UP Lab

members/xiatian.jpeg

Universal Perception (UP) Lab is led by Xiatian Zhu, a Senior Lecturer with Surrey Institute for People-Centred Artificial Intelligence, and Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, UK. He was a research scientist at Samsung AI Centre, Cambridge, UK. He received his Ph.D. from the Queen Mary University of London.

The mission of UP Lab is to advance the capabilities of AI through modeling a variety of perception data (e.g. images, videos, audio, text, 3D points). We are working around the understanding of both machine learning theories and real-world domain applications, with the aim to develop transformitive technologies for the good of our society.

News

Nov 19, 2022 1 AAAI paper accepted
Oct 3, 2022 Welcome Al-Hussein Abutaleb on board
Sep 27, 2022 Welcome Swapnil Bhosale on board
Sep 14, 2022 3 NeurIPS papers accepted
Aug 10, 2022 1 survey paper accepted to IEEE TPAMI

Selected publications

  1. AAAI
    PolarFormer: Multi-camera 3D Object Detection with Polar Transformers
    Jiang, Yanqin, Zhang, Li, Miao, Zhenwei,  Zhu, Xiatian, Gao, Jin, Hu, Weiming, and Jiang, Yu-Gang
    In AAAI Conference on Artificial Intelligence 2023
  2. NeurIPS
    MetaTeacher: Coordinating Multi-Model Domain Adaptation for Medical Image Classification
    Wang, Zhenbin, Ye, Mao,  Zhu, Xiatian, Peng, Liuhan, Tian, Liang, and Zhu, Yingying
    In Annual Conference on Neural Information Processing Systems 2022
  3. NeurIPS
    ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning
    Pan, Junting, Lin, Ziyi,  Zhu, Xiatian, Shao, Jing, and Li, Hongsheng
    In Annual Conference on Neural Information Processing Systems 2022
  4. NeurIPS
    DeepInteraction: 3D Object Detection via Modality Interaction
    Yang, Zeyu, Chen, Jiaqi, Miao, Zhenwei, Li, Wei,  Zhu, Xiatian, and Zhang, Li
    In Annual Conference on Neural Information Processing Systems 2022
  5. Preprint
    Self-supervised Video Representation Learning with Motion-Aware Masked Autoencoders
    Yang, Haosen, Huang, Deng, Wen, Bin, Wu, Jiannan, Yao, Hongxun, Jiang, Yi,  Zhu, Xiatian, and Yuan, Zehuan
    arXiv 2022
  6. Preprint
    Post-Processing Temporal Action Detection
    Nag, Sauradip,  Zhu, Xiatian, Song, Yi-Zhe, and Xiang, Tao
    arXiv 2022
  7. Preprint
    Multi-Modal Few-Shot Temporal Action Detection via Vision-Language Meta-Adaptation
    Nag, Sauradip, Xu, Mengmeng,  Zhu, Xiatian, Perez-Rua, Juan-Manuel, Ghanem, Bernard, Song, Yi-Zhe, and Xiang, Tao
    arXiv 2022
  8. Preprint
    Accelerating Score-based Generative Models for High-Resolution Image Synthesis
    Ma, Hengyuan, Zhang, Li,  Zhu, Xiatian, Zhang, Jingfeng, and Feng, Jianfeng
    In arXiv 2022
  9. TPAMI
    Semi-Supervised and Unsupervised Deep Visual Learning: A Survey
    Chen, Yanbei, Mancini, Massimiliano,  Zhu, Xiatian, and Akata, Zeynep
    IEEE Transactions on Pattern Analysis and Machine Intelligence 2022
  10. ECCV
    EdgeViTs: Competing Light-weight CNNs on Mobile Devices with Vision Transformers
    Pan, Junting, Bulat, Adrian, Tan, Fuwen,  Zhu, Xiatian, Dudziak, Lukasz, Li, Hongsheng, Tzimiropoulos, Georgios, and Martinez, Brais
    In European Conference on Computer Vision 2022
  11. ECCV
    Learning Ego 3D Representation as Ray Tracing
    Lu, Jiachen, Zhou, Zheyuan,  Zhu, Xiatian, Xu, Hang, and Zhang, Li
    In European Conference on Computer Vision 2022
  12. ECCV
    Accelerating Score-based Generative Models with Preconditioned Diffusion Sampling
    Ma, Hengyuan, Zhang, Li,  Zhu, Xiatian, and Feng, Jianfeng
    In European Conference on Computer Vision 2022
  13. ECCV
    Temporal Action Detection with Global Segmentation Mask Learning
    Nag, Sauradip,  Zhu, Xiatian, Song, Yi-Zhe, and Xiang, Tao
    In European Conference on Computer Vision 2022
  14. ECCV
    Semi-Supervised Temporal Action Detection with Proposal-Free Masking
    Nag, Sauradip,  Zhu, Xiatian, Song, Yi-Zhe, and Xiang, Tao
    In European Conference on Computer Vision 2022
  15. ECCV
    Zero-Shot Temporal Action Detection via Vision-Language Prompting
    Nag, Sauradip,  Zhu, Xiatian, Song, Yi-Zhe, and Xiang, Tao
    In European Conference on Computer Vision 2022
  16. ECCV
    FashionViL: Fashion-Focused Vision-and-Language Representation Learning
    Han, Xiao, Yu, Licheng,  Zhu, Xiatian, Zhang, Li, Song, Yi-Zhe, and Xiang, Tao
    In European Conference on Computer Vision 2022
  17. ECCV
    SOS! Self-supervised Learning Over Sets Of Handled Objects In Egocentric Action Recognition
    Escorcia, Victor, Guerrero, Ricardo,  Zhu, Xiatian, and Martinez, Brais
    In European Conference on Computer Vision 2022
  18. ACM MM
    Class Discriminative Adversarial Learning for Unsupervised Domain Adaptation
    Zhou, Lihua, Ye, Mao,  Zhu, Xiatian, Li, Shuaifeng, and Liu, Yiguang
    In ACM Multimedia 2022
  19. Preprint
    Multimodal Learning with Transformers: A Survey
    Xu, Peng,  Zhu, Xiatian, and Clifton, David A
    arXiv preprint arXiv:2206.06488 2022
  20. Preprint
    Knowledge Distillation Meets Open-Set Semi-Supervised Learning
    Yang, Jing,  Zhu, Xiatian, Bulat, Adrian, Martinez, Brais, and Tzimiropoulos, Georgios
    arXiv preprint arXiv:2205.06701 2022
  21. CVPR
    Source-Free Object Detection by Learning To Overlook Domain Style
    Li, Shuaifeng, Ye, Mao,  Zhu, Xiatian, Zhou, Lihua, and Xiong, Lin
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Jun 2022