mlsanityData to 7 Oct 2026

Temporal Coherent Test-Time Optimization for Robust Video Classification

arXiv 2302.14309 ↗First posted 28 Feb 2023cs.CVcited by 15

Not on the map. Why?

Abstract (arXiv)

Deep neural networks are likely to fail when the test data is corrupted in real-world deployment (e.g., blur, weather, etc.). Test-time optimization is an effective way that adapts models to generalize to corrupted data during testing, which has been shown in the image domain. However, the techniques for improving video classification corruption robustness remain few. In this work, we propose a Temporal Coherent Test-time Optimization framework (TeCo) to utilize spatio-temporal information in test-time optimization for robust video classification. To exploit information in video with self-supervised learning, TeCo uses global content from video clips and optimizes models for entropy minimization. TeCo minimizes the entropy of the prediction based on the global content from video clips. Meanwhile, it also feeds local content to regularize the temporal coherence at the feature level. TeCo retains the generalization ability of various video classification models and achieves significant improvements in corruption robustness across Mini Kinetics-C and Mini SSV2-C. Furthermore, TeCo sets a new baseline in video classification corruption robustness via test-time optimization.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 50 of its 62 references that are in the map. First posted on arXiv 28 Feb 2023.

Builds on

50 of 62 references.

References · 50

  1. 2016Layer Normalizationcited by 5,579
  2. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  3. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  4. 2017Non-local Neural Networkscited by 2,290
  5. 2018SlowFast Networks for Video Recognitioncited by 1,862
  6. 2021Is Space-Time Attention All You Need for Video Understanding?cited by 1,609
  7. 2017The "something something" video database for learning and evaluating visual common sensecited by 1,092
  8. 2014Two-Stream Convolutional Networks for Action Recognition in Videoscited by 1,067
  9. 2016Temporal Segment Networks: Towards Good Practices for Deep Action Recognitioncited by 899
  10. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 897
  11. 2018Robustness May Be at Odds with Accuracycited by 873
  12. 2018TSM: Temporal Shift Module for Efficient Video Understandingcited by 852
38 more
  1. 2020Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptationcited by 844
  2. 2020X3D: Expanding Architectures for Efficient Video Recognitioncited by 635
  3. 2017Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classificationcited by 521
  4. 2022Continual Test-Time Domain Adaptationcited by 520
  5. 2021MViTv2: Improved Multiscale Vision Transformers for Classification and Detectioncited by 516
  6. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 511
  7. 2022Efficient Test-Time Model Adaptation without Forgettingcited by 467
  8. 2020Improving robustness against common corruptions by covariate shift adaptationcited by 427
  9. 2022Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Modelscited by 379
  10. 2019Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Comingcited by 332
  11. 2018Feature Denoising for Improving Adversarial Robustnesscited by 312
  12. 2017"Zero-Shot" Super-Resolution using Deep Internal Learningcited by 285
  13. 2019Learning Correspondence from the Cycle-Consistency of Timecited by 269
  14. 2018Generalisation in humans and deep neural networkscited by 237
  15. 2020TDN: Temporal Difference Networks for Efficient Action Recognitioncited by 183
  16. 2017Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognitioncited by 178
  17. 2016Improving the Robustness of Deep Neural Networks via Stability Trainingcited by 156
  18. 2019Temporal Cycle-Consistency Learningcited by 151
  19. 2021MoViNets: Mobile Video Networks for Efficient Video Recognitioncited by 135
  20. 2020Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularizationcited by 122
  21. 20223D Common Corruptions and Data Augmentationcited by 120
  22. 2019Benchmarking the Robustness of Semantic Segmentation Modelscited by 111
  23. 2020Heterogeneous Domain Generalization via Domain Mixupcited by 103
  24. 2019Temporal Attentive Alignment for Large-Scale Video Domain Adaptationcited by 100
  25. 2021AugMax: Adversarial Composition of Random Augmentations for Robust Trainingcited by 89
  26. 2018Sparse DNNs with Improved Adversarial Robustnesscited by 71
  27. 2019More Is Less: Learning Efficient Video Representations by Big-Little Network and Depthwise Temporal Aggregationcited by 64
  28. 2022Towards Robust Rain Removal Against Adversarial Attacks: A Comprehensive Benchmark Analysis and Beyondcited by 48
  29. 2014Unsupervised Learning of Spatiotemporally Coherent Metricscited by 45
  30. 2020Deep Analysis of CNN-based Spatio-temporal Representations for Action Recognitioncited by 45
  31. 2015Learning image representations tied to ego-motioncited by 41
  32. 2022Sparsity Winning Twice: Better Robust Generalization from More Efficient Trainingcited by 41
  33. 2021Benchmarking the Robustness of Spatial-Temporal Models Against Corruptionscited by 35
  34. 2017Comparing deep neural networks against humans: object recognition when the signal gets weakercited by 34
  35. 2020A simple way to make neural networks robust against diverse image corruptionscited by 30
  36. 2020Neural Networks with Recurrent Generative Feedbackcited by 23
  37. 2021Variational Disentanglement for Domain Generalizationcited by 18
  38. 2019Robustness Guarantees for Deep Neural Networks on Videoscited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 3; 2025: 4; 2026: 3.

15 papers.

Sort:

By area:

  1. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 353
  2. 2024Efficient Test-Time Adaptation of Vision-Language Modelscited by 138
  3. 2023Fast-Slow Test-Time Adaptation for Online Vision-and-Language Navigationcited by 25
  4. 2023Rapid Network Adaptation: Learning to Adapt Neural Networks Using Test-Time Feedbackcited by 10
  5. 2025JailDAM: Jailbreak Detection with Adaptive Memory for Vision-Language Modelcited by 10
  6. 2023Advancing Test-Time Adaptation in Wild Acoustic Test Settingscited by 7
  7. 2025Exploring Audio Cues for Enhanced Test-Time Video Model Adaptationcited by 3
  8. 2026Exposing and Defending the Achilles' Heel of Video Mixture-of-Expertscited by 3
  9. 2023Few Clicks Suffice: Active Test-Time Adaptation for Semantic Segmentationcited by 2
  10. 2024Enhanced Online Test-time Adaptation with Feature-Weight Cosine Alignmentcited by 1
  11. 2025Low-Cost Test-Time Adaptation for Robust Video Editingcited by 1
  12. 2026Do All Individual Layers Help? An Empirical Study of Task-Interfering Layers in Vision-Language Modelscited by 1
3 more
  1. 2024Adaptify: A Refined Adaptation Scheme for Frame Classification in Atrophic Gastritis Videoscited by 0
  2. 2025PAS: A Training-Free Stabilizer for Temporal Encoding in Video LLMscited by 0
  3. 2026Zero-Shot Temporal Action Localization Through Textual Guidancecited by 0