# CoopTrack: Exploring End-to-End Learning for Efficient Cooperative Sequential Perception Source: [CoopTrack: Exploring End-to-End Learning for Efficient Cooperative Sequential Perception]() Collection index: [llms.txt]() Data updated: 2025-10-26T05:15:13.470Z Authors: Jiaru Zhong, Jiahao Wang, Jiahui Xu, Xiaofan Li, Zaiqing Nie, Haibao Yu Published: 2025-07-25T13:04:54.000Z ## Abstract Cooperative perception aims to address the inherent limitations of single-vehicle autonomous driving systems through information exchange among multiple agents. Previous research has primarily focused on single-frame perception tasks. However, the more challenging cooperative sequential perception tasks, such as cooperative 3D multi-object tracking, have not been thoroughly investigated. Therefore, we propose CoopTrack, a fully instance-level end-to-end framework for cooperative tracking, featuring learnable instance association, which fundamentally differs from existing approaches. CoopTrack transmits sparse instance-level features that significantly enhance perception capabilities while maintaining low transmission costs. Furthermore, the framework comprises two key components: Multi-Dimensional Feature Extraction, and Cross-Agent Association and Aggregation, which collectively enable comprehensive instance representation with semantic and motion features, and adaptive cross-agent association and fusion based on a feature graph. Experiments on both the V2X-Seq and Griffin datasets demonstrate that CoopTrack achieves excellent performance. Specifically, it attains state-of-the-art results on V2X-Seq, with 39.0\\% mAP and 32.8\\% AMOTA. The project is available at https://github.com/zhongjiaru/CoopTrack. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Multi-Object Tracking on Griffin 25m](): Multi-Object Tracking; Griffin 25m; AMOTA (0-100 m Overall): 26.8. - [3D Object Detection on Griffin 25m](): 3D Object Detection; Griffin 25m; AP (Overall, 0-100m): 27.9. - [3D Object Detection on V2X-Seq](): 3D Object Detection; V2X-Seq; AP (0-150m): 23.2. - [3D Object Tracking on V2X-Seq](): 3D Object Tracking; V2X-Seq; AMOTA (0-150m Overall): 17.1. ## Original sources and implementation [Original paper]() [PDF]()