Extending Temporal Data Augmentation for Video Action Recognition
Not on the map. Why?
Abstract (arXiv)
Pixel space augmentation has grown in popularity in many Deep Learning areas, due to its effectiveness, simplicity, and low computational cost. Data augmentation for videos, however, still remains an under-explored research topic, as most works have been treating inputs as stacks of static images rather than temporally linked series of data. Recently, it has been shown that involving the time dimension when designing augmentations can be superior to its spatial-only variants for video action recognition. In this paper, we propose several novel enhancements to these techniques to strengthen the relationship between the spatial and temporal domains and achieve a deeper level of perturbations. The video action recognition results of our techniques outperform their respective variants in Top-1 and Top-5 settings on the UCF-101 and the HMDB-51 datasets.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 48 of its 69 references that are in the map. First posted on arXiv 9 Nov 2022.
Builds on
48 of 69 references.
References · 48
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
- 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
- 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
- 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
- 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
- 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
- 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
- 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
- 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
36 more
- 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
- 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
- 2018SlowFast Networks for Video Recognitioncited by 1,862
- 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
- 2017Accurate, Large Minibatch SGD: Training ImageNet in 1 Hourcited by 1,479
- 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
- 2017Adversarial Discriminative Domain Adaptationcited by 1,309
- 2017The "something something" video database for learning and evaluating visual common sensecited by 1,092
- 2014Two-Stream Convolutional Networks for Action Recognition in Videoscited by 1,067
- 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 918
- 2019Self-Supervised Learning of Pretext-Invariant Representationscited by 806
- 2018AutoAugment: Learning Augmentation Policies from Datacited by 728
- 2016Tutorial on Variational Autoencoderscited by 404
- 2016Convolutional Two-Stream Network Fusion for Video Action Recognitioncited by 384
- 2017Data Augmentation Generative Adversarial Networkscited by 278
- 2019Fast AutoAugmentcited by 243
- 2018GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classificationcited by 242
- 2018A DIRT-T Approach to Unsupervised Domain Adaptationcited by 215
- 2018Low-Shot Learning from Imaginary Datacited by 181
- 2019Population Based Augmentation: Efficient Learning of Augmentation Policy Schedulescited by 153
- 2020Feature Space Augmentation for Long-Tailed Datacited by 136
- 2017Dataset Augmentation in Feature Spacecited by 124
- 2018Data Augmentation by Pairing Samples for Images Classificationcited by 96
- 2016Long-term Temporal Convolutions for Action Recognitioncited by 84
- 2020Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Analysis and a New Strategycited by 66
- 2017Smart Augmentation - Learning an Optimal Data Augmentation Strategycited by 54
- 2017A Bayesian Data Augmentation Approach for Learning Deep Modelscited by 50
- 2018Improved Mixed-Example Data Augmentationcited by 42
- 2015Human Action Recognition using Factorized Spatio-Temporal Convolutional Networkscited by 40
- 2020Milking CowMask for Semi-Supervised Image Classificationcited by 35
- 2018Feature Space Transfer for Data Augmentationcited by 21
- 2019Virtual Mixup Training for Unsupervised Domain Adaptationcited by 21
- 2020Learning Temporally Invariant and Localizable Features via Data Augmentation for Video Recognitioncited by 13
- 2020Virtual Adversarial Training in Feature Space to Improve Unsupervised Video Domain Adaptationcited by 1
- 2021Spatio-temporal Data Augmentation for Visual Surveillancecited by 1
- 2021Improving Automated Sonar Video Analysis to Notify About Jellyfish Bloomscited by 1
Built on by
Citing papers per year: 2024: 2.
2 papers.