# Analytical and Convolutional Neural Network-Based Motion-Vector Propagation for Efficient Video Object Detection

arXiv: https://arxiv.org/abs/2609.34142 · HTML: https://mlsanity.com/paper/2609.34142/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 20 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Builds on (most cited first, 12 of 12)

- [Deep Feature Flow for Video Recognition](https://mlsanity.com/paper/1611.07715/) (2016)
- [Flow-Guided Feature Aggregation for Video Object Detection](https://mlsanity.com/paper/1703.10025/) (2017)
- [Memory Enhanced Global-Local Aggregation for Video Object Detection](https://mlsanity.com/paper/2003.12063/) (2020)
- [Compressed Video Action Recognition](https://mlsanity.com/paper/1712.00636/) (2017)
- [UA-DETRAC: A New Benchmark and Protocol for Multi-Object Detection and Tracking](https://mlsanity.com/paper/1511.04136/) (2015)
- [Sequence Level Semantics Aggregation for Video Object Detection](https://mlsanity.com/paper/1907.06390/) (2019)
- [Mobile Video Object Detection with Temporally-Aware Feature Maps](https://mlsanity.com/paper/1711.06368/) (2017)
- [Progressive Sparse Local Attention for Video object detection](https://mlsanity.com/paper/1903.09126/) (2019)
- [Looking Fast and Slow: Memory-Guided Mobile Video Object Detection](https://mlsanity.com/paper/1903.10172/) (2019)
- [See Without Decoding: Motion-Vector-Based Tracking in Compressed Video](https://mlsanity.com/paper/2602.00153/) (2026)
- [Scheduling Techniques of AI Models on Modern Heterogeneous Edge GPU -- A Critical Review](https://mlsanity.com/paper/2506.01377/) (2025)
- [MVP: Motion Vector Propagation for Zero-Shot Video Object Detection](https://mlsanity.com/paper/2509.18388/) (2025)

## Abstract (arXiv)

Continuous video analytics requires accurate localization at low latency within embedded power budgets. This paper presents a hardware-software design methodology that reuses codec motion vectors (MVs) between detector invocations. Two alternative models support translation and scale changes: analytical motion-vector propagation (Analytical-MV) and learned propagation using a convolutional neural network (CNN) (CNN-MV). The learned model uses convolutional operations and independent object updates suited to parallel execution on an edge graphics processing unit (GPU). Analytical-MV combines a harmonic-mean precision-recall score (F1) of 0.909 with a mean end-to-end latency of 9.03 ms and an energy consumption of 0.177 J per frame, yielding the lowest latency and energy among the evaluated configurations. Relative to detection on every frame, it reduces mean latency by 25.9% and energy per frame by 36.4%. CNN-MV offers a different trade-off: its fastest configuration raises recall from 0.871 for Analytical-MV to 0.890 and lowers mean power from 19.64 to 17.32 W, while achieving a latency of 18.42 ms and an energy consumption of 0.319 J per frame. It is therefore useful when recall or operating power is more important than minimum latency and energy. Execution on a deep learning accelerator (DLA) further reduces time-averaged GPU utilization relative to GPU execution. Host-processing optimization substantially improves both latency and energy, demonstrating the value of jointly designing temporal models and their execution pipelines.