See Without Decoding: Motion-Vector-Based Tracking in Compressed Video
Computer Vision and Pattern Recognition
2026-02-03 v1 Artificial Intelligence
Image and Video Processing
Abstract
We propose a lightweight compressed-domain tracking model that operates directly on video streams, without requiring full RGB video decoding. Using motion vectors and transform coefficients from compressed data, our deep model propagates object bounding boxes across frames, achieving a computational speed-up of order up to 3.7 with only a slight 4% mAP@0.5 drop vs RGB baseline on MOTS15/17/20 datasets. These results highlight codec-domain motion modeling efficiency for real-time analytics in large monitoring systems.
Cite
@article{arxiv.2602.00153,
title = {See Without Decoding: Motion-Vector-Based Tracking in Compressed Video},
author = {Axel Duché and Clément Chatelain and Gilles Gasso},
journal= {arXiv preprint arXiv:2602.00153},
year = {2026}
}