Publications

Publications by categories in reversed chronological order.

2022

  1. arxiv
    Towards Fast Adaptation of Pretrained Contrastive Models for Multi-channel Video-Language Retrieval
    Xudong Lin, Simran Tiwari, Shiyuan Huang, Manling Li, Mike Zheng Shou, Heng Ji, and Shih-Fu Chang
    arXiv preprint arXiv:2206.02082 2022
    Paper
  2. arxiv
    Multimodal Few-Shot Object Detection with Meta-Learning Based Cross-Modal Prompting
    Guangxing Han, Jiawei Ma, Shiyuan Huang, Long Chen, Rama Chellappa, and Shih-Fu Chang
    arXiv preprint arXiv:2204.07841 2022
    Paper
  3. CVPR
    Task-Adaptive Negative Envision for Few-Shot Open-Set Recognition
    Shiyuan Huang*, Jiawei Ma*, Guangxing Han, and Shih-Fu Chang
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022
    Paper
  4. CVPR
    Few-Shot Object Detection With Fully Cross-Transformer
    Guangxing Han, Jiawei Ma, Shiyuan Huang, Long Chen, and Shih-Fu Chang
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022
    Paper

2021

  1. AAAI
    Meta faster r-cnn: Towards accurate few-shot object detection with attentive feature alignment
    Guangxing Han, Shiyuan Huang, Jiawei Ma, Yicheng He, and Shih-Fu Chang
    Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI) 2021
    Paper
  2. ICCV
    Query adaptive few-shot object detection with heterogeneous graph convolutional networks
    Guangxing Han, Yicheng He, Shiyuan Huang, Jiawei Ma, and Shih-Fu Chang
    In Proceedings of the IEEE/CVF International Conference on Computer Vision 2021
    Paper

2020

    2019

    1. arxiv
      Flow-distilled IP two-stream networks for compressed video action recognition
      Shiyuan Huang, Xudong Lin, Svebor Karaman, and Shih-Fu Chang
      arXiv preprint arXiv:1912.04462 2019
      Paper

    2018

    1. ICIP
      Pyramid structured optical flow learning with motion cues
      Ji Dai, Shiyuan Huang, and Truong Nguyen
      In 2018 25th IEEE international conference on image processing (ICIP) 2018
      Paper