mlsanityData to 13 Oct 2026

Evidential Deep Learning for Open Set Action Recognition

arXiv 2107.10161 ↗First posted 21 Jul 2021cs.CVcited by 96

Not on the map. Why?

Abstract (arXiv)

In a real-world scenario, human actions are typically out of the distribution from training data, which requires a model to both recognize the known actions and reject the unknown. Different from image data, video actions are more challenging to be recognized in an open-set setting due to the uncertain temporal dynamics and static bias of human actions. In this paper, we propose a Deep Evidential Action Recognition (DEAR) method to recognize actions in an open testing set. Specifically, we formulate the action recognition problem from the evidential deep learning (EDL) perspective and propose a novel model calibration method to regularize the EDL training. Besides, to mitigate the static bias of video representation, we propose a plug-and-play module to debias the learned representation through contrastive learning. Experimental results show that our DEAR method achieves consistent performance gain on multiple mainstream action recognition models and benchmarks. Code and pre-trained models are available at smallurlhttps://www.rit.edu/actionlab/dear.

Key facts. Cited by 96 papers in the map (data through 13 Oct 2026). Builds on 37 of its 67 references that are in the map. First posted on arXiv 21 Jul 2021.

Builds on

37 of 67 references.

References · 37

  1. 2017On Calibration of Modern Neural Networkscited by 4,902
  2. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,264
  3. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,340
  4. 2018SlowFast Networks for Video Recognitioncited by 1,864
  5. 2018TSM: Temporal Shift Module for Efficient Video Understandingcited by 853
  6. 2017SphereFace: Deep Hypersphere Embedding for Face Recognitioncited by 735
  7. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 729
  8. 2018Predictive Uncertainty Estimation via Prior Networkscited by 555
  9. 2015Towards Open Set Deep Networkscited by 535
  10. 2019Deep Evidential Regressioncited by 355
  11. 2020Calibrating Deep Neural Networks using Focal Losscited by 353
  12. 2018Recent Advances in Open Set Recognition: A Surveycited by 310
25 more
  1. 2018Learning Not to Learn: Training Deep Neural Networks with Biased Datacited by 255
  2. 2014Towards Open World Recognitioncited by 226
  3. 2018Human Action Recognition and Prediction: A Surveycited by 226
  4. 2019Learning De-biased Representations with Biased Representationscited by 199
  5. 2020Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Countscited by 164
  6. 2020Temporal Pyramid Network for Action Recognitioncited by 163
  7. 2017Generative OpenMax for Multi-Class Open Set Classificationcited by 157
  8. 2018Evaluating Bayesian Deep Learning Methods for Semantic Segmentationcited by 143
  9. 2019C2AE: Class Conditioned Auto-Encoder for Open-set Recognitioncited by 142
  10. 2020Improving model calibration with accuracy versus uncertainty optimizationcited by 123
  11. 2019Why Can't I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognitioncited by 117
  12. 2020Learning Open Set Network with Discriminative Reciprocal Pointscited by 115
  13. 2020Conditional Gaussian Distribution Learning for Open Set Recognitioncited by 104
  14. 2020Uncertainty-based Traffic Accident Anticipation with Spatio-Temporal Relational Learningcited by 91
  15. 2019Out-of-Distribution Detection for Generalized Zero-Shot Action Recognitioncited by 54
  16. 2020Uncertainty-Aware Deep Classifiers using Generative Modelscited by 41
  17. 2018Open-world Learning and Application to Product Classificationcited by 39
  18. 2019Multi-Moments in Time: Learning and Interpreting Models for Multi-Action Video Understandingcited by 37
  19. 2019Uncertainty Estimation in One-Stage Object Detectioncited by 36
  20. 2019Specifying Weight Priors in Bayesian Deep Neural Networks with Empirical Bayescited by 32
  21. 2019Mimetics: Towards Understanding Human Actions Out of Contextcited by 32
  22. 2019Open Set Domain Adaptation for Image and Action Recognitioncited by 30
  23. 2019Quantifying Classification Uncertainty using Regularized Evidential Neural Networkscited by 13
  24. 2019ODN: Opening the Deep Network for Open-set Action Recognitioncited by 10
  25. 2018BAR: Bayesian Activity Recognition using variational inferencecited by 9

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 2; 2022: 14; 2023: 32; 2024: 19; 2025: 19; 2026: 10.

96 papers.

