Xinpeng Liu (xinpengliu0907@gmail.com)

About

I’m a third-year Ph.D student under the supervision of Prof. Cewu Lu. Currently, I am a member of Machine Vision and Intelligence Group (MVIG). Prior to that, I received my Bachelor’s and Master’s degrees (Computer Science) from Shanghai Jiao Tong University. My research interests include human motion understanding and activity understanding.

Publications (Google Scholar)

Physics in human motion

• Xinpeng Liu, Junxuan Liang, Chenshuo Zhang, Zixuan Cai, Cewu Lu, Yong-Lu Li. “Homogeneous Dynamics Space for Heterogeneous Human”. arXiv preprint. [Project].

• Xinpeng Liu, Junxuan Liang, Zili Lin, Haowen Hou, Yong-Lu Li*, Cewu Lu* (*=corresponding authors). “ImDy: Human Inverse Dynamics from Imitated Observations.” arXiv preprint. [Paper] [Project]

Human motion generation

• Xinpeng Liu*, Haowen Hou*, Yanchao Yang, Yong-Lu Li, and Cewu Lu (*=equal contribution). “Revisit Human-Scene Interaction via Space Occupancy” ECCV 2024. [Paper][Page].

• Xinpeng Liu, Yong-Lu Li*, Ailing Zeng, Zizheng Zhou, Yang You, and Cewu Lu* (*=corresponding authors). “Bridging the Gap between Human Motion and Action Semantics via Kinematic Phrases” ECCV 2024. [Paper][Page]

Human action understanding

• Xiaoyang Liu*, Boran Wen*, Xinpeng Liu*, Zizheng Zhou, Hongwei Fan, Cewu Lu, Lizhuang Ma, Yulong Chen, Yong-Lu Li (*=equal contribution). “Interacted Object Grounding in Spatio-Temporal Human-Object Interactions”. AAAI 2025.

• Zehao Wang, Xinpeng Liu, Xiaoqian Wu, Yudonglin Zhang, Zhou Fang, Yifan Fang, Junfu Pu, Cewu Lu, Yong-Lu Li. “Verb Mirage: Unveiling and Assessing Verb Concept Hallucinations in Multimodal Large Language Models”. arXiv preprint. [Paper].

• Yong-Lu Li*, Xiaoqian Wu*, Xinpeng Liu, Zehao Wang, Yiming Dou, Yikun Ji, Junyi Zhang, Yixing Li, Xudong Lu, Jingru Tan, Cewu Lu. “From Isolated Islands to Pangea: Unifying Semantic Space for Human Action Understanding.” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2024. [Paper] [Project] [Code]

• Siqi Liu, Yong-Lu Li, Zhou Fang, Xinpeng Liu, Yang You, Cewu Lu. “Primitive-based 3D Human-Object Interaction Modelling and Programming.” Proceedings of the AAAI Conference on Artificial Intelligence. 2024. [Paper] [Project]

• Yong-Lu Li, Xinpeng Liu, Xiaoqian Wu, Yizhuo Li, Zuoyu Qiu, Liang Xu, Yue Xu, Hao-Shu Fang, Cewu Lu. “Hake: a knowledge engine foundation for human activity understanding.” IEEE Transactions on Pattern Analysis and Machine Intelligence (2023). [Paper]

• Xiaoqian Wu*, Yong-Lu Li*, Xinpeng Liu, Junyi Zhang, Yuzhe Wu, Cewu Lu. “Mining Cross-Person Cues for Body-Part Interactiveness Learning in HOI Detection.” European Conference on Computer Vision (pp. 121-136). Cham: Springer Nature Switzerland. [Paper] [Code]

• Xinpeng Liu*, Yong-Lu Li*, Xiaoqian Wu, Cewu Lu, Chi-Keung Tang. “Interactiveness Field in Human-Object Interactions.” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2022. [Paper]

• Xinpeng Liu*, Yong-Lu Li*, Cewu Lu. “Highlighting Object Category Immunity for the Generalization of Human-Object Interaction Detection.” Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 36. No. 2. 2022. [Paper] [Code]

• Yong-Lu Li, Xinpeng Liu, Xiaoqian Wu, Xijie Huang, Liang Xu, Cewu Lu. “Transferable Interactiveness Knowledge for Human-Object Interaction Detection.” IEEE Transactions on Pattern Analysis & Machine Intelligence 44.07 (2022): 3870-3882. [Paper] [Code]

• Yong-Lu Li*, Xinpeng Liu*, Xiaoqian Wu, Yizhuo Li, Cewu Lu (*=equal contribution). “HOI Analysis: Integrating and Decomposing Human-Object Interaction.” Advances in Neural Information Processing Systems 33 (2020): 5011-5022. [Paper] [Code]

• Yong-Lu Li, Xinpeng Liu, Han Lu, Shiyi Wang, Junqi Liu, Jiefeng Li, and Cewu Lu. “Detailed 2D-3D Joint Representation for Human-Object Interaction.” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10166-10175. 2020. [Paper] [Code]

• Yong-Lu Li, Liang Xu, Xinpeng Liu, Xijie Huang, Yue Xu, Shiyi Wang, Hao-Shu Fang, Ze Ma, Mingyang Chen, and Cewu Lu. “PaStaNet: Toward Human Activity Knowledge Engine.” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 382-391. 2020. [Paper] [Code]

• Yong-Lu Li, Liang Xu, Xinpeng Liu, Xijie Huang, Yue Xu, Mingyang Chen, Ze Ma, Shiyi Wang, Hao-Shu Fang, and Cewu Lu. “Hake: Human activity knowledge engine.” arXiv preprint arXiv:1904.06539 (2019). [Project] [Paper] [Code]

Teaching

• Project Tutor for SJTU CS348: Computer Vision (2022 Fall, 2023 Fall)

  Co-advising “DiffAnnot: Improved Neural Annotator with Denoising Diffusion Model”; Chaofan Lin, Tianyuan Qiu, Hanchong Yan, Muzi Tao. ICIPMC 2023. [Page]

  Co-advising “Kinematic Motion Diffusion: Towards Semantic-adaptive Motion Synthesis via Kinematic Guidance”; Leizhi Li, Jincheng Yang, Yichao Zhong, Junxian Guo. ICMSSP 2024. [Page]

• TA for SJTU AI3618: Virtual Reality (2023 Spring, 2024 Spring)

Academic Services

• Conference Reviewer: ICLR, NeurIPS, ICML, CVPR, ICCV, ECCV, ACCV, NeurIPS Track Datasets and Benchmarks, AAAI, AISTAT.

• Journal Reviewer: IoT, TMM, JVIS, JVCIP.

Honors

• Graduate Fellowship, The 85th Computer Department Education Development Fund and Yang Yuanqing Education Fund, Aug. 2022.
• Wu Wenjun Honor Ph.D. Fellowship, Shanghai Jiao Tong University, Sept. 2022.