# Motion Feature Network: Fixed Motion Filter for Action Recognition

arXiv: https://arxiv.org/abs/1807.10037 · HTML: https://mlsanity.com/paper/1807.10037/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jul 2018.

## Built on by (most cited first, 30 of 34)

- [VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text](https://mlsanity.com/paper/2104.11178/) (2021)
- [ACTION-Net: Multipath Excitation for Action Recognition](https://mlsanity.com/paper/2103.07372/) (2021)
- [Continuous Sign Language Recognition with Correlation Network](https://mlsanity.com/paper/2303.03202/) (2023)
- [E2(GO)MOTION: Motion Augmented Event Stream for Egocentric Action Recognition](https://mlsanity.com/paper/2112.03596/) (2021)
- [MGSampler: An Explainable Sampling Strategy for Video Action Recognition](https://mlsanity.com/paper/2104.09952/) (2021)
- [MoLo: Motion-augmented Long-short Contrastive Learning for Few-shot Action Recognition](https://mlsanity.com/paper/2304.00946/) (2023)
- [AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognition](https://mlsanity.com/paper/2105.05165/) (2021)
- [Domain Generalization through Audio-Visual Relative Norm Alignment in First Person Action Recognition](https://mlsanity.com/paper/2110.10101/) (2021)
- [Learning Self-Similarity in Space and Time as Generalized Motion for Video Action Recognition](https://mlsanity.com/paper/2102.07092/) (2021)
- [A Survey on Video Action Recognition in Sports: Datasets, Methods and Applications](https://mlsanity.com/paper/2206.01038/) (2022)
- [No Pain, Big Gain: Classify Dynamic Point Cloud Sequences with Static Models by Fitting Feature-level Space-time Surfaces](https://mlsanity.com/paper/2203.11113/) (2022)
- [Imposing Consistency for Optical Flow Estimation](https://mlsanity.com/paper/2204.07262/) (2022)
- [Prune Spatio-temporal Tokens by Semantic-aware Temporal Accumulation](https://mlsanity.com/paper/2308.04549/) (2023)
- [TSM: Temporal Shift Module for Efficient and Scalable Video Understanding on Edge Device](https://mlsanity.com/paper/2109.13227/) (2021)
- [Boosting Object Representation Learning via Motion and Object Continuity](https://mlsanity.com/paper/2211.09771/) (2022)
- [Relational Self-Attention: What's Missing in Attention for Video Understanding](https://mlsanity.com/paper/2111.01673/) (2021)
- [Gate-Shift-Fuse for Video Action Recognition](https://mlsanity.com/paper/2203.08897/) (2022)
- [Deformable Video Transformer](https://mlsanity.com/paper/2203.16795/) (2022)
- [Attention in Attention: Modeling Context Correlation for Efficient Video Classification](https://mlsanity.com/paper/2204.09303/) (2022)
- [OCAI: Improving Optical Flow Estimation by Occlusion and Consistency Aware Interpolation](https://mlsanity.com/paper/2403.18092/) (2024)
- [FAR: Fourier Aerial Video Recognition](https://mlsanity.com/paper/2203.10694/) (2022)
- [Cross-Domain First Person Audio-Visual Action Recognition through Relative Norm Alignment](https://mlsanity.com/paper/2106.01689/) (2021)
- [Motion-driven Visual Tempo Learning for Video-based Action Recognition](https://mlsanity.com/paper/2202.12116/) (2022)
- [Modality Mixer for Multi-modal Action Recognition](https://mlsanity.com/paper/2208.11314/) (2022)
- [CorrNet+: Sign Language Recognition and Translation via Spatial-Temporal Correlation](https://mlsanity.com/paper/2404.11111/) (2024)
- [Differentiable Frequency-based Disentanglement for Aerial Video Action Recognition](https://mlsanity.com/paper/2209.09194/) (2022)
- [Motion Aware Self-Supervision for Generic Event Boundary Detection](https://mlsanity.com/paper/2210.05574/) (2022)
- [Continuous Sign Language Recognition Based on Motor attention mechanism and frame-level Self-distillation](https://mlsanity.com/paper/2402.19118/) (2024)
- [SciFlow: Empowering Lightweight Optical Flow Models with Self-Cleaning Iterations](https://mlsanity.com/paper/2404.08135/) (2024)
- [Efficient Action Recognition Using Confidence Distillation](https://mlsanity.com/paper/2109.02137/) (2021)

## Abstract (arXiv)

Spatio-temporal representations in frame sequences play an important role in the task of action recognition. Previously, a method of using optical flow as a temporal information in combination with a set of RGB images that contain spatial information has shown great performance enhancement in the action recognition tasks. However, it has an expensive computational cost and requires two-stream (RGB and optical flow) framework. In this paper, we propose MFNet (Motion Feature Network) containing motion blocks which make it possible to encode spatio-temporal information between adjacent frames in a unified network that can be trained end-to-end. The motion block can be attached to any existing CNN-based action recognition frameworks with only a small additional cost. We evaluated our network on two of the action recognition datasets (Jester and Something-Something) and achieved competitive performances for both datasets by training the networks from scratch.