# Motion Guided Token Compression for Efficient Masked Video Modeling

arXiv: https://arxiv.org/abs/2402.18577 · HTML: https://mlsanity.com/paper/2402.18577/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Visual token pruning in multimodal models, one of 12 directions in Efficient LLM inference and serving.
- Builds on 43 of its 66 references that are in the map.
- First posted on arXiv 10 Jan 2024.

## Placed in

- Efficient LLM inference and serving / [Visual token pruning in multimodal models](https://mlsanity.com/inference/visual-token-pruning-in-multimodal-models/)

## Builds on (most cited first, 30 of 43)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [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)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [SimMIM: A Simple Framework for Masked Image Modeling](https://mlsanity.com/paper/2111.09886/) (2021)
- [The "something something" video database for learning and evaluating visual common sense](https://mlsanity.com/paper/1706.04261/) (2017)
- [Multiscale Vision Transformers](https://mlsanity.com/paper/2104.11227/) (2021)
- [TSM: Temporal Shift Module for Efficient Video Understanding](https://mlsanity.com/paper/1811.08383/) (2018)
- [AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition](https://mlsanity.com/paper/2205.13535/) (2022)
- [Masked Feature Prediction for Self-Supervised Visual Pre-Training](https://mlsanity.com/paper/2112.09133/) (2021)
- [VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking](https://mlsanity.com/paper/2303.16727/) (2023)
- [InternVideo: General Video Foundation Models via Generative and Discriminative Learning](https://mlsanity.com/paper/2212.03191/) (2022)
- [Spatiotemporal Contrastive Video Representation Learning](https://mlsanity.com/paper/2008.03800/) (2020)
- [Video Action Transformer Network](https://mlsanity.com/paper/1812.02707/) (2018)
- [Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles](https://mlsanity.com/paper/2306.00989/) (2023)
- [Video Transformer Network](https://mlsanity.com/paper/2102.00719/) (2021)
- [Self-Supervised Learning by Cross-Modal Audio-Video Clustering](https://mlsanity.com/paper/1911.12667/) (2019)
- [Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers](https://mlsanity.com/paper/2106.05392/) (2021)
- [Deep Contextual Video Compression](https://mlsanity.com/paper/2109.15047/) (2021)
- [A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning](https://mlsanity.com/paper/2104.14558/) (2021)
- [UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning](https://mlsanity.com/paper/2201.04676/) (2022)
- [BEVT: BERT Pretraining of Video Transformers](https://mlsanity.com/paper/2112.01529/) (2021)
- [UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer](https://mlsanity.com/paper/2211.09552/) (2022)
- [Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning](https://mlsanity.com/paper/2212.04500/) (2022)
- [An Image is Worth 16x16 Words, What is a Video Worth?](https://mlsanity.com/paper/2103.13915/) (2021)

## Abstract (arXiv)

Recent developments in Transformers have achieved notable strides in enhancing video comprehension. Nonetheless, the O(N2) computation complexity associated with attention mechanisms presents substantial computational hurdles when dealing with the high dimensionality of videos. This challenge becomes particularly pronounced when striving to increase the frames per second (FPS) to enhance the motion capturing capabilities. Such a pursuit is likely to introduce redundancy and exacerbate the existing computational limitations. In this paper, we initiate by showcasing the enhanced performance achieved through an escalation in the FPS rate. Additionally, we present a novel approach, Motion Guided Token Compression (MGTC), to empower Transformer models to utilize a smaller yet more representative set of tokens for comprehensive video representation. Consequently, this yields substantial reductions in computational burden and remains seamlessly adaptable to increased FPS rates. Specifically, we draw inspiration from video compression algorithms and scrutinize the variance between patches in consecutive video frames across the temporal dimension. The tokens exhibiting a disparity below a predetermined threshold are then masked. Notably, this masking strategy effectively addresses video redundancy while conserving essential information. Our experiments, conducted on widely examined video recognition datasets, Kinetics-400, UCF101 and HMDB51, demonstrate that elevating the FPS rate results in a significant top-1 accuracy score improvement of over 1.6, 1.6 and 4.0. By implementing MGTC with the masking ratio of 25%, we further augment accuracy by 0.1 and simultaneously reduce computational costs by over 31% on Kinetics-400. Even within a fixed computational budget, higher FPS rates paired with MGTC sustain performance gains when compared to lower FPS settings.