mlsanityData to 7 Oct 2026

ObjectMix: Data Augmentation by Copy-Pasting Objects in Videos for Action Recognition

arXiv 2204.00239 ↗First posted 1 Apr 2022cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose a data augmentation method for action recognition using instance segmentation. Although many data augmentation methods have been proposed for image recognition, few of them are tailored for action recognition. Our proposed method, ObjectMix, extracts each object region from two videos using instance segmentation and combines them to create new videos. Experiments on two action recognition datasets, UCF101 and HMDB51, demonstrate the effectiveness of the proposed method and show its superiority over VideoMix, a prior work.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 32 of its 47 references that are in the map. First posted on arXiv 1 Apr 2022.

Builds on

32 of 47 references.

References · 32

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  3. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  4. 2017Non-local Neural Networkscited by 2,290
  5. 2017The Kinetics Human Action Video Datasetcited by 1,894
  6. 2018SlowFast Networks for Video Recognitioncited by 1,862
  7. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  8. 2022VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Trainingcited by 1,305
  9. 2017The "something something" video database for learning and evaluating visual common sensecited by 1,092
  10. 2014Two-Stream Convolutional Networks for Action Recognition in Videoscited by 1,067
  11. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,054
  12. 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 878
20 more
  1. 2020X3D: Expanding Architectures for Efficient Video Recognitioncited by 635
  2. 2020Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentationcited by 595
  3. 2018Albumentations: fast and flexible image augmentationscited by 558
  4. 2017Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?cited by 551
  5. 2017MoCoGAN: Decomposing Motion and Content for Video Generationcited by 523
  6. 2020Spatiotemporal Contrastive Video Representation Learningcited by 372
  7. 2017Learning from Synthetic Humanscited by 358
  8. 2021Self-Supervised Learning with Data Augmentations Provably Isolates Content from Stylecited by 308
  9. 2019Kornia: an Open Source Differentiable Computer Vision Library for PyTorchcited by 231
  10. 2021A Large-Scale Study on Unsupervised Spatiotemporal Representation Learningcited by 214
  11. 2017Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detectioncited by 209
  12. 2021A Good Image Generator Is What You Need for High-Resolution Video Synthesiscited by 162
  13. 2021Image-to-Image Translation: Methods and Applicationscited by 116
  14. 2020Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Analysis and a New Strategycited by 66
  15. 2020Removing the Background by Adding the Background: Towards Background Robust Self-supervised Video Representation Learningcited by 66
  16. 2020VideoMix: Rethinking Data Augmentation for Video Classificationcited by 55
  17. 2021Self-supervised Video Representation Learning by Context and Motion Decouplingcited by 34
  18. 2021CutDepth:Edge-aware Data Augmentation in Depth Estimationcited by 14
  19. 2020Video Action Understandingcited by 13
  20. 2021SA-GAN: Structure-Aware GAN for Organ-Preserving Synthetic CT Generationcited by 5

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 1; 2024: 1; 2025: 3.

7 papers.

  1. 2022Mitigating and Evaluating Static Bias of Action Representations in the Background and the Foregroundcited by 26
  2. 2025Can masking background and object reduce static bias for zero-shot action recognition?cited by 6
  3. 2023S3Aug: Segmentation, Sampling, and Shift for Action Recognitioncited by 3
  4. 2024Don't Judge by the Look: Towards Motion Coherent Video Representationcited by 2
  5. 2022Context-Matched Collage Generation for Underwater Invertebrate Detectioncited by 0
  6. 2025MoExDA: Domain Adaptation for Edge-based Action Recognitioncited by 0
  7. 2025Disentangling Static and Dynamic Information for Reducing Static Bias in Action Recognitioncited by 0