# MoCLIP-Lite: Efficient Video Recognition by Fusing CLIP with Motion Vectors

arXiv: https://arxiv.org/abs/2509.17084 · HTML: https://mlsanity.com/paper/2509.17084/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 19 references that are in the map.
- First posted on arXiv 21 Sep 2025.

## Builds on (most cited first, 13 of 13)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [Two-Stream Convolutional Networks for Action Recognition in Videos](https://mlsanity.com/paper/1406.2199/) (2014)
- [CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval](https://mlsanity.com/paper/2104.08860/) (2021)
- [Expanding Language-Image Pretrained Models for General Video Recognition](https://mlsanity.com/paper/2208.02816/) (2022)
- [Temporal Segment Networks for Action Recognition in Videos](https://mlsanity.com/paper/1705.02953/) (2017)
- [Compressed Video Action Recognition](https://mlsanity.com/paper/1712.00636/) (2017)
- [Real-time Action Recognition with Enhanced Motion Vector CNNs](https://mlsanity.com/paper/1604.07669/) (2016)

## 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)
- [Selective Spatio-Temporal Fruit Inspector (S2FI): A Mamba-based Framework for Rotational Fruit Quality Assessment](https://mlsanity.com/paper/2610.12868/) (2026)

## Abstract (arXiv)

Video action recognition is a fundamental task in computer vision, but state-of-the-art models are often computationally expensive and rely on extensive video pre-training. In parallel, large-scale vision-language models like Contrastive Language-Image Pre-training (CLIP) offer powerful zero-shot capabilities on static images, while motion vectors (MV) provide highly efficient temporal information directly from compressed video streams. To synergize the strengths of these paradigms, we propose MoCLIP-Lite, a simple yet powerful two-stream late fusion framework for efficient video recognition. Our approach combines features from a frozen CLIP image encoder with features from a lightweight, supervised network trained on raw MV. During fusion, both backbones are frozen, and only a tiny Multi-Layer Perceptron (MLP) head is trained, ensuring extreme efficiency. Through comprehensive experiments on the UCF101 dataset, our method achieves a remarkable 89.2% Top-1 accuracy, significantly outperforming strong zero-shot (65.0%) and MV-only (66.5%) baselines. Our work provides a new, highly efficient baseline for video understanding that effectively bridges the gap between large static models and dynamic, low-cost motion cues. Our code and models are available at https://github.com/microa/MoCLIP-Lite.