# MVP: Motion Vector Propagation for Zero-Shot Video Object Detection

arXiv: https://arxiv.org/abs/2509.18388 · HTML: https://mlsanity.com/paper/2509.18388/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 20 references that are in the map.
- First posted on arXiv 22 Sep 2025.

## Builds on (most cited first, 16 of 16)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Open-vocabulary Object Detection via Vision and Language Knowledge Distillation](https://mlsanity.com/paper/2104.13921/) (2021)
- [RegionCLIP: Region-based Language-Image Pretraining](https://mlsanity.com/paper/2112.09106/) (2021)
- [Detecting Twenty-thousand Classes using Image-level Supervision](https://mlsanity.com/paper/2201.02605/) (2022)
- [YOLO-World: Real-Time Open-Vocabulary Object Detection](https://mlsanity.com/paper/2401.17270/) (2024)
- [Scaling Open-Vocabulary Object Detection](https://mlsanity.com/paper/2306.09683/) (2023)
- [YOLOv12: Attention-Centric Real-Time Object Detectors](https://mlsanity.com/paper/2502.12524/) (2025)
- [Flow-Guided Feature Aggregation for Video Object Detection](https://mlsanity.com/paper/1703.10025/) (2017)
- [Compressed Video Action Recognition](https://mlsanity.com/paper/1712.00636/) (2017)
- [Sequence Level Semantics Aggregation for Video Object Detection](https://mlsanity.com/paper/1907.06390/) (2019)
- [Object Detection from Video Tubelets with Convolutional Neural Networks](https://mlsanity.com/paper/1604.04053/) (2016)
- [Mobile Video Object Detection with Temporally-Aware Feature Maps](https://mlsanity.com/paper/1711.06368/) (2017)
- [Fast Object Detection in Compressed Video](https://mlsanity.com/paper/1811.11057/) (2018)

## Built on by (most cited first, 2 of 2)

- [MVTrack: Ultrafast Appearance-Free Moving Object Tracking from Compressed Bitstreams](https://mlsanity.com/paper/2608.10790/) (2026)
- [Analytical and Convolutional Neural Network-Based Motion-Vector Propagation for Efficient Video Object Detection](https://mlsanity.com/paper/2609.34142/) (2026)

## Abstract (arXiv)

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.