Research
MVTrack: Ultrafast Appearance-Free Moving Object Tracking from Compressed Bitstreams
arXiv:2608.10790v1 Announce Type: cross Abstract: Deploying modern video trackers at scale is bottlenecked by the computational cost of RGB-based object detectors. To this end, we present MVTrack, an
arXiv:2608.10790v1 Announce Type: cross Abstract: Deploying modern video trackers at scale is bottlenecked by the computational cost of RGB-based object detectors. To this end, we present MVTrack, an ultrafast tracker for moving objects that operates directly on H.264 bitstreams. MVTrack combines MVDet, a lightweight detector for motion vector fields, with MVLink, a minimalist kinematic association module. On VIRAT, MVTrack outperforms YOLO26n while using 60imes fewer parameters, requiring 40imes fewer FLOPs, and reducing CPU latency by 8.6imes. These results demonstrate that compressed video data alone can enable accurate and scalable surveillance tracking, thereby bypassing the need for pixel reconstruction.
Related
- FeedbackTrack: Visual-Cortex-Inspired Cross-Frame Feedback for Transformer Tracking
- Temporal Preservation over Processing: Diagnosing and Designing Spatiotemporal Single-Stage Video Detectors
Source: arXiv cs.AI | 2026-08-12