mlsanityData to 14 Oct 2026

Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos

arXiv 1507.05738 ↗First posted 21 Jul 2015cs.CVcited by 93

Not on the map. Why?

Abstract (arXiv)

Every moment counts in action recognition. A comprehensive understanding of human activity in video requires labeling every frame according to the actions occurring, placing multiple labels densely over a video sequence. To study this problem we extend the existing THUMOS dataset and introduce MultiTHUMOS, a new dataset of dense labels over unconstrained internet videos. Modeling multiple, dense labels benefits from temporal relations within and across classes. We define a novel variant of long short-term memory (LSTM) deep networks for modeling these temporal relations via multiple input and output connections. We show that this model improves action labeling accuracy and further enables deeper understanding tasks ranging from structured retrieval to action prediction.

Key facts. Cited by 93 papers in the map (data through 14 Oct 2026). First posted on arXiv 21 Jul 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 25; 2022: 12; 2023: 25; 2024: 19; 2025: 7; 2026: 5.

93 papers.

Sort:

By area:

  1. 2021BABEL: Bodies, Action and Behavior with English Labelscited by 265
  2. 2021ASFormer: Transformer for Action Segmentationcited by 168
  3. 2022Self-Supervised Learning for Videos: A Surveycited by 85
  4. 2021MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actionscited by 84
  5. 2021OadTR: Online Action Detection with Transformerscited by 83
  6. 2021FineAction: A Fine-Grained Video Dataset for Temporal Action Localizationcited by 61
  7. 2024Language Repository for Long Video Understandingcited by 55
  8. 2021Spoken Moments: Learning Joint Audio-Visual Representations from Video Descriptionscited by 53
  9. 2023CaptainCook4D: A Dataset for Understanding Errors in Procedural Activitiescited by 51
  10. 2024Pixel-Wise Recognition for Holistic Surgical Scene Understandingcited by 49
  11. 2021Representation Learning via Global Temporal Alignment and Cycle-Consistencycited by 44
  12. 2021MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detectioncited by 42
38 more
  1. 2022Spotting Temporally Precise, Fine-Grained Events in Videocited by 40
  2. 2021JRDB-Act: A Large-scale Dataset for Spatio-temporal Action, Social Group and Activity Detectioncited by 39
  3. 2024360+x: A Panoptic Multi-modal Scene Understanding Datasetcited by 35
  4. 2021Modeling Multi-Label Action Dependencies for Temporal Action Localizationcited by 32
  5. 2021Learning an Augmented RGB Representation with Cross-Modal Knowledge Distillation for Action Detectioncited by 32
  6. 2021Deep Learning-based Action Detection in Untrimmed Videos: A Surveycited by 32
  7. 2025Temporal Preference Optimization for Long-Form Video Understandingcited by 29
  8. 2021Coarse-Fine Networks for Temporal Activity Detection in Videoscited by 28
  9. 2023TemporalMaxer: Maximize Temporal Context with only Max Pooling for Temporal Action Localizationcited by 28
  10. 2023VicTR: Video-conditioned Text Representations for Activity Recognitioncited by 28
  11. 2023Action Sensitivity Learning for Temporal Action Localizationcited by 28
  12. 2021Action Unit Memory Network for Weakly Supervised Temporal Action Localizationcited by 26
  13. 2022Token Turing Machinescited by 25
  14. 2022PointTAD: Multi-Label Temporal Action Detection with Learnable Query Pointscited by 22
  15. 2022Colar: Effective and Efficient Online Action Detection by Consulting Exemplarscited by 21
  16. 2024T-DEED: Temporal-Discriminability Enhancer Encoder-Decoder for Precise Event Spotting in Sports Videoscited by 21
  17. 2024Dual DETRs for Multi-Label Temporal Action Detectioncited by 20
  18. 2024MMAD: Multi-label Micro-Action Detection in Videoscited by 20
  19. 2021CTRN: Class-Temporal Relational Network for Action Detectioncited by 15
  20. 2021Coarse Temporal Attention Network (CTA-Net) for Driver's Activity Recognitioncited by 14
  21. 2022Learning Temporal Point Processes for Efficient Retrieval of Continuous Time Event Sequencescited by 14
  22. 2021Temporally smooth online action detection using cycle-consistent future anticipationcited by 13
  23. 2023Temporal Action Localization with Enhanced Instant Discriminabilitycited by 13
  24. 2022Video Action Detection: Analysing Limitations and Challengescited by 12
  25. 2023Action-slot: Visual Action-centric Representations for Multi-label Atomic Activity Recognition in Traffic Scenescited by 12
  26. 2022ProActive: Self-Attentive Temporal Point Process Flows for Activity Sequencescited by 11
  27. 2023A Survey of Deep Learning in Sports Applications: Perception, Comprehension, and Decisioncited by 11
  28. 2023A Survey on Deep Learning Techniques for Action Anticipationcited by 11
  29. 2021Sign Segmentation with Changepoint-Modulated Pseudo-Labellingcited by 10
  30. 2024Computer Vision for Primate Behavior Analysis in the Wildcited by 10
  31. 2025OpenTAD: A Unified Framework and Comprehensive Study of Temporal Action Detectioncited by 10
  32. 2024A Survey of Video Datasets for Grounded Event Understandingcited by 9
  33. 2024Human Action Anticipation: A Surveycited by 9
  34. 2023JOADAA: joint online action detection and action anticipationcited by 7
  35. 2021Learning to Discriminate Information for Online Action Detection: Analysis and Applicationcited by 6
  36. 2023PAT: Position-Aware Transformer for Dense Multi-Label Action Detectioncited by 6
  37. 2023Are current long-term video understanding datasets long-term?cited by 6
  38. 2024Action Selection Learning for Multi-label Multi-view Action Recognitioncited by 6

50 most cited of 93 All 93 (JSON)