# Unsupervised Domain Adaptation for Spatio-Temporal Action Localization

arXiv: https://arxiv.org/abs/2010.09211 · HTML: https://mlsanity.com/paper/2010.09211/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Oct 2020.

## Built on by (most cited first, 6 of 6)

- [Domain Generalization through Audio-Visual Relative Norm Alignment in First Person Action Recognition](https://mlsanity.com/paper/2110.10101/) (2021)
- [Domain Adaptation in Multi-View Embedding for Cross-Modal Video Retrieval](https://mlsanity.com/paper/2110.12812/) (2021)
- [Spatio-Temporal Context Prompting for Zero-Shot Action Detection](https://mlsanity.com/paper/2408.15996/) (2024)
- [Exploiting Instance-based Mixed Sampling via Auxiliary Source Domain Supervision for Domain-adaptive Action Detection](https://mlsanity.com/paper/2209.15439/) (2022)
- [Object-based (yet Class-agnostic) Video Domain Adaptation](https://mlsanity.com/paper/2311.17942/) (2023)
- [SADA: Semantic adversarial unsupervised domain adaptation for Temporal Action Localization](https://mlsanity.com/paper/2312.13377/) (2023)

## Abstract (arXiv)

Spatio-temporal action localization is an important problem in computer vision that involves detecting where and when activities occur, and therefore requires modeling of both spatial and temporal features. This problem is typically formulated in the context of supervised learning, where the learned classifiers operate on the premise that both training and test data are sampled from the same underlying distribution. However, this assumption does not hold when there is a significant domain shift, leading to poor generalization performance on the test data. To address this, we focus on the hard and novel task of generalizing training models to test samples without access to any labels from the latter for spatio-temporal action localization by proposing an end-to-end unsupervised domain adaptation algorithm. We extend the state-of-the-art object detection framework to localize and classify actions. In order to minimize the domain shift, three domain adaptation modules at image level (temporal and spatial) and instance level (temporal) are designed and integrated. We design a new experimental setup and evaluate the proposed method and different adaptation modules on the UCF-Sports, UCF-101 and JHMDB benchmark datasets. We show that significant performance gain can be achieved when spatial and temporal features are adapted separately, or jointly for the most effective results.