mlsanityData to 7 Oct 2026

Multiview Pseudo-Labeling for Semi-supervised Learning from Video

arXiv 2104.00682 ↗First posted 1 Apr 2021cs.CV cs.AI cs.LGcited by 32

Not on the map. Why?

Abstract (arXiv)

We present a multiview pseudo-labeling approach to video learning, a novel framework that uses complementary views in the form of appearance and motion information for semi-supervised learning in video. The complementary views help obtain more reliable pseudo-labels on unlabeled video, to learn stronger video representations than from purely supervised data. Though our method capitalizes on multiple views, it nonetheless trains a model that is shared across appearance and motion input and thus, by design, incurs no additional computation overhead at inference time. On multiple video recognition datasets, our method substantially outperforms its supervised counterpart, and compares favorably to previous work on standard benchmarks in self-supervised video representation learning.

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). Builds on 46 of its 68 references that are in the map. First posted on arXiv 1 Apr 2021.

Builds on

46 of 68 references.

References · 46

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  4. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  5. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  6. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  7. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  8. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  9. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  10. 2018SlowFast Networks for Video Recognitioncited by 1,862
  11. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  12. 2017Accurate, Large Minibatch SGD: Training ImageNet in 1 Hourcited by 1,479
34 more
  1. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
  2. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,304
  3. 2017A Closer Look at Spatiotemporal Convolutions for Action Recognitioncited by 1,139
  4. 2017The "something something" video database for learning and evaluating visual common sensecited by 1,092
  5. 2014Two-Stream Convolutional Networks for Action Recognition in Videoscited by 1,067
  6. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,057
  7. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,054
  8. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 918
  9. 2016Temporal Segment Networks: Towards Good Practices for Deep Action Recognitioncited by 899
  10. 2019Data-Efficient Image Recognition with Contrastive Predictive Codingcited by 672
  11. 2019End-to-End Learning of Visual Representations from Uncurated Instructional Videoscited by 506
  12. 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 470
  13. 2016Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learningcited by 441
  14. 2016Convolutional Two-Stream Network Fusion for Video Action Recognitioncited by 384
  15. 2020Spatiotemporal Contrastive Video Representation Learningcited by 372
  16. 2018A Short Note about Kinetics-600cited by 331
  17. 2019A Short Note on the Kinetics-700 Human Action Datasetcited by 308
  18. 2020ActBERT: Learning Global-Local Video-Text Representationscited by 267
  19. 2019Self-Supervised Learning by Cross-Modal Audio-Video Clusteringcited by 264
  20. 2018Cooperative Learning of Audio and Video Models from Self-Supervised Synchronizationcited by 246
  21. 2019Billion-scale semi-supervised learning for image classificationcited by 232
  22. 2020Self-supervised Co-training for Video Representation Learningcited by 232
  23. 2019EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognitioncited by 226
  24. 2020Audio-Visual Instance Discrimination with Cross-Modal Agreementcited by 192
  25. 2020SpeedNet: Learning the Speediness in Videoscited by 171
  26. 2020Audiovisual SlowFast Networks for Video Recognitioncited by 144
  27. 2020Multi-Modal Domain Adaptation for Fine-Grained Action Recognitioncited by 115
  28. 2020Labelling unlabelled videos from scratch with multi-modal self-supervisioncited by 99
  29. 2020A Short Note on the Kinetics-700-2020 Human Action Datasetcited by 89
  30. 2020Video Representation Learning with Visual Tempo Consistencycited by 57
  31. 2020VideoSSL: Semi-Supervised Learning for Video Classificationcited by 27
  32. 2019DistInit: Learning Video Representations Without a Single Labeled Videocited by 21
  33. 2018Semi-Supervised Convolutional Neural Networks for Human Activity Recognitioncited by 8
  34. 2016Much Ado About Time: Exhaustive Annotation of Temporal Datacited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 10; 2023: 8; 2024: 6; 2025: 3; 2026: 2.

