Xiangteng He 何相腾

Research Assistant Professor, Peking University

Email: hexiangteng AT pku.edu.cn

Google Scholar

Biography

I am a Research Assistant Professor at MIPL Group (led by Prof. Yuxin Peng) at Peking University. I received Ph.D. degree from Wangxuan Institute of Computer Technology, Peking University in 2020 (advised by Prof. Yuxin Peng), and B.E degree from College of Computer Science, Nankai University in 2014 (advised by Prof. Jufeng Yang). I have authored more than 30 papers, including IJCV, TIP, TMM, TCSVT, CVPR, ICCV, ICDE, ACM MM, ACM SIGIR, IJCAI and AAAI. My research interests include fine-grained visual analysis, video retrieval, multi-modal content analysis. I was one of the recipients of 2020 CCF (China Computer Federation) Outstanding Doctoral Dissertation Award and 2018 Baidu Scholarship, and awarded Young Elite Scientists Sponsorship Program by CAST in 2022.

Call for papers

  • The 11th Workshop on Fine-Grained Visual Categorization, CVPR 2024.
    This year, FGVC will have two paper tracks: an 8-page CVPR proceedings and a 4-page non-archival track. Deadlines March 1st & 20th. More information here.
  • News

  • 2024-04-17: One paper is accepted by IJCAI 2024. Congrats to Hongbo Sun!
  • 2024-04-12: One paper is accepted by ACM TOMM. Congrats to Ruoyan Pi!
  • 2024-02-21: One paper is accepted by IEEE TIP. Congrats to Peng Wu !
  • 2024-01-17: Very honored to win MIR Outstanding Reviewer Award in 2023.
  • 2023-12-24: Co-organizing the FGVC11 workshop at CVPR 2024.
  • 2023-12-09: One papers is accepted by AAAI 2024. Congrats to Yanzhe Chen!
  • 2023-12-01: One papers is accepted by ICDE 2024. Congrats to Hulingxiao He!
  • 2023-10-16: One papers is accepted by IEEE TMM 2023. Congrats to Hongbo Sun!
  • 2023-07-26: Four papers are accepted by ACM MM 2023. Congrats to Hongbo Sun, Zijun Deng, and Yanzhe Chen!
  • 2023-07-14: One paper is accepted by ICCV 2023. Congrats to Yulin Pan!
  • 2023-03-07: One paper is accepted by ACM TOMM. Congrats to Zijun Deng!
  • 2023-02-28: One paper is accepted by CVPR 2023. Congrats to HsiaoYuan Hsu!
  • 2023-01-10: Co-organizing the FGVC10 workshop at CVPR 2023.
  • 2023-01-03: One paper is accepted by ACM TOMM. Congrats to Duoduo Feng!
  • 2022-11-29: Invited to serve as Area Chair in ICME 2023.
  • 2022-10-25: Awarded Young Elite Scientists Sponsorship Program by CAST(中国科协青年人才托举工程项目).
  • 2022-07-20: I give a talk “Fine-grained Cross-media Categorization and Retrieval” at ChinaMM 2022 .
  • 2022-07-08: One paper is accepted by Chinese Journal of Electronics (《电子学报》英文版). Congrats to Zhaoda Ye!
  • 2022-07-01: One paper is accepted by ACM MM 2022. Congrats to Hongbo Sun!
  • 2022-03-31: One paper is accepted by ACM SIGIR 2022.
  • 2022-01-05: Co-organizing the FGVC9 workshop at CVPR 2022.
  • 2021-07-04: Two papers are accepted by ACM MM 2021. Congrats to Zhen Han and Peng Wu !
  • 2021-05-17: I give a talk "Fine-grained Visual Categorization and Retrieval" at Peking Unversity.
  • 2021-01-31: I attend the award ceremony of CCF (China Computer Federation) Outstanding Doctoral Dissertation Award.
  • 2020-12-10: Very honored to serve as SPC in IJCAI 2021.
  • 2020-12-03: I give a talk "Use What You Have: Multi-modal Information in Fine-grained Analysis" at WebFG Workshop in ACCV 2020 .
  • Selected Publications

    FineFMPL: Fine-grained Feature Mining Prompt Learning for Few-Shot Class Incremental Learning

    Hongbo Sun, Jiahuan Zhou, Xiangteng He, Jinglin Xu, Yuxin Peng
    International Joint Conference on Artificial Intelligence (IJCAI), 2024

    EOGT: Video Anomaly Detection with Enhanced Object Information and Global Temporal Dependency

    Ruoyan Pi, Peng Wu, Xiangteng He* and Yuxin Peng
    ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 2024

    Toward Video Anomaly Retrieval From Video Anomaly Detection: New Benchmarks and Model

    Peng Wu, Jing Liu, Xiangteng He, Yuxin Peng, Peng Wang, Yanning Zhang
    IEEE Transactions on Image Processing (IEEE TIP), 2024

    FashionERN: Enhance-and-Refine Network for Composed Fashion Image Retrieval

    Yanzhe Chen, Huasong Zhong, Xiangteng He, Yuxin Peng, Jiahuan Zhou, Lele Cheng
    AAAI Conference on Artificial Intelligence (AAAI), 2024

    Firzen: Firing Strict Cold-Start Items with Frozen Heterogeneous and Homogeneous Graphs for Recommendation

    Hulingxiao He, Xiangteng He*, Yuxin Peng, Zifei Shan, Xin Su
    IEEE International Conference on Data Engineering (ICDE), 2024

    HCL: Hierarchical Consistency Learning for Webly Supervised Fine-Grained Recognition

