# Gate-Shift-Fuse for Video Action Recognition

arXiv: https://arxiv.org/abs/2203.08897 · HTML: https://mlsanity.com/paper/2203.08897/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 67 of its 86 references that are in the map.
- First posted on arXiv 16 Mar 2022.

## Builds on (most cited first, 30 of 67)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [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)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [A Closer Look at Spatiotemporal Convolutions for Action Recognition](https://mlsanity.com/paper/1711.11248/) (2017)
- [The "something something" video database for learning and evaluating visual common sense](https://mlsanity.com/paper/1706.04261/) (2017)
- [Two-Stream Convolutional Networks for Action Recognition in Videos](https://mlsanity.com/paper/1406.2199/) (2014)
- [HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips](https://mlsanity.com/paper/1906.03327/) (2019)
- [Temporal Segment Networks: Towards Good Practices for Deep Action Recognition](https://mlsanity.com/paper/1608.00859/) (2016)
- [X3D: Expanding Architectures for Efficient Video Recognition](https://mlsanity.com/paper/2004.04730/) (2020)
- [Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?](https://mlsanity.com/paper/1711.09577/) (2017)
- [Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification](https://mlsanity.com/paper/1712.04851/) (2017)
- [Long-term Recurrent Convolutional Networks for Visual Recognition and Description](https://mlsanity.com/paper/1411.4389/) (2014)
- [Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks](https://mlsanity.com/paper/1711.10305/) (2017)
- [Convolutional Two-Stream Network Fusion for Video Action Recognition](https://mlsanity.com/paper/1604.06573/) (2016)
- [Temporal Relational Reasoning in Videos](https://mlsanity.com/paper/1711.08496/) (2017)
- [Video Classification with Channel-Separated Convolutional Networks](https://mlsanity.com/paper/1904.02811/) (2019)
- [Long-Term Feature Banks for Detailed Video Understanding](https://mlsanity.com/paper/1812.05038/) (2018)
- [Videos as Space-Time Region Graphs](https://mlsanity.com/paper/1806.01810/) (2018)
- [Moments in Time Dataset: one million videos for event understanding](https://mlsanity.com/paper/1801.03150/) (2018)
- [TEA: Temporal Excitation and Aggregation for Action Recognition](https://mlsanity.com/paper/2004.01398/) (2020)
- [Temporal Pyramid Network for Action Recognition](https://mlsanity.com/paper/2004.03548/) (2020)
- [STM: SpatioTemporal and Motion Encoding for Action Recognition](https://mlsanity.com/paper/1908.02486/) (2019)
- [MoViNets: Mobile Video Networks for Efficient Video Recognition](https://mlsanity.com/paper/2103.11511/) (2021)
- [AdaFrame: Adaptive Frame Selection for Fast Video Recognition](https://mlsanity.com/paper/1811.12432/) (2018)
- [SCSampler: Sampling Salient Clips from Video for Efficient Action Recognition](https://mlsanity.com/paper/1904.04289/) (2019)
- [Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustness](https://mlsanity.com/paper/2010.08001/) (2020)

## Built on by (most cited first, 15 of 15)

- [T-DEED: Temporal-Discriminability Enhancer Encoder-Decoder for Precise Event Spotting in Sports Videos](https://mlsanity.com/paper/2404.05392/) (2024)
- [CAST: Cross-Attention in Space and Time for Video Action Recognition](https://mlsanity.com/paper/2311.18825/) (2023)
- [Event Stream based Human Action Recognition: A High-Definition Benchmark Dataset and Algorithms](https://mlsanity.com/paper/2408.09764/) (2024)
- [Action Anticipation from SoccerNet Football Video Broadcasts](https://mlsanity.com/paper/2504.12021/) (2025)
- [SoccerNet 2024 Challenges Results](https://mlsanity.com/paper/2409.10587/) (2024)
- [Deep learning for action spotting in association football videos](https://mlsanity.com/paper/2410.01304/) (2024)
- [Gate-Shift-Pose: Enhancing Action Recognition in Sports with Skeleton Information](https://mlsanity.com/paper/2503.04470/) (2025)
- [AdaSpot: Spend Resolution Where It Matters for Precise Event Spotting](https://mlsanity.com/paper/2602.22073/) (2026)
- [Detecting Precise Hand Touch Moments in Egocentric Video](https://mlsanity.com/paper/2604.12343/) (2026)
- [FLAMES: A Hybrid Spiking-State Space Model for Adaptive Memory Retention in Event-Based Learning](https://mlsanity.com/paper/2504.01257/) (2025)
- [Multi-Focus Temporal Shifting for Precise Event Spotting in Sports Videos](https://mlsanity.com/paper/2507.07381/) (2025)
- [Your Image is My Video: Reshaping the Receptive Field via Image-To-Video Differentiable AutoAugmentation and Fusion](https://mlsanity.com/paper/2403.15194/) (2024)
- [Boosting Hyperspectral Image Classification with Gate-Shift-Fuse Mechanisms in a Novel CNN-Transformer Approach](https://mlsanity.com/paper/2406.14120/) (2024)
- [CA^2ST: Cross-Attention in Audio, Space, and Time for Holistic Video Recognition](https://mlsanity.com/paper/2503.23447/) (2025)
- [Towards Precise Action Spotting: Addressing Temporal Misalignment in Labels with Dynamic Label Assignment](https://mlsanity.com/paper/2504.00149/) (2025)

## Abstract (arXiv)

Convolutional Neural Networks are the de facto models for image recognition. However 3D CNNs, the straight forward extension of 2D CNNs for video recognition, have not achieved the same success on standard action recognition benchmarks. One of the main reasons for this reduced performance of 3D CNNs is the increased computational complexity requiring large scale annotated datasets to train them in scale. 3D kernel factorization approaches have been proposed to reduce the complexity of 3D CNNs. Existing kernel factorization approaches follow hand-designed and hard-wired techniques. In this paper we propose Gate-Shift-Fuse (GSF), a novel spatio-temporal feature extraction module which controls interactions in spatio-temporal decomposition and learns to adaptively route features through time and combine them in a data dependent manner. GSF leverages grouped spatial gating to decompose input tensor and channel weighting to fuse the decomposed tensors. GSF can be inserted into existing 2D CNNs to convert them into an efficient and high performing spatio-temporal feature extractor, with negligible parameter and compute overhead. We perform an extensive analysis of GSF using two popular 2D CNN families and achieve state-of-the-art or competitive performance on five standard action recognition benchmarks.