Runzhou Ge

Nomor Research (Germany) — Germany

Computer Science · Physical Sciences

9h-index768citations15works8.32yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Advanced Neural Network Applications(7), Human Pose and Action Recognition(7), Video Surveillance and Tracking Methods(4), Multimodal Machine Learning Applications(4), Advanced Vision and Imaging(3)

Publications15 total

MoST: Multi-modality Scene Tokenization for Motion Prediction
2024· 9 cited
WOMD-LiDAR: Raw Sensor Dataset Benchmark for Motion Forecasting
2024· 15 cited
MoST: Multi-modality Scene Tokenization for Motion Prediction
arXiv (Cornell University)·2024· 1 citedOpen Access
WOMD-LiDAR: Raw Sensor Dataset Benchmark for Motion Forecasting
arXiv (Cornell University)·2023Open Access
AFDetV2: Rethinking the Necessity of the Second Stage for Object Detection from Point Clouds
Proceedings of the AAAI Conference on Artificial Intelligence·2022· 123 citedOpen Access
AFDetV2: Rethinking the Necessity of the Second Stage for Object Detection from Point Clouds
arXiv (Cornell University)·2021Open Access
Real-Time Anchor-Free Single-Stage 3D Detection with IoU-Awareness
arXiv (Cornell University)·2021· 6 citedOpen Access
2nd Place Solution for Waymo Open Dataset Challenge -- 2D Object Detection
arXiv (Cornell University)·2020· 6 citedOpen Access
1st Place Solution for Waymo Open Dataset Challenge -- 3D Detection and Domain Adaptation
arXiv (Cornell University)·2020· 19 citedOpen Access
1st Place Solutions for Waymo Open Dataset Challenges -- 2D and 3D Tracking
arXiv (Cornell University)·2020· 10 citedOpen Access
AFDet: Anchor Free One Stage 3D Object Detection
arXiv (Cornell University)·2020· 96 citedOpen Access
MAC: Mining Activity Concepts for Language-Based Temporal Localization
2019· 185 cited
MAC: Mining Activity Concepts for Language-based Temporal Localization
arXiv (Cornell University)·2018· 20 citedOpen Access
Motion-Appearance Co-memory Networks for Video Question Answering
2018· 255 cited
Motion-Appearance Co-Memory Networks for Video Question Answering
arXiv (Cornell University)·2018· 23 citedOpen Access

Frequent Co-authors

Zhuangzhuang Ding(7), Kan Chen(6), Yihan Hu(5), Li Huang(5), Jiyang Gao(4), Ram Nevatia(4), Sijia Chen(4), Charles R. Qi(4), Zoey Yang(4), Scott Ettinger(4), Dragomir Anguelov(4), Kun Li(3), Yu Wang(3), Jie Liao(3), Yihan Hu(2), Wenxin Shao(2), Li Huang(2), Qiang Liu(2), Kan Chen(2), Hang Qiu(2)