mlsanityData to 14 Oct 2026

Unsupervised Learning of Spatiotemporally Coherent Metrics

arXiv 1412.6056 ↗First posted 18 Dec 2014cs.CVcited by 46

Not on the map. Why?

Abstract (arXiv)

Current state-of-the-art classification and detection algorithms rely on supervised training. In this work we study unsupervised feature learning in the context of temporally coherent video data. We focus on feature learning from unlabeled video data, using the assumption that adjacent video frames contain semantically similar information. This assumption is exploited to train a convolutional pooling auto-encoder regularized by slowness and sparsity. We establish a connection between slow feature learning to metric learning and show that the trained encoder can be used to define a more temporally and semantically coherent metric.

Key facts. Cited by 46 papers in the map (data through 14 Oct 2026). First posted on arXiv 18 Dec 2014.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 16; 2022: 11; 2023: 9; 2024: 5; 2025: 4; 2026: 1.

46 papers.

Sort:

By area:

  1. 2021Masked Feature Prediction for Self-Supervised Visual Pre-Trainingcited by 576
  2. 2024Revisiting Feature Prediction for Learning Visual Representations from Videocited by 531
  3. 2022Masked Autoencoders As Spatiotemporal Learnerscited by 429
  4. 2021A Large-Scale Study on Unsupervised Spatiotemporal Representation Learningcited by 214
  5. 2021Towards Long-Form Video Understandingcited by 146
  6. 2024CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videoscited by 128
  7. 2024BootsTAP: Bootstrapped Training for Tracking-Any-Pointcited by 120
  8. 2021Rethinking Self-supervised Correspondence Learning: A Video Frame-level Similarity Perspectivecited by 81
  9. 2023Siamese Masked Autoencoderscited by 76
  10. 2023Diffusion Models as Masked Autoencoderscited by 71
  11. 2021Self-supervised Video Transformercited by 64
  12. 2021Unsupervised Action Segmentation by Joint Representation Learning and Online Clusteringcited by 49
34 more
  1. 2021Learning by Aligning Videos in Timecited by 48
  2. 2023Nonlinear Independent Component Analysis for Principled Disentanglement in Unsupervised Deep Learningcited by 48
  3. 2024DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor Controlcited by 44
  4. 2021Long-Short Temporal Contrastive Learning of Video Transformerscited by 42
  5. 2021ReSkin: versatile, replaceable, lasting tactile skinscited by 35
  6. 2021Noether Networks: Meta-Learning Useful Conserved Quantitiescited by 26
  7. 2021Learning to Align Sequential Actions in the Wildcited by 20
  8. 2022Self-supervised video pretraining yields robust and more human-aligned visual representationscited by 20
  9. 2021Contrastive Learning of Image Representations with Cross-Video Cycle-Consistencycited by 19
  10. 2021There Is No Turning Back: A Self-Supervised Approach for Reversibility-Aware Reinforcement Learningcited by 18
  11. 2022TempCLR: Temporal Alignment Representation with Contrastive Learningcited by 15
  12. 2023Temporal Coherent Test-Time Optimization for Robust Video Classificationcited by 15
  13. 2022MABe22: A Multi-Species Multi-Task Benchmark for Learned Representations of Behaviorcited by 12
  14. 2023HyRSM++: Hybrid Relation Guided Temporal Set Matching for Few-shot Action Recognitioncited by 12
  15. 2025Joint Self-Supervised Video Alignment and Action Segmentationcited by 11
  16. 2023Language-based Action Concept Spaces Improve Video Self-Supervised Learningcited by 10
  17. 2021Leveraging Time Irreversibility with Order-Contrastive Pre-trainingcited by 7
  18. 2022Palm up: Playing in the Latent Manifold for Unsupervised Pretrainingcited by 7
  19. 2021Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrastingcited by 6
  20. 2022Minimalistic Unsupervised Learning with the Sparse Manifold Transformcited by 6
  21. 2022ProtoX: Explaining a Reinforcement Learning Agent via Prototypingcited by 4
  22. 2025Procedure Learning via Regularized Gromov-Wasserstein Optimal Transportcited by 4
  23. 2022Extraneousness-Aware Imitation Learningcited by 3
  24. 2023Learning by Aligning 2D Skeleton Sequences and Multi-Modality Fusioncited by 3
  25. 2021PreViTS: Contrastive Pretraining with Video Tracking Supervisioncited by 2
  26. 2022Learning Muti-expert Distribution Calibration for Long-tailed Video Classificationcited by 2
  27. 2023DPPMask: Masked Image Modeling with Determinantal Point Processescited by 2
  28. 2022Case-Based Inverse Reinforcement Learning Using Temporal Coherencecited by 1
  29. 2023Learning to Summarize Videos by Contrasting Clipscited by 1
  30. 2022Temporal Alignment for History Representation in Reinforcement Learningcited by 0
  31. 2024DustNet: skillful neural network predictions of Saharan dustcited by 0
  32. 2025Reinforcement Learning meets Masked Video Modeling : Trajectory-Guided Adaptive Token Selectioncited by 0
  33. 2025VESSA: Video-based objEct-centric Self-Supervised Adaptation for Visual Foundation Modelscited by 0
  34. 2026T-JEPA: A Temporal Joint-Embedding Predictive Architecture for Learning Better Remote Sensing Representationscited by 0