AI Paper Atlas

Research map / Detection and segmentation / Tracking

Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Tracking

Jinlong Peng, Changan Wang, Fangbin Wan, Yang Wu, Yabiao Wang, Ying Tai, Chengjie Wang, Jilin Li, Feiyue Huang, Yanwei Fu

ECCV 2020 · Detection and segmentation › Tracking · approach: Memory and correlation-based MOT · 406 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 object attention (classification confidence map) to the paired regression branch (ablation)CTracker baseline · MOT17 testMOTA: 64.4 -> 66.0Improved
add object attention (classification confidence map) to the paired regression branch (ablation)CTracker baseline · MOT17 testIDF1: 51.6 -> 55.7Improved
add object attention to the baseline (ablation)CTracker baseline · MOT17 testMOTP: 78.2 -> 78.8Improved
add a stand-alone ID verification branch without using it as attention (ablation)Baseline+ObjAtten · MOT17 testMOTA: 66.0 -> 65.6Hurt
add a stand-alone ID verification branch without using it as attention (ablation)Baseline+ObjAtten · MOT17 testIDF1: 55.7 -> 55.2Hurt
use ID verification output as additional attention (joint attention) (ablation)Baseline+ObjAtten · MOT17 testMOTA: 66.0 -> 66.6Improved
use ID verification output as additional attention (joint attention) (ablation)Baseline+ObjAtten · MOT17 testIDF1: 55.7 -> 57.4Improved
use ID verification output as additional attention (joint attention) (ablation)Baseline+ObjAtten · MOT17 testMOTP: 78.8 -> 78.2Hurt
add Memory Sharing Mechanism (feature reuse across chain nodes) (ablation)CTracker · Inference time, 1080x1920Total time (ms): 223.56 -> 148.10Improved
use CTracker detections instead of public detections for TracktorTracktor · MOT17 testMOTA: 53.5 -> 54.4Improved
use CTracker detections instead of public detections for TracktorTracktor · MOT17 testIDF1: 52.3 -> 56.1Improved
replace Tracktor+CTdet tracking with CTracker's chained paired regressionTracktor+CTdet · MOT17 test (private detection)MOTA: 54.4 -> 66.6Improved

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