Research
Referring Multi-Object Tracking in Moving-Camera Videos via Global Motion Compensation
arXiv:2610.04185v1 Announce Type: new Abstract: Referring multi-object tracking (RMOT) takes a video and a language expression as input and tracks all referred objects. Many tracking requirements invo
arXiv:2610.04185v1 Announce Type: new Abstract: Referring multi-object tracking (RMOT) takes a video and a language expression as input and tracks all referred objects. Many tracking requirements involve how an object moves rather than how it appears. However, in a video captured by a moving camera, a parked vehicle may appear to move, while a moving vehicle may show little displacement. Existing RMOT methods relate motion with text but do not explicitly remove camera-induced motion. In this paper, we propose extracting residual motion across frames by estimating camera motion in driver-view videos and compare motion characteristics with the query expression. We consider the motion-matching extent and integrate it with the RMOT method's prediction result through late fusion. In the evaluation, we verify the performance gain of taking the motion compensation module as a plug-in across different RMOT hosts.
Related
- ViewSAM: Learning View-aware Cross-modal Semantics for Weakly Supervised Cross-view Referring Multi-Object Tracking
- Training-Free Semantic Multi-Object Tracking with Vision-Language Models
- HDST-GNN: Heterogeneous Dynamic Spatiotemporal Graph Neural Networks for Multi-Object Tracking in UAV Aerial Imagery
Source: arXiv cs.CV | 2026-10-06