastive Learning
    Deng Li*, Bohao Xing*, and Xin Liu
    IEEE Signal Processing Letters, 2024
    DOI
  3. Eald-mllm: Emotion analysis in long-sequential and de-identity videos with multi-modal large language model
    Deng Li, Xin Liu, Bohao Xing, and 4 more authors
    arXiv preprint arXiv:2405.00574, 2024
  4. scFusionTTT: Single-cell transcriptomics and proteomics fusion with Test-Time Training layers
    Dian Meng*, Bohao Xing*, Xinlei Huang, and 5 more authors
    arXiv preprint arXiv:2410.13257, 2024