mlsanityData to 14 Oct 2026

Object-based (yet Class-agnostic) Video Domain Adaptation

arXiv 2311.17942 ↗First posted 29 Nov 2023cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Existing video-based action recognition systems typically require dense annotation and struggle in environments when there is significant distribution shift relative to the training data. Current methods for video domain adaptation typically fine-tune the model using fully annotated data on a subset of target domain data or align the representation of the two domains using bootstrapping or adversarial learning. Inspired by the pivotal role of objects in recent supervised object-centric action recognition models, we present Object-based (yet Class-agnostic) Video Domain Adaptation (ODAPT), a simple yet effective framework for adapting the existing action recognition systems to new domains by utilizing a sparse set of frames with class-agnostic object annotations in a target domain. Our model achieves a +6.5 increase when adapting across kitchens in Epic-Kitchens and a +3.1 increase adapting between Epic-Kitchens and the EGTEA dataset. ODAPT is a general framework that can also be combined with previous unsupervised methods, offering a +5.0 boost when combined with the self-supervised multi-modal method MMSADA and a +1.7 boost when added to the adversarial-based method TA3N on Epic-Kitchens.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 34 of its 47 references that are in the map. First posted on arXiv 29 Nov 2023.

Builds on

34 of 47 references.

References · 34

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2023Segment Anythingcited by 8,234
  3. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  4. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,270
  5. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  6. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  7. 2018SlowFast Networks for Video Recognitioncited by 1,867
  8. 2021Is Space-Time Attention All You Need for Video Understanding?cited by 1,620
  9. 2017Adversarial Discriminative Domain Adaptationcited by 1,311
  10. 2021Video Swin Transformercited by 1,091
  11. 2014Two-Stream Convolutional Networks for Action Recognition in Videoscited by 1,068
  12. 2021Multiscale Vision Transformerscited by 897
22 more
  1. 2018TSM: Temporal Shift Module for Efficient Video Understandingcited by 856
  2. 2018Scaling Egocentric Vision: The EPIC-KITCHENS Datasetcited by 795
  3. 2021MViTv2: Improved Multiscale Vision Transformers for Classification and Detectioncited by 519
  4. 2014Long-term Recurrent Convolutional Networks for Visual Recognition and Descriptioncited by 484
  5. 2018Domain Adaptive Faster R-CNN for Object Detection in the Wildcited by 443
  6. 2016Convolutional Two-Stream Network Fusion for Video Action Recognitioncited by 384
  7. 2020Understanding Human Hands in Contact at Internet Scalecited by 281
  8. 2017Temporal Segment Networks for Action Recognition in Videoscited by 279
  9. 2015Beyond Short Snippets: Deep Networks for Video Classificationcited by 233
  10. 2020The EPIC-KITCHENS Dataset: Collection, Challenges and Baselinescited by 225
  11. 2021Keeping Your Eye on the Ball: Trajectory Attention in Video Transformerscited by 224
  12. 2018Videos as Space-Time Region Graphscited by 221
  13. 2020Multi-Modal Domain Adaptation for Fine-Grained Action Recognitioncited by 115
  14. 2018Actor and Observer: Joint Modeling of First and Third-Person Videoscited by 103
  15. 2019Temporal Attentive Alignment for Large-Scale Video Domain Adaptationcited by 100
  16. 2016Long-term Temporal Convolutions for Action Recognitioncited by 84
  17. 2021Object-Region Video Transformerscited by 73
  18. 2019Adversarial Cross-Domain Action Recognition with Co-Attentioncited by 51
  19. 2021Contrast and Mix: Temporal Contrastive Video Domain Adaptation with Background Mixingcited by 49
  20. 2021Unified Graph Structured Models for Video Understandingcited by 38
  21. 2018Unsupervised Learning of View-invariant Action Representationscited by 32
  22. 2020Unsupervised Domain Adaptation for Spatio-Temporal Action Localizationcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Generalization Under Scrutiny: Cross-Domain Detection Progresses, Pitfalls, and Persistent Challengescited by 0