mlsanityData to 14 Oct 2026

TempT: Temporal consistency for Test-time adaptation

arXiv 2303.10536 ↗First posted 19 Mar 2023cs.CV cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

We introduce Temporal consistency for Test-time adaptation (TempT) a novel method for test-time adaptation on videos through the use of temporal coherence of predictions across sequential frames as a self-supervision signal. TempT is an approach with broad potential applications in computer vision tasks including facial expression recognition (FER) in videos. We evaluate TempT performance on the AffWild2 dataset. Our approach focuses solely on the unimodal visual aspect of the data and utilizes a popular 2D CNN backbone in contrast to larger sequential or attention-based models used in other approaches. Our preliminary experimental results demonstrate that TempT has competitive performance compared to the previous years reported performances and its efficacy provides a compelling proof-of-concept for its use in various real-world applications.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 31 of its 42 references that are in the map. First posted on arXiv 19 Mar 2023.

Builds on

31 of 42 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2017Squeeze-and-Excitation Networkscited by 4,789
  5. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,546
  6. 2017Decoupled Weight Decay Regularizationcited by 1,831
  7. 2021ViViT: A Video Vision Transformercited by 1,620
  8. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 989
  9. 2020Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptationcited by 848
  10. 2016Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networkscited by 543
  11. 2022Continual Test-Time Domain Adaptationcited by 525
  12. 2017AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wildcited by 492
19 more
  1. 2020Improving robustness against common corruptions by covariate shift adaptationcited by 431
  2. 2021MEMO: Test Time Robustness via Adaptation and Augmentationcited by 377
  3. 2016Revisiting Batch Normalization For Practical Domain Adaptationcited by 288
  4. 2019Expression, Affect, Action Unit Recognition: Aff-Wild2, Multi-Task Learning and ArcFacecited by 222
  5. 2018Deep Affect Prediction in-the-wild: Aff-Wild Database and Challenge, Deep Architectures, and Beyondcited by 216
  6. 2020Adaptive Risk Minimization: Learning to Adapt to Domain Shiftcited by 183
  7. 2020Analysing Affective Behavior in the First ABAW 2020 Competitioncited by 178
  8. 2021Affect Analysis in-the-wild: Valence-Arousal, Expressions, Action Units and a Unified Frameworkcited by 174
  9. 2021Distribution Matching for Heterogeneous Multi-Task Learning: a Large-scale Face Studycited by 168
  10. 2021Analysing Affective Behavior in the second ABAW2 Competitioncited by 163
  11. 2019Face Behavior a la carte: Expressions, Affect and Action Units in a Single Networkcited by 155
  12. 2022NOTE: Robust Continual Test-time Adaptation Against Temporal Correlationcited by 151
  13. 2019Robust Learning with Jacobian Regularizationcited by 129
  14. 2023ABAW: Valence-Arousal Estimation, Expression Recognition, Action Unit Detection & Emotional Reaction Intensity Estimation Challengescited by 110
  15. 2020Training BatchNorm and Only BatchNorm: On the Expressive Power of Random Features in CNNscited by 104
  16. 2021TransFER: Learning Relation-aware Facial Expression Representations with Transformerscited by 85
  17. 2015Modeling Spatial-Temporal Clues in a Hybrid Deep Learning Framework for Video Classificationcited by 21
  18. 2021Partial transfusion: on the expressive influence of trainable batch norm parameters for transfer learningcited by 15
  19. 2022Facial Affect Analysis: Learning from Synthetic Data & Multi-Task Learning Challengescited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 1; 2026: 1.

5 papers.

  1. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 359
  2. 2024The 6th Affective Behavior Analysis in-the-wild (ABAW) Competitioncited by 78
  3. 20247th ABAW Competition: Multi-Task Learning and Compound Expression Recognitioncited by 53
  4. 2025FIESTA: Fisher Information-based Efficient Selective Test-time Adaptationcited by 2
  5. 2026Fine-tuning a multimodal large language model for clinician-grade autism behavioral scoring from short home videoscited by 1