mlsanityData to 13 Oct 2026

Uncertainty-Guided Appearance-Motion Association Network for Out-of-Distribution Action Detection

arXiv 2409.09953 ↗First posted 16 Sep 2024cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

Out-of-distribution (OOD) detection targets to detect and reject test samples with semantic shifts, to prevent models trained on in-distribution (ID) dataset from producing unreliable predictions. Existing works only extract the appearance features on image datasets, and cannot handle dynamic multimedia scenarios with much motion information. Therefore, we target a more realistic and challenging OOD detection task: OOD action detection (ODAD). Given an untrimmed video, ODAD first classifies the ID actions and recognizes the OOD actions, and then localizes ID and OOD actions. To this end, in this paper, we propose a novel Uncertainty-Guided Appearance-Motion Association Network (UAAN), which explores both appearance features and motion contexts to reason spatial-temporal inter-object interaction for ODAD.Firstly, we design separate appearance and motion branches to extract corresponding appearance-oriented and motion-aspect object representations. In each branch, we construct a spatial-temporal graph to reason appearance-guided and motion-driven inter-object interaction. Then, we design an appearance-motion attention module to fuse the appearance and motion features for final action detection. Experimental results on two challenging datasets show that UAAN beats state-of-the-art methods by a significant margin, illustrating its effectiveness.

Key facts. Cited by 12 papers in the map (data through 13 Oct 2026). Builds on 60 of its 146 references that are in the map. First posted on arXiv 16 Sep 2024.

Builds on

60 of 146 references.

References · 60

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,950
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,625
  3. 2017Mask R-CNNcited by 7,266
  4. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,264
  5. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,371
  6. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,475
  7. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,327
  8. 2020Energy-based Out-of-distribution Detectioncited by 1,297
  9. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 729
  10. 2016Training Region-based Object Detectors with Online Hard Example Miningcited by 578
  11. 2015Towards Open Set Deep Networkscited by 535
  12. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
38 more
  1. 2019Distance-IoU Loss: Faster and Better Learning for Bounding Box Regressioncited by 455
  2. 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
  3. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 405
  4. 2017Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samplescited by 389
  5. 2018Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptationcited by 295
  6. 2017Temporal Action Detection with Structured Segment Networkscited by 265
  7. 2018Human Action Recognition and Prediction: A Surveycited by 226
  8. 2020Why Normalizing Flows Fail to Detect Out-of-Distribution Datacited by 220
  9. 2019Input complexity and out-of-distribution detection with likelihood-based generative modelscited by 186
  10. 2021Learning Salient Boundary Feature for Anchor-free Temporal Action Localizationcited by 156
  11. 2021End-to-end Temporal Action Detection with Transformercited by 150
  12. 2019Deep Learning on Image Denoising: An overviewcited by 128
  13. 2022How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?cited by 128
  14. 2018Out-of-Distribution Detection Using an Ensemble of Self Supervised Leave-out Classifierscited by 126
  15. 2017Single Shot Temporal Action Detectioncited by 123
  16. 2018A Systematic DNN Weight Pruning Framework using Alternating Direction Method of Multiplierscited by 120
  17. 2019Unsupervised Out-of-Distribution Detection by Maximum Classifier Discrepancycited by 112
  18. 2022Retrieval Augmented Classification for Long-Tail Visual Recognitioncited by 106
  19. 2015End-to-end Learning of Action Detection from Frame Glimpses in Videoscited by 101
  20. 2021Evidential Deep Learning for Open Set Action Recognitioncited by 96
  21. 2022Fusing Global and Local Features for Generalized AI-Synthesized Image Detectioncited by 88
  22. 2016Online Action Detectioncited by 69
  23. 2022Rethinking Reconstruction Autoencoder-Based Out-of-Distribution Detectioncited by 59
  24. 2016Going Deeper into Action Recognition: A Surveycited by 55
  25. 2022Learning for Vehicle-to-Vehicle Cooperative Perception under Lossy Communicationcited by 47
  26. 2022Multi-Modal Cross-Domain Alignment Network for Video Moment Retrievalcited by 43
  27. 2022Domain Adaptive Object Detection for Autonomous Driving under Foggy Weathercited by 41
  28. 2023You Can Ground Earlier than See: An Effective and Efficient Pipeline for Temporal Sentence Grounding in Compressed Videoscited by 41
  29. 2023AI-Synthesized Voice Detection Using Neural Vocoder Artifactscited by 41
  30. 2022An Empirical Study of End-to-End Temporal Action Detectioncited by 40
  31. 2022Hierarchical Local-Global Transformer for Temporal Sentence Groundingcited by 38
  32. 2017On the Compactness, Efficiency, and Representation of 3D Convolutional Networks: Brain Parcellation as a Pretext Taskcited by 36
  33. 2022Exploring Optical-Flow-Guided Motion and Detection-Based Appearance for Temporal Sentence Groundingcited by 35
  34. 2020Unbalanced Incomplete Multi-view Clustering via the Scheme of View Evolution: Weak Views are Meat; Strong Views do Eatcited by 30
  35. 2020ANIMC: A Soft Framework for Auto-weighted Noisy and Incomplete Multi-view Clusteringcited by 30
  36. 2018Hierarchical Novelty Detection for Visual Object Recognitioncited by 26
  37. 2023Open Set Action Recognition via Multi-Label Evidential Learningcited by 26
  38. 2023Hypotheses Tree Building for One-Shot Temporal Sentence Localizationcited by 25

50 most cited of 60 All 60 (JSON)

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2024: 1; 2025: 4; 2026: 7.

12 papers.

  1. 2024Multi-Pair Temporal Sentence Grounding via Multi-Thread Knowledge Transfer Networkcited by 15
  2. 2025Taylor Series-Inspired Local Structure Fitting Network for Few-shot Point Cloud Semantic Segmentationcited by 14
  3. 2025Adaptive Multi-prompt Contrastive Network for Few-shot Out-of-distribution Detectioncited by 8
  4. 2026Rethinking Weakly-supervised Video Temporal Grounding From a Game Perspectivecited by 8
  5. 2026Not All Inputs Are Valid: Towards Open-Set Video Moment Retrieval Using Languagecited by 6
  6. 2025SciEducator: Scientific Video Understanding and Educating via Deming-Cycle Multi-Agent Systemcited by 4
  7. 2026Immuno-VLM: Immunizing Large Vision-Language Models via Generative Semantic Antibodies for Open-World Trustworthinesscited by 2
  8. 2026Curiosity Driven Knowledge Retrieval for Mobile Agentscited by 1
  9. 2026Hierarchical Semantic-Augmented Navigation: Optimal Transport and Graph-Driven Reasoning for Vision-Language Navigationcited by 1
  10. 2025Learning from Few Samples: A Novel Approach for High-Quality Malcode Generationcited by 0
  11. 2026Optimal Transport-Induced Samples against Out-of-Distribution Overconfidencecited by 0
  12. 2026Turing Patterns for Multimedia: Reaction-Diffusion Multi-Modal Fusion for Language-Guided Video Moment Retrievalcited by 0