    Hongbo Sun, Xiangteng He, Yuxin Peng
    IEEE Transactions on Multimedia (TMM), 2024

    Fine-Grained Visual Prompt Learning of Vision-Language Models for Image Recognition

    Hongbo Sun, Xiangteng He, Jiahuan Zhou, Yuxin Peng
    ACM Multimedia Conference (ACM MM), 2023

    Real20M: A Large-scale E-commerce Dataset for Cross-domain Retrieval

    Yanzhe Chen, Huasong Zhong, Xiangteng He, Yuxin Peng, Lele Cheng
    ACM Multimedia Conference (ACM MM), 2023

    MV-Diffusion: Motion-aware Video Diffusion Model

    Zijun Deng, Xiangteng He, Yuxin Peng, Xiongwei Zhu, Lele Cheng
    ACM Multimedia Conference (ACM MM), 2023

    Efficiency-optimized Video Diffusion Models

    Zijun Deng, Xiangteng He, Yuxin Peng
    ACM Multimedia Conference (ACM MM), 2023

    Scanning Only Once: An End-to-end Framework for Fast Temporal Grounding in Long Videos

    Yulin Pan, Xiangteng He*, Biao Gong, Yiliang Lv, Yujun Shen, Yuxin Peng, Deli Zhao*
    International Conference of Computer Vision (ICCV), 2023

    PosterLayout: A New Benchmark and Approach for Content-Aware Visual-Textual Presentation Layout

    HsiaoYuan Hsu, Xiangteng He, Yuxin Peng, Hao Kong and Qing Zhang
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023

    LFR-GAN: Local Feature Refinement based Generative Adversarial Network for Text-to-Image Generation

    Zijun Deng, Xiangteng He and Yuxin Peng
    ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 2023

    MKVSE: Multimodal Knowledge Enhanced Visual-Semantic Embedding for Image-Text Retrieval

    Duoduo Feng, Xiangteng He and Yuxin Peng
    ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 2023

    SIM-Trans: Structure Information Modeling Transformer for Fine-grained Visual Categorization

    Hongbo Sun, Xiangteng He and Yuxin Peng
    ACM Multimedia Conference (ACM MM), 2022

    Learn from Unlabeled Videos for Near-duplicate Video Retrieval

    Xiangteng He#, Yulin Pan#, Mingqian Tang, Yiliang Lv and Yuxin Peng
    ACM SIGIR Conference on Research and Development in Information Retrieval (ACM SIGIR), 2022

    HANet: Hierarchical Alignment Networks for Video-Text Retrieval

    Peng Wu, Xiangteng He*, Mingqian Tang, Yiliang Lv and Jing Liu*
    ACM Multimedia Conference (ACM MM), 2021
    [PDF] [BibTeX] [Code]

    Video Similarity and Alignment Learning on Partial Video Copy Detection

    Zhen Han, Xiangteng He*, Mingqian Tang and Yiliang Lv
    ACM Multimedia Conference (ACM MM), 2021
    [PDF] [BibTeX] [Project]

    Fine-grained Visual-textual Representation Learning

    Xiangteng He and Yuxin Peng
    IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2020

    Which and How Many Regions to Gaze: Focus Discriminative Regions for Fine-grained Visual Categorization

    Xiangteng He, Yuxin Peng and Junjie Zhao
    International Journal of Computer Vision (IJCV), 2019

    A New Benchmark and Approach for Fine-grained Cross-media Retrieval

    Xiangteng He, Yuxin Peng and Liu Xie
    ACM Multimedia Conference (ACM MM), 2019

    Fast Fine-grained Image Classification via Weakly Supervised Discriminative Localization

    Xiangteng He, Yuxin Peng and Junjie Zhao
    IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2019

    Object-Part Attention Model for Fine-grained Image Classification
    (This work was the highly cited paper by ESI, which received enough citations to place it in the top 1% of its academic field.)
    Yuxin Peng, Xiangteng He and Junjie Zhao
    IEEE Transactions on Image Processing (TIP), 2018

    StackDRL: Stacked Deep Reinforcement Learning for Fine-grained Visual Categorization

    Xiangteng He, Yuxin Peng and Junjie Zhao
    International Joint Conference on Artificial Intelligence (IJCAI), 2018

    Only Learn One Sample: Fine-Grained Visual Categorization with One Sample Training

    Xiangteng He and Yuxin Peng
    ACM Multimedia Conference (ACM MM), 2018

    Fine-grained Image Classification via Combining Vision and Language

    Xiangteng He and Yuxin Peng
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017

    Weakly Supervised Learning of Part Selection Model with Spatial Constraints for Fine-grained Image Classification

    Xiangteng He and Yuxin Peng
    AAAI Conference on Artificial Intelligence (AAAI), 2017

    Fine-grained Discriminative Localization via Saliency-guided Faster R-CNN

    Xiangteng He, Yuxin Peng and Junjie Zhao
    ACM Multimedia Conference (ACM MM), 2017

    Honors

  • Young Elite Scientists Sponsorship Program by CAST, 2022.
  • CCF (China Computer Federation) Outstanding Doctoral Dissertation Award (10 in total), 2020.
  • Excellent Doctorate Dissertation Award of Peking University, 2020.
  • Excellent Graduates of Beijing, 2020.
  • Excellent Graduates of Peking University, 2020.
  • Huawei Scholarship, 2019.
  • Baidu Scholarship (6 in China, 10 in total of the world), 2018.
  • National Scholarship (Top 1), 2018.
  • Chancellor's Scholarship of Peking University, 2018.
  • Top 10 Outstanding Academic Students, School of EECS, Peking University, 2018.
  • Huawei Scholarship, 2017.