AI Paper Atlas

Research map / Detection and segmentation / Tracking

PS-MOT: Cultivating Instance Awareness from Point Seeds for Multi-Object Tracking

Kai Luo, Fei Teng, Mengfei Duan, Wanjun Jia, Xu Wang, Hao Shi, Kunyu Peng, Zhiyong Li, Kailun Yang

ECCV 2026 · Detection and segmentation › Tracking · approach: Association cues for online MOT · 0 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 Temporal-Feedback Prompting (negative cues + motion priors) to the naive point-to-box baseline (ablation)PS-Track (MOTIP) · DanceTrack valHOTA: 30.3 -> 49.0Improved
add Uncertainty-Guided Gaussian Learning (ablation)PS-Track with TFP · DanceTrack valHOTA: 49.0 -> 49.4Improved
add Point-Excited Wavelet Attention (ablation)PS-Track with TFP+UGL · DanceTrack valHOTA: 49.4 -> 50.3Improved
stochastic PEWA activation during training (p in 0.2 to 0.8) instead of always on (ablation)PS-Track (2-epoch schedule) · DanceTrack valHOTA: 44.2 -> 43.3 (p=0.4)Hurt
PEWA always on versus removed (p=1.0 vs p=0.0) (ablation)PS-Track (2-epoch schedule) · DanceTrack valHOTA: 43.7 -> 44.2Improved
add Gaussian noise to training points, up to 16 px (ablation)PS-Track (2-epoch schedule) · DanceTrack valHOTA: 44.2 -> 44.1No clear effect
increase point noise to 48 px (ablation)PS-Track (2-epoch schedule) · DanceTrack valHOTA: 44.2 -> 39.8Hurt
vary regression loss weight lambda_reg from 1 to 2, 3, 4, 5 (ablation)PS-Track (2-epoch schedule) · DanceTrack valHOTA: 44.2 (1) / 42.7 (2) / 44.8 (3) / 40.8 (4) / 43.7 (5)Mixed
use stronger SAM variant (v1 -> v2 -> v3) for offline pseudo-labels (ablation)PS-Track · DanceTrack valHOTA: 20.7 -> 39.0 -> 50.3Improved
train YOLOX with PS-Track plus BYTE instead of Point2RBox-v3 detector with off-the-shelf associatorsTBD pipeline · DanceTrack (point-supervised detector, TBD)HOTA: 10.8 -> 42.9Improved
point supervision via PS-Track instead of box supervisionMOTIP · DanceTrack valHOTA: 62.2 -> 50.3Hurt
point supervision via PS-Track instead of box supervisionBYTE · DanceTrack valHOTA: 47.1 -> 42.9Hurt

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