{"ID":2867947,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.18388","arxiv_id":"2509.18388","title":"MVP: Motion Vector Propagation for Zero-Shot Video Object Detection","abstract":"Running a large open-vocabulary (Open-vocab) detector on every video frame is accurate but expensive. We introduce a training-free pipeline that invokes OWLv2 only on fixed-interval keyframes and propagates detections to intermediate frames using compressed-domain motion vectors (MV). A simple 3x3 grid aggregation of motion vectors provides translation and uniform-scale updates, augmented with an area-growth check and an optional single-class switch. The method requires no labels, no fine-tuning, and uses the same prompt list for all open-vocabulary methods. On ILSVRC2015-VID (validation dataset), our approach (MVP) attains mAP@0.5=0.609 and mAP@[0.5:0.95]=0.316. At loose intersection-over-union (IoU) thresholds it remains close to framewise OWLv2-Large (0.747/0.721 at 0.2/0.3 versus 0.784/0.780), reflecting that coarse localization is largely preserved. Under the same keyframe schedule, MVP outperforms tracker-based propagation (MOSSE, KCF, CSRT) at mAP@0.5. A supervised reference (YOLOv12x) reaches 0.631 at mAP@0.5 but requires labeled training, whereas our method remains label-free and open-vocabulary. These results indicate that compressed-domain propagation is a practical way to reduce detector invocations while keeping strong zero-shot coverage in videos. Our code and models are available at https://github.com/microa/MVP.","short_abstract":"Running a large open-vocabulary (Open-vocab) detector on every video frame is accurate but expensive. We introduce a training-free pipeline that invokes OWLv2 only on fixed-interval keyframes and propagates detections to intermediate frames using compressed-domain motion vectors (MV). A simple 3x3 grid aggregation of m...","url_abs":"https://arxiv.org/abs/2509.18388","url_pdf":"https://arxiv.org/pdf/2509.18388v1","authors":"[\"Binhua Huang\",\"Ni Wang\",\"Wendong Yao\",\"Soumyabrata Dev\"]","published":"2025-09-22T20:18:27Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":609527,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2867947,"paper_url":"https://arxiv.org/abs/2509.18388","paper_title":"MVP: Motion Vector Propagation for Zero-Shot Video Object Detection","repo_url":"https://github.com/microa/MVP","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}