# Spatial-Temporal Alignment Network for Action Recognition

arXiv: https://arxiv.org/abs/2308.09897 · HTML: https://mlsanity.com/paper/2308.09897/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 45 references that are in the map.
- First posted on arXiv 19 Aug 2023.

## Builds on (most cited first, 28 of 28)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [A Closer Look at Spatiotemporal Convolutions for Action Recognition](https://mlsanity.com/paper/1711.11248/) (2017)
- [Two-Stream Convolutional Networks for Action Recognition in Videos](https://mlsanity.com/paper/1406.2199/) (2014)
- [Multiscale Vision Transformers](https://mlsanity.com/paper/2104.11227/) (2021)
- [MViTv2: Improved Multiscale Vision Transformers for Classification and Detection](https://mlsanity.com/paper/2112.01526/) (2021)
- [Videos as Space-Time Region Graphs](https://mlsanity.com/paper/1806.01810/) (2018)
- [Rethinking the Faster R-CNN Architecture for Temporal Action Localization](https://mlsanity.com/paper/1804.07667/) (2018)
- [Learning Human-Object Interactions by Graph Parsing Neural Networks](https://mlsanity.com/paper/1808.07962/) (2018)
- [R-C3D: Region Convolutional 3D Network for Temporal Activity Detection](https://mlsanity.com/paper/1703.07814/) (2017)
- [Graph-Based Global Reasoning Networks](https://mlsanity.com/paper/1811.12814/) (2018)
- [Spatiotemporal Residual Networks for Video Action Recognition](https://mlsanity.com/paper/1611.02155/) (2016)
- [Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization](https://mlsanity.com/paper/2006.07976/) (2020)
- [Stacked Capsule Autoencoders](https://mlsanity.com/paper/1906.06818/) (2019)
- [STEP: Spatio-Temporal Progressive Learning for Video Action Detection](https://mlsanity.com/paper/1904.09288/) (2019)
- [Tube Convolutional Neural Network (T-CNN) for Action Detection in Videos](https://mlsanity.com/paper/1703.10664/) (2017)
- [A Structured Model For Action Detection](https://mlsanity.com/paper/1812.03544/) (2018)
- [VideoCapsuleNet: A Simplified Network for Action Detection](https://mlsanity.com/paper/1805.08162/) (2018)
- [Inverse Compositional Spatial Transformer Networks](https://mlsanity.com/paper/1612.03897/) (2016)
- [Asynchronous Temporal Fields for Action Recognition](https://mlsanity.com/paper/1612.06371/) (2016)
- [Bag of Visual Words and Fusion Methods for Action Recognition: Comprehensive Study and Good Practice](https://mlsanity.com/paper/1405.4506/) (2014)
- [Multi-dataset Training of Transformers for Robust Action Recognition](https://mlsanity.com/paper/2209.12362/) (2022)
- [Spatial-Temporal Alignment Network for Action Recognition and Detection](https://mlsanity.com/paper/2012.02426/) (2020)

## Built on by (most cited first, 1 of 1)

- [GeoDeformer: Geometric Deformable Transformer for Action Recognition](https://mlsanity.com/paper/2311.17975/) (2023)

## Abstract (arXiv)

This paper studies introducing viewpoint invariant feature representations in existing action recognition architecture. Despite significant progress in action recognition, efficiently handling geometric variations in large-scale datasets remains challenging. To tackle this problem, we propose a novel Spatial-Temporal Alignment Network (STAN), which explicitly learns geometric invariant representations for action recognition. Notably, the STAN model is light-weighted and generic, which could be plugged into existing action recognition models (e.g., MViTv2) with a low extra computational cost. We test our STAN model on widely-used datasets like UCF101 and HMDB51. The experimental results show that the STAN model can consistently improve the state-of-the-art models in action recognition tasks in trained-from-scratch settings.