# Learning Temporally Invariant and Localizable Features via Data Augmentation for Video Recognition

arXiv: https://arxiv.org/abs/2008.05721 · HTML: https://mlsanity.com/paper/2008.05721/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Aug 2020.

## Built on by (most cited first, 13 of 13)

- [Benchmarking the Robustness of Temporal Action Detection Models Against Temporal Corruptions](https://mlsanity.com/paper/2403.20254/) (2024)
- [VIPriors 1: Visual Inductive Priors for Data-Efficient Deep Learning Challenges](https://mlsanity.com/paper/2103.03768/) (2021)
- [Flow Snapshot Neurons in Action: Deep Neural Networks Generalize to Biological Motion Perception](https://mlsanity.com/paper/2405.16493/) (2024)
- [Improve Video Representation with Temporal Adversarial Augmentation](https://mlsanity.com/paper/2304.14601/) (2023)
- [MUG: Pseudo Labeling Augmented Audio-Visual Mamba Network for Audio-Visual Video Parsing](https://mlsanity.com/paper/2507.01384/) (2025)
- [Extending Temporal Data Augmentation for Video Action Recognition](https://mlsanity.com/paper/2211.04888/) (2022)
- [Selective Volume Mixup for Video Action Recognition](https://mlsanity.com/paper/2309.09534/) (2023)
- [The Role of Video Generation in Enhancing Data-Limited Action Understanding](https://mlsanity.com/paper/2505.19495/) (2025)
- [The Effects of Mixed Sample Data Augmentation are Class Dependent](https://mlsanity.com/paper/2307.09136/) (2023)
- [MomentMix Augmentation with Length-Aware DETR for Temporally Robust Moment Retrieval](https://mlsanity.com/paper/2412.20816/) (2024)
- [Workflow Augmentation of Video Data for Event Recognition with Time-Sensitive Neural Networks](https://mlsanity.com/paper/2109.15063/) (2021)
- [Test-Time Mixup Augmentation for Data and Class-Specific Uncertainty Estimation in Deep Learning Image Classification](https://mlsanity.com/paper/2212.00214/) (2022)
- [Data-Efficient Challenges in Visual Inductive Priors: A Retrospective](https://mlsanity.com/paper/2506.08612/) (2025)

## Abstract (arXiv)

Deep-Learning-based video recognition has shown promising improvements along with the development of large-scale datasets and spatiotemporal network architectures. In image recognition, learning spatially invariant features is a key factor in improving recognition performance and robustness. Data augmentation based on visual inductive priors, such as cropping, flipping, rotating, or photometric jittering, is a representative approach to achieve these features. Recent state-of-the-art recognition solutions have relied on modern data augmentation strategies that exploit a mixture of augmentation operations. In this study, we extend these strategies to the temporal dimension for videos to learn temporally invariant or temporally localizable features to cover temporal perturbations or complex actions in videos. Based on our novel temporal data augmentation algorithms, video recognition performances are improved using only a limited amount of training data compared to the spatial-only data augmentation algorithms, including the 1st Visual Inductive Priors (VIPriors) for data-efficient action recognition challenge. Furthermore, learned features are temporally localizable that cannot be achieved using spatial augmentation algorithms. Our source code is available at https://github.com/taeoh-kim/temporal_data_augmentation.