32 papers.

Sort:

By area:

  1. 2022SVFormer: Semi-supervised Video Transformer for Action Recognitioncited by 67
  2. 2021Cross-Model Pseudo-Labeling for Semi-Supervised Action Recognitioncited by 29
  3. 2021Learning from Temporal Gradient for Semi-supervised Action Recognitioncited by 26
  4. 2021Multimodal Semi-Supervised Learning for 3D Objectscited by 24
  5. 2023Missing Modality Robustness in Semi-Supervised Multi-Modal Semantic Segmentationcited by 24
  6. 2022Transformer-CNN Cohort: Semi-supervised Semantic Segmentation by the Best of Both Studentscited by 16
  7. 2023TimeBalance: Temporally-Invariant and Temporally-Distinctive Video Representations for Semi-Supervised Action Recognitioncited by 16
  8. 2023DQS3D: Densely-matched Quantization-aware Semi-supervised 3D Detectioncited by 16
  9. 2022A Review of Speech-centric Trustworthy Machine Learning: Privacy, Safety, and Fairnesscited by 13
  10. 2023STEPs: Self-Supervised Key Step Extraction and Localization from Unlabeled Procedural Videoscited by 13
  11. 2022Semi-FedSER: Semi-supervised Learning for Speech Emotion Recognition On Federated Learning using Multiview Pseudo-Labelingcited by 12
  12. 2022Weakly-Supervised Online Action Segmentation in Multi-View Instructional Videoscited by 12
20 more
  1. 2022Cyclical Self-Supervision for Semi-Supervised Ejection Fraction Prediction from Echocardiogram Videoscited by 12
  2. 2023Decomposed Cross-modal Distillation for RGB-based Temporal Action Detectioncited by 12
  3. 2025STiL: Semi-supervised Tabular-Image Learning for Comprehensive Task-Relevant Information Exploration in Multimodal Classificationcited by 12
  4. 2024CLIP the Divergence: Language-guided Unsupervised Domain Adaptationcited by 5
  5. 2024Semi-Supervised Object Detection: A Survey on Progress from CNN to Transformercited by 4
  6. 2022Confident Sinkhorn Allocation for Pseudo-Labelingcited by 3
  7. 2024ActNetFormer: Transformer-ResNet Hybrid Method for Semi-Supervised Action Recognition in Videoscited by 3
  8. 2024FinePseudo: Improving Pseudo-Labelling through Temporal-Alignablity for Semi-Supervised Fine-Grained Action Recognitioncited by 3
  9. 2022Analyzing the factors affecting usefulness of Self-Supervised Pre-trained Representations for Speech Recognitioncited by 2
  10. 2022On the Surprising Effectiveness of Transformers in Low-Labeled Video Recognitioncited by 2
  11. 2023Multi-view knowledge distillation transformer for human action recognitioncited by 2
  12. 2024Learning Discriminative Spatio-temporal Representations for Semi-supervised Action Recognitioncited by 2
  13. 2023UTOPIA: Unconstrained Tracking Objects without Preliminary Examination via Cross-Domain Adaptationcited by 1
  14. 2023Egocentric RGB+Depth Action Recognition in Industry-Like Settingscited by 1
  15. 2024SITAR: Semi-supervised Image Transformer for Action Recognitioncited by 1
  16. 2022How Do You Do It? Fine-Grained Action Understanding with Pseudo-Adverbscited by 0
  17. 2025Semi-Supervised Audio-Visual Video Action Recognition with Audio Source Localization Guided Mixupcited by 0
  18. 2025Adapt, Agree, Aggregate: Semi-Supervised Ensemble Labeling for Graph Convolutional Networkscited by 0
  19. 2026LEViL: Label-Efficient Video Learning via Zero-Shot Distillation over VLM-Generated Pseudo-Label Spacescited by 0
  20. 2026Temporal Feature Distillation for Label-Efficient Precise Event Spotting in Sports Videoscited by 0