mlsanityData to 7 Oct 2026

S3Aug: Segmentation, Sampling, and Shift for Action Recognition

arXiv 2310.14556 ↗First posted 23 Oct 2023cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Action recognition is a well-established area of research in computer vision. In this paper, we propose S3Aug, a video data augmenatation for action recognition. Unlike conventional video data augmentation methods that involve cutting and pasting regions from two videos, the proposed method generates new videos from a single training video through segmentation and label-to-image transformation. Furthermore, the proposed method modifies certain categories of label images by sampling to generate a variety of videos, and shifts intermediate features to enhance the temporal coherency between frames of the generate videos. Experimental results on the UCF101, HMDB51, and Mimetics datasets demonstrate the effectiveness of the proposed method, paricularlly for out-of-context videos of the Mimetics dataset.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 39 of its 49 references that are in the map. First posted on arXiv 23 Oct 2023.

Builds on

39 of 49 references.

References · 39

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  6. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  7. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  8. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,338
  9. 2017Non-local Neural Networkscited by 2,290
  10. 2022Video Diffusion Modelscited by 2,280
  11. 2017The Kinetics Human Action Video Datasetcited by 1,894
  12. 2018SlowFast Networks for Video Recognitioncited by 1,862
27 more
  1. 2021ViViT: A Video Vision Transformercited by 1,610
  2. 2021Is Space-Time Attention All You Need for Video Understanding?cited by 1,609
  3. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  4. 2017The "something something" video database for learning and evaluating visual common sensecited by 1,092
  5. 2016COCO-Stuff: Thing and Stuff Classes in Contextcited by 858
  6. 2018TSM: Temporal Shift Module for Efficient Video Understandingcited by 852
  7. 2018Panoptic Segmentationcited by 796
  8. 2021VideoGPT: Video Generation using VQ-VAE and Transformerscited by 651
  9. 2020X3D: Expanding Architectures for Efficient Video Recognitioncited by 635
  10. 2020Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentationcited by 595
  11. 2023VideoMAE V2: Scaling Video Masked Autoencoders with Dual Maskingcited by 516
  12. 2018Video-to-Video Synthesiscited by 388
  13. 2023VideoFusion: Decomposed Diffusion Models for High-Quality Video Generationcited by 330
  14. 2018Generative Adversarial Network in Medical Imaging: A Reviewcited by 257
  15. 2018Human Action Recognition and Prediction: A Surveycited by 226
  16. 2020A Survey on Generative Adversarial Networks: Variants, Applications, and Trainingcited by 97
  17. 2021Token Shift Transformer for Video Classificationcited by 61
  18. 2020VideoMix: Rethinking Data Augmentation for Video Classificationcited by 55
  19. 2019Mimetics: Towards Understanding Human Actions Out of Contextcited by 32
  20. 2022When Shift Operation Meets Vision Transformer: An Extremely Simple Alternative to Attention Mechanismcited by 30
  21. 2022Learn2Augment: Learning to Composite Videos for Data Augmentation in Action Recognitioncited by 27
  22. 2022Vision Transformers for Action Recognition: A Surveycited by 25
  23. 2021Learning Representational Invariances for Data-Efficient Action Recognitioncited by 22
  24. 2016Human Action Recognition without Humancited by 17
  25. 2020Video Action Understandingcited by 13
  26. 2022ObjectMix: Data Augmentation by Copy-Pasting Objects in Videos for Action Recognitioncited by 7
  27. 2022Vision Transformer with Cross-attention by Temporal Shift for Efficient Action Recognitioncited by 5

Built on by

Cited by year

Citing papers per year: 2025: 3.

3 papers.

  1. 2025Can masking background and object reduce static bias for zero-shot action recognition?cited by 6
  2. 2025MoExDA: Domain Adaptation for Edge-based Action Recognitioncited by 0
  3. 2025Disentangling Static and Dynamic Information for Reducing Static Bias in Action Recognitioncited by 0