List of publications

  1. Rethinking Efficient and Effective Point-based Networks for Event Camera Classification and Regression - TPAMI CCF-A

    Authors: Ren, H., Zhou, Y., Zhu, J., Fu, H., Huang, Y., Lin, X., ... Cheng, B.

    Summary: We introduce a novel Point Cloud framework, named EventMamba, for event-based action recognition, CPR, and eye-tracking tasks.

  2. Spikepoint: An Efficient Point-based Spiking Neural Network - ICLR 2024 Spotlight CAAI-A

    Authors: Ren, H., Zhou, Y., Huang, Y., Fu, H., Lin, X., Song, J., Cheng, B.

    Summary: We propose SpikePoint, a novel end-to-end point-based SNN architecture. SpikePoint excels at processing sparse event cloud data, effectively extracting both global and local features through a singular-stage structure.

  3. A Simple and Effective Point-based Network for Event Camera 6-DOFs Pose Relocalization - CVPR 2024 CCF-A

    Authors: Ren, H., Zhu, J., Zhou, Y., Fu, H., Huang, Y., Cheng, B.

    Summary: We rethink the relationship between the event camera and camera pose relocalization tasks, leveraging the raw Point Cloud directly as network input to harness the high-temporal resolution and inherent sparsity of events.

  4. Exploring Temporal Dynamics in Event-based Eye Tracker - CVPR 2025 Event-based Vision workshop

    Authors: Ren, H. Lin X. Huang H. Cheng, B.

    Summary: We propose TDTracker, an effective eye-tracking framework that captures rapid eye movements by thoroughly modeling temporal dynamics from both implicit and explicit perspectives.

  5. FAPNet: An Effective Frequency Adaptive Point-based Eye Tracker - CVPR 2024 AIS workshop

    Authors: Lin, X.*, Ren, H.*, Cheng, B.

    Summary: We utilize Point Cloud as the event representation to harness the high temporal resolution and sparse characteristics of events in eye-tracking tasks.

  6. TTPOINT: A Tensorized Point Cloud Network for Lightweight Action Recognition - ACM MM 2023 CCF-A

    Authors: Ren, H., Zhuo Li, Aiersi Tuerhong, ... Cheng, B.

    Summary: We propose an efficient and effective single-modality tracker using Point Cloud representation named E2B.

  7. E2B: A Single Modality Point-based Tracker With Event Cameras - ICRA 2025 CCF-B CAAI-A

    Authors: Ren, H., Zhou, Y., Fu, H., Huang, Y., Xu, R., Cheng, B.

    Summary: We propose a lightweight and generalized point cloud network called TTPOINT, which achieves competitive results even compared to the state-of-the-art frame-based method in action recognition tasks.

  8. An FPGA Processor Employing Point-based SNN for Real-time Recognition with DVS - ISCAS 2025 CCF-C

    Authors: Wenjia Wang*, Ren, H.*, Wente Yi, Kexun cheng, Lehao Tan, Ying Cui, Bojun Cheng and Biao Pan.

    Summary: We implement hardware deployment and optimization of Spikepoint on FPGA through algorithmic-hardware collaborative design based on the completed algorithm work.

  9. ATFVO: Light Monocular Visual Odometry through Tensor Compressed LSTM Model - SARA 2021 Best Student Paper

    Authors: Ren, H., Li, C., Zhang, X., Ding, C., Man, C., Yu, H.

    Summary: This paper proposes a new framework called ATFVO which can be deployed on the edge device to resolve monocular visual odometry problem.