# Spatial-Temporal Alignment Network for Action Recognition and Detection

Source: [Spatial-Temporal Alignment Network for Action Recognition and Detection](<https://www.sota2.com/research/paper/68fa68de1e209131cea1ed14>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:47:52.778Z

Authors: Junwei Liang, Liangliang Cao, Xuehan Xiong, Ting Yu, Alexander Hauptmann

Published: 2020-12-04T06:23:40.000Z

## Abstract

This paper studies how to introduce viewpoint-invariant feature representations that can help action recognition and detection. Although we have witnessed great progress of action recognition in the past decade, it remains challenging yet interesting how to efficiently model the geometric variations in large scale datasets. This paper proposes a novel Spatial-Temporal Alignment Network (STAN) that aims to learn geometric invariant representations for action recognition and action detection. The STAN model is very light-weighted and generic, which could be plugged into existing action recognition models like ResNet3D and the SlowFast with a very low extra computational cost. We test our STAN model extensively on AVA, Kinetics-400, AVA-Kinetics, Charades, and Charades-Ego datasets. The experimental results show that the STAN model can consistently improve the state of the arts in both action detection and action recognition tasks. We will release our data, models and code.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2012.02426>)

[PDF](<https://arxiv.org/pdf/2012.02426.pdf>)