mlsanityData to 14 Oct 2026

Dual Guidance Semi-Supervised Action Detection

arXiv 2507.21247 ↗First posted 28 Jul 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Semi-Supervised Learning (SSL) has shown tremendous potential to improve the predictive performance of deep learning models when annotations are hard to obtain. However, the application of SSL has so far been mainly studied in the context of image classification. In this work, we present a semi-supervised approach for spatial-temporal action localization. We introduce a dual guidance network to select better pseudo-bounding boxes. It combines a frame-level classification with a bounding-box prediction to enforce action class consistency across frames and boxes. Our evaluation across well-known spatial-temporal action localization datasets, namely UCF101-24 , J-HMDB-21 and AVA shows that the proposed module considerably enhances the model's performance in limited labeled data settings. Our framework achieves superior results compared to extended image-based semi-supervised baselines.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 45 of its 61 references that are in the map. First posted on arXiv 28 Jul 2025.

Builds on

45 of 61 references.

References · 45

  1. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  2. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  3. 2015Fast R-CNNcited by 2,933
  4. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  5. 2018SlowFast Networks for Video Recognitioncited by 1,867
  6. 2016YOLO9000: Better, Faster, Strongercited by 1,431
  7. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,391
  8. 2014Two-Stream Convolutional Networks for Action Recognition in Videoscited by 1,068
  9. 2018TSM: Temporal Shift Module for Efficient Video Understandingcited by 856
  10. 2017AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actionscited by 449
  11. 2019S4L: Self-Supervised Semi-Supervised Learningcited by 335
  12. 2018Video Action Transformer Networkcited by 316
33 more
  1. 2021End-to-End Semi-Supervised Object Detection with Soft Teachercited by 316
  2. 2021Unbiased Teacher for Semi-Supervised Object Detectioncited by 306
  3. 2020A Simple Semi-Supervised Learning Framework for Object Detectioncited by 282
  4. 2017Temporal Segment Networks for Action Recognition in Videoscited by 279
  5. 2017Temporal Action Detection with Structured Segment Networkscited by 267
  6. 2017Data Distillation: Towards Omni-Supervised Learningcited by 126
  7. 2021Humble Teachers Teach Better Students for Semi-Supervised Object Detectioncited by 116
  8. 2021Instant-Teaching: An End-to-End Semi-Supervised Object Detection Frameworkcited by 113
  9. 2018Actor-Centric Relation Networkcited by 87
  10. 2017Action Tubelet Detector for Spatio-Temporal Action Localizationcited by 77
  11. 2016VideoLSTM Convolves, Attends and Flows for Action Recognitioncited by 60
  12. 2019You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localizationcited by 59
  13. 2016Online Real-time Multiple Spatiotemporal Action Localisation and Predictioncited by 57
  14. 2020Actions as Moving Pointscited by 55
  15. 2020Proposal Learning for Semi-Supervised Object Detectioncited by 55
  16. 2021TubeR: Tubelet Transformer for Video Action Detectioncited by 55
  17. 2019STEP: Spatio-Temporal Progressive Learning for Video Action Detectioncited by 51
  18. 2014Finding Action Tubescited by 50
  19. 2017Tube Convolutional Neural Network (T-CNN) for Action Detection in Videoscited by 50
  20. 2021Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detectioncited by 49
  21. 2015Learning to track for spatio-temporal action localizationcited by 44
  22. 2018A Structured Model For Action Detectioncited by 43
  23. 2019TACNet: Transition-Aware Context Network for Spatio-Temporal Action Detectioncited by 36
  24. 2016Deep Learning for Detecting Multiple Space-Time Action Tubes in Videoscited by 35
  25. 2017Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detectioncited by 34
  26. 2019Dance with Flow: Two-in-One Stream Action Detectioncited by 30
  27. 2021ST-HOI: A Spatial-Temporal Baseline for Human-Object Interaction Detection in Videoscited by 20
  28. 2021Motion-Augmented Self-Training for Video Recognition at Smaller Scalecited by 17
  29. 2016Actionness Estimation Using Hybrid Fully Convolutional Networkscited by 15
  30. 2021Object Priors for Classifying and Localizing Unseen Actionscited by 15
  31. 2018Guess Where? Actor-Supervision for Spatiotemporal Action Localizationcited by 8
  32. 2017Localizing Actions from Video Labels and Pseudo-Annotationscited by 6
  33. 2019Video action detection by learning graph-based spatio-temporal interactionscited by 4

Built on by

Not cited yet.