Email Facebook LinkedIn Github

I am currently a Lecturer at the ReLER lab, University of Technology Sydney. My research interests include video representation learning, unsupervised learning, self-supervised learning, few-shot learning, transfer learning.

I received my Ph.D. degree in University of Technology Sydney, advised by Prof. Yi Yang. I graduated from Zhejiang University with a bachelor’s degree.


  • Connective Cognition Network for Directional Visual Commonsense Reasoning
    Aming Wu, Linchao Zhu, Yahong Han, Yi Yang
    NeurIPS 2019

  • Dual Attention Matching for Audio-Visual Event Localization [PDF]
    Yu Wu, Linchao Zhu, Yan Yan, Yi Yang
    ICCV, 2019 (Oral)

  • Entangled Transformer for Image Captioning [PDF]
    Guang Li, Linchao Zhu, Ping Liu, Yi Yang
    ICCV, 2019

  • Auto-ReID: Searching for a Part-Aware ConvNet for Person Re-Identification [PDF]
    Ruijie Quan, Xuanyi Dong, Yu Wu, Linchao Zhu, Yi Yang
    ICCV, 2019

  • Sim-Real Joint Reinforcement Transfer for 3D Indoor Navigation [PDF]
    Fengda Zhu, Linchao Zhu, Yi Yang
    CVPR, 2019

  • Cubic LSTMs for Video Prediction [PDF]
    Hehe Fan, Linchao Zhu, Yi Yang
    AAAI, 2019

  • Compound Memory Networks for Few-shot Video Classification [PDF], [train.list, val.list, test.list]
    Linchao Zhu, Yi Yang
    ECCV, 2018

  • Decoupled Novel Object Captioner [PDF Code]
    Yu Wu, Linchao Zhu, Lu Jiang, Yi Yang
    ACM MM 2018

  • Fast Parameter Adaptation for Few-shot Image Captioning and Visual Question Answering [PDF Code]
    Xuanyi Dong, Linchao Zhu, De Zhang, Yi Yang, Fei Wu
    ACM MM, 2018

  • Watching a Small Portion could be as Good as Watching All:
    Towards Efficient Video Classification [PDF Code]
    Hehe Fan, Zhongwen Xu, Linchao Zhu, Chenggang Yan, Jianjun Ge, Yi Yang
    IJCAI 2018

  • Bidirectional Multirate Reconstruction for Temporal Modeling in Videos [PDF Code]
    Linchao Zhu, Zhongwen Xu, Yi Yang
    CVPR 2017 (Spotlight)

  • Few-Shot Object Recognition from Machine-Labeled Web Images [PDF Code]
    Zhongwen Xu*, Linchao Zhu*, Yi Yang
    CVPR 2017 (Spotlight), * indicates equal contributions

  • Uncovering Temporal Context for Video Question Answering [PDF] [Project]
    Linchao Zhu, Zhongwen Xu, Yi Yang, Alex G. Hauptmann
    IJCV, DOI: 10.1007/s11263-017-1033-7, 2017

  • Recognizing an action using its name: A knowledge-based approach [PDF]
    Chuang Gan, Yi Yang, Linchao Zhu, Deli Zhao, Yueting Zhuang
    IJCV, DOI: 10.1007/s11263-016-0893-6, 2016


  • Learning to Transfer Learn [Arxiv]
    Linchao Zhu, Sercan O. Arık, Yi Yang, Tomas Pfister

  • FASTER Recurrent Networks for Video Classification [Arxiv]
    Linchao Zhu, Laura Sevilla-Lara, Du Tran, Matt Feiszli, Yi Yang, Heng Wang

  • Attentive Sequence to Sequence Translation for Localizing Clips of Interest by Natural Language Descriptions [Arxiv]
    Ke Ning, Linchao Zhu, Ming Cai, Yi Yang, Di Xie, Fei Wu

  • Meta Filter Pruning to Accelerate Deep Convolutional Neural Networks [Arxiv]
    Yang He, Ping Liu, Linchao Zhu, Yi Yang


  • We ranked first in EPIC-Kitchen Action Recognition 2019. See our report.

  • Our report on ActivityNet Trimmed Action Recognition 2017.

  • Our report on Google YouTube8M Classification 2017.

  • We got the first place on the video localization task in TRECVID 2016 competition. See our report.

  • We got the first place on the Action Recognition task in THUMOS 2015. See our notebook paper.