Sort:

By area:

  1. 2022InternVideo: General Video Foundation Models via Generative and Discriminative Learningcited by 446
  2. 2022Trusted Multi-View Classification with Dynamic Evidential Fusioncited by 167
  3. 2022Is Out-of-Distribution Detection Learnable?cited by 109
  4. 2021UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detectioncited by 92
  5. 2023A Survey on Uncertainty Quantification Methods for Deep Learningcited by 79
  6. 2021Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimationcited by 71
  7. 2023Nearest Neighbor Guidance for Out-of-Distribution Detectioncited by 64
  8. 2023Uncertainty Estimation by Fisher Information-based Evidential Deep Learningcited by 58
  9. 2024Benchmarking Micro-action Recognition: Dataset, Methods, and Applicationscited by 48
  10. 2023On Second-Order Scoring Rules for Epistemic Uncertainty Quantificationcited by 38
  11. 2024Is Epistemic Uncertainty Faithfully Represented by Evidential Deep Learning Methods?cited by 35
  12. 2023Learn to Accumulate Evidence from All Training Samples: Theory and Practicecited by 28
38 more
  1. 2022Towards Open Set Video Anomaly Detectioncited by 26
  2. 2023Open Set Action Recognition via Multi-Label Evidential Learningcited by 26
  3. 2024A Comprehensive Survey on Evidential Deep Learning and Its Applicationscited by 25
  4. 2022Causal Reasoning Meets Visual Representation Learning: A Prospective Studycited by 24
  5. 2022OpenTAL: Towards Open Set Temporal Action Localizationcited by 23
  6. 2023Dirichlet-based Uncertainty Calibration for Active Domain Adaptationcited by 23
  7. 2023Opening the Vocabulary of Egocentric Actionscited by 23
  8. 2024MADiff: Motion-Aware Mamba Diffusion Models for Hand Trajectory Prediction on Egocentric Videoscited by 17
  9. 2023The Devil is in the Wrongly-classified Samples: Towards Unified Open-set Recognitioncited by 16
  10. 2023EdVAE: Mitigating Codebook Collapse with Evidential Discrete Variational Autoencoderscited by 16
  11. 2023Evidential Active Recognition: Intelligent and Prudent Open-World Embodied Perceptioncited by 15
  12. 2024Revisiting Essential and Nonessential Settings of Evidential Deep Learningcited by 15
  13. 2023Evidential Detection and Tracking Collaboration: New Problem, Benchmark and Algorithm for Robust Anti-UAV Systemcited by 14
  14. 2023Evidential Uncertainty Quantification: A Variance-Based Perspectivecited by 14
  15. 2024Open-Set Recognition in the Age of Vision-Language Modelscited by 13
  16. 2023SOAR: Scene-debiasing Open-set Action Recognitioncited by 12
  17. 2024CREST: Cross-modal Resonance through Evidential Deep Learning for Enhanced Zero-Shot Learningcited by 12
  18. 2024Uncertainty-Guided Appearance-Motion Association Network for Out-of-Distribution Action Detectioncited by 12
  19. 2024Advancing Open-Set Domain Generalization Using Evidential Bi-Level Hardest Domain Schedulercited by 12
  20. 2023UMat: Uncertainty-Aware Single Image High Resolution Material Capturecited by 11
  21. 2023Continual Evidential Deep Learning for Out-of-Distribution Detectioncited by 11
  22. 2023EvCenterNet: Uncertainty Estimation for Object Detection using Evidential Learningcited by 10
  23. 2024Beyond Uncertainty: Evidential Deep Learning for Robust Video Temporal Groundingcited by 10
  24. 2023Uncertainty-guided Boundary Learning for Imbalanced Social Event Detectioncited by 8
  25. 2025H-MoRe: Learning Human-centric Motion Representation for Action Analysiscited by 8
  26. 2022ViT-ReT: Vision and Recurrent Transformer Neural Networks for Human Activity Recognition in Videoscited by 7
  27. 2024OSSAR: Towards Open-Set Surgical Activity Recognition in Robot-assisted Surgerycited by 7
  28. 2022Evidential Deep Learning for Class-Incremental Semantic Segmentationcited by 6
  29. 2023Flexible Visual Recognition by Evidential Modeling of Confusion and Ignorancecited by 6
  30. 2023Deep Learning Approaches for Seizure Video Analysis: A Reviewcited by 6
  31. 2024Mitigating Label Noise using Prompt-Based Hyperbolic Meta-Learning in Open-Set Domain Generalizationcited by 6
  32. 2025Uncertainty-aware Cross-training for Semi-supervised Medical Image Segmentationcited by 6
  33. 2025Procedural Mistake Detection via Action Effect Modelingcited by 6
  34. 2024Evidential Deep Partial Multi-View Classification With Discount Fusioncited by 5
  35. 2024Uncertainty Estimation for 3D Object Detection via Evidential Learningcited by 5
  36. 2025ALBAR: Adversarial Learning approach to mitigate Biases in Action Recognitioncited by 5
  37. 2023Toward Unsupervised Realistic Visual Question Answeringcited by 4
  38. 2022VLG: General Video Recognition with Web Textual Knowledgecited by 3

50 most cited of 96 All 96 (JSON)