AI Paper Atlas

Research map / Detection and segmentation / Tracking

CoopTrack: Exploring End-to-End Learning for Efficient Cooperative Sequential Perception

Jiaru Zhong, Jiahao Wang, Jiahui Xu, Xiaofan Li, Zaiqing Nie, Haibao Yu

ICCV 2025 · Detection and segmentation › Tracking · approach: Memory and correlation-based MOT · 11 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add fusion-after-decoding pipeline (ablation)CoopTrack · V2X-Seq (10Hz) ablationmAP: 0.310 -> 0.337Improved
add multi-dimensional feature extraction (MDFE) (ablation)CoopTrack · V2X-Seq (10Hz) ablationAMOTA: 0.277 -> 0.283Improved
add cross-agent alignment (CAA) (ablation)CoopTrack · V2X-Seq (10Hz) ablationAMOTA: 0.277 -> 0.304Improved
add graph-based association (GBA) (ablation)CoopTrack · V2X-Seq (10Hz) ablationAMOTA: 0.277 -> 0.295Improved
add GBA on top of MDFE and CAA (ablation)CoopTrack · V2X-Seq (10Hz) ablationAMOTA: 0.332 -> 0.346Improved
increase historical frames from 0 to 4 (ablation)CoopTrack · V2X-Seq (10Hz)AMOTA: 0.100 -> 0.346Improved
increase historical frames from 4 to 5 (ablation)CoopTrack · V2X-Seq (10Hz)AMOTA: 0.346 -> 0.324No clear effect
use end-to-end CoopTrack instead of UniV2XCoopTrack · V2X-Seq (2Hz)AMOTA: 0.239 -> 0.328Improved
use CoopTrack instead of V2X-ViTCoopTrack · V2X-Seq (2Hz)mAP: 0.268 -> 0.390Improved
use CoopTrack instead of Early FusionCoopTrack · Griffin-25mAMOTA: 0.670 -> 0.488Hurt
replace ResNet101 with ConvNeXt-S backboneCoopTrack · V2X-Seq (2Hz)AMOTA: 0.328 -> 0.429Improved
add feature flow prediction for latency compensationCoopTrack · V2X-Seq 500ms latencymAP/AMOTA degradation: 15.3% -> 3.8% mAP drop; 31.8% -> 6.8% AMOTA dropImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy