mlsanityData to 7 Oct 2026

AutoLabel: CLIP-based framework for Open-set Video Domain Adaptation

arXiv 2304.01110 ↗First posted 3 Apr 2023cs.CVcited by 18

Not on the map. Why?

Abstract (arXiv)

Open-set Unsupervised Video Domain Adaptation (OUVDA) deals with the task of adapting an action recognition model from a labelled source domain to an unlabelled target domain that contains "target-private" categories, which are present in the target but absent in the source. In this work we deviate from the prior work of training a specialized open-set classifier or weighted adversarial learning by proposing to use pre-trained Language and Vision Models (CLIP). The CLIP is well suited for OUVDA due to its rich representation and the zero-shot recognition capabilities. However, rejecting target-private instances with the CLIP's zero-shot protocol requires oracle knowledge about the target-private label names. To circumvent the impossibility of the knowledge of label names, we propose AutoLabel that automatically discovers and generates object-centric compositional candidate target-private class names. Despite its simplicity, we show that CLIP when equipped with AutoLabel can satisfactorily reject the target-private instances, thereby facilitating better alignment between the shared classes of the two domains. The code is available.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 37 of its 59 references that are in the map. First posted on arXiv 3 Apr 2023.

Builds on

37 of 59 references.

References · 37

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  6. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  7. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  8. 2021ViLT: Vision-and-Language Transformer Without Convolution or Region Supervisioncited by 1,224
  9. 2014Two-Stream Convolutional Networks for Action Recognition in Videoscited by 1,067
  10. 2016Temporal Segment Networks: Towards Good Practices for Deep Action Recognitioncited by 899
  11. 2018Scaling Egocentric Vision: The EPIC-KITCHENS Datasetcited by 789
  12. 2017Maximum Classifier Discrepancy for Unsupervised Domain Adaptationcited by 682
25 more
  1. 2016Deep Transfer Learning with Joint Adaptation Networkscited by 609
  2. 2021VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understandingcited by 596
  3. 2014Long-term Recurrent Convolutional Networks for Visual Recognition and Descriptioncited by 483
  4. 2016Convolutional Two-Stream Network Fusion for Video Action Recognitioncited by 384
  5. 2021ActionCLIP: A New Paradigm for Video Action Recognitioncited by 317
  6. 2018Video Action Transformer Networkcited by 316
  7. 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
  8. 2014Towards Open World Recognitioncited by 226
  9. 2018Human Action Recognition and Prediction: A Surveycited by 226
  10. 2017Unsupervised Representation Learning by Sorting Sequencescited by 219
  11. 2017Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognitioncited by 178
  12. 2021Zero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIPcited by 151
  13. 2018Open Set Domain Adaptation by Backpropagationcited by 150
  14. 2020Multi-Modal Domain Adaptation for Fine-Grained Action Recognitioncited by 115
  15. 2019Temporal Attentive Alignment for Large-Scale Video Domain Adaptationcited by 100
  16. 2021OVANet: One-vs-All Network for Universal Domain Adaptationcited by 92
  17. 2020A Comprehensive Study of Deep Video Action Recognitioncited by 87
  18. 2021Space-time Mixing Attention for Video Transformercited by 84
  19. 2017ActionVLAD: Learning spatio-temporal aggregation for action classificationcited by 73
  20. 2020On the Effectiveness of Image Rotation for Open Set Domain Adaptationcited by 72
  21. 2021Learning Cross-modal Contrastive Features for Video Domain Adaptationcited by 47
  22. 2019Open Set Domain Adaptation for Image and Action Recognitioncited by 30
  23. 2020Adversarial Bipartite Graph Learning for Video Domain Adaptationcited by 28
  24. 2021Conditional Extreme Value Theory for Open Set Video Domain Adaptationcited by 9
  25. 2016AdaScan: Adaptive Scan Pooling in Deep Convolutional Neural Networks for Human Action Recognition in Videoscited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 8; 2025: 5; 2026: 2.

18 papers.

Sort:

By area:

  1. 2024Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Surveycited by 36
  2. 2023EmoCLIP: A Vision-Language Method for Zero-Shot Video Facial Expression Recognitioncited by 31
  3. 2025Advances in Multimodal Adaptation and Generalization: From Traditional Approaches to Foundation Modelscited by 23
  4. 2025CLIP-Powered Domain Generalization and Domain Adaptation: A Comprehensive Surveycited by 15
  5. 2024MissionGNN: Hierarchical Multimodal GNN-based Weakly Supervised Video Anomaly Recognition with Mission-Specific Knowledge Graph Generationcited by 14
  6. 2024Open-Set Recognition in the Age of Vision-Language Modelscited by 13
  7. 2023LMC: Large Model Collaboration with Cross-assessment for Training-Free Open-Set Object Recognitioncited by 10
  8. 2024Recall and Refine: A Simple but Effective Source-free Open-set Domain Adaptation Frameworkcited by 6
  9. 2024Language-Guided Instance-Aware Domain-Adaptive Panoptic Segmentationcited by 4
  10. 2025Target Semantics Clustering via Text Representations for Robust Universal Domain Adaptationcited by 4
  11. 2025Preserving Clusters in Prompt Learning for Unsupervised Domain Adaptationcited by 4
  12. 2024Open-Set Video-based Facial Expression Recognition with Human Expression-sensitive Promptingcited by 3
6 more
  1. 2024ICON: Improving Inter-Report Consistency in Radiology Report Generation via Lesion-aware Mixup Augmentationcited by 2
  2. 2023Trustworthy Representation Learning Across Domainscited by 1
  3. 2024Continuous GNN-based Anomaly Detection on Edge using Efficient Adaptive Knowledge Graph Learningcited by 1
  4. 2025Training-Free Label Space Alignment for Universal Domain Adaptationcited by 1
  5. 2026SemAlign: Language Guided Semi-supervised Domain Generalizationcited by 0
  6. 2026Return of Frustratingly Easy Unsupervised Video Domain Adaptationcited by 0