mlsanityData to 7 Oct 2026

Timeception for Complex Action Recognition

arXiv 1812.01289 ↗First posted 4 Dec 2018cs.CVcited by 89

Not on the map. Why?

Abstract (arXiv)

This paper focuses on the temporal aspect for recognizing human activities in videos; an important visual cue that has long been undervalued. We revisit the conventional definition of activity and restrict it to Complex Action: a set of one-actions with a weak temporal pattern that serves a specific purpose. Related works use spatiotemporal 3D convolutions with fixed kernel size, too rigid to capture the varieties in temporal extents of complex actions, and too short for long-range temporal modeling. In contrast, we use multi-scale temporal convolutions, and we reduce the complexity of 3D convolutions. The outcome is Timeception convolution layers, which reasons about minute-long temporal patterns, a factor of 8 longer than best related works. As a result, Timeception achieves impressive accuracy in recognizing the human activities of Charades, Breakfast Actions, and MultiTHUMOS. Further, we demonstrate that Timeception learns long-range temporal dependencies and tolerate temporal extents of complex actions.

Key facts. Cited by 89 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 24; 2022: 18; 2023: 15; 2024: 17; 2025: 13; 2026: 2.

89 papers.

Sort:

By area:

  1. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,530
  2. 2021Multiscale Vision Transformerscited by 896
  3. 2024VideoMamba: State Space Model for Efficient Video Understandingcited by 325
  4. 2021ActionCLIP: A New Paradigm for Video Action Recognitioncited by 317
  5. 2024MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understandingcited by 223
  6. 2022MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognitioncited by 189
  7. 2023A Simple LLM Framework for Long-Range Video Question-Answeringcited by 176
  8. 2021ASFormer: Transformer for Action Segmentationcited by 166
  9. 2021Towards Long-Form Video Understandingcited by 146
  10. 2024LongVLM: Efficient Long Video Understanding via Large Language Modelscited by 146
  11. 2021TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?cited by 127
  12. 2022Long Movie Clip Classification with State-Space Video Modelscited by 106
38 more
  1. 2023Selective Structured State-Spaces for Long-Form Video Understandingcited by 105
  2. 2022Learning To Recognize Procedural Activities with Distant Supervisioncited by 85
  3. 2022Temporal Action Segmentation: An Analysis of Modern Techniquescited by 85
  4. 2023AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?cited by 79
  5. 2023Knowing Where to Focus: Event-aware Transformer for Video Groundingcited by 79
  6. 2023HierVL: Learning Hierarchical Video-Language Embeddingscited by 66
  7. 2024Mamba-360: Survey of State Space Models as Transformer Alternative for Long Sequence Modelling: Methods, Applications, and Challengescited by 63
  8. 2022Bridge-Prompt: Towards Ordinal Action Understanding in Instructional Videoscited by 50
  9. 2021SportsCap: Monocular 3D Human Motion Capture and Fine-grained Understanding in Challenging Sports Videoscited by 40
  10. 2022MECCANO: A Multimodal Egocentric Dataset for Humans Behavior Understanding in the Industrial-like Domaincited by 36
  11. 2021VideoLT: Large-scale Long-tailed Video Recognitioncited by 35
  12. 2021VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Livingcited by 35
  13. 2021Space-Time Crop & Attend: Improving Cross-modal Video Representation Learningcited by 31
  14. 2022Rethinking Learning Approaches for Long-Term Action Anticipationcited by 29
  15. 2021Coarse to Fine Multi-Resolution Temporal Convolutional Networkcited by 28
  16. 2022Beyond Fixation: Dynamic Window Visual Transformercited by 28
  17. 2023PALM: Predicting Actions through Language Modelscited by 28
  18. 2025Temporal Working Memory: Query-Guided Segment Refinement for Enhanced Multimodal Understandingcited by 28
  19. 2021Unsupervised Discriminative Embedding for Sub-Action Learning in Complex Activitiescited by 26
  20. 2022Mitigating and Evaluating Static Bias of Action Representations in the Background and the Foregroundcited by 26
  21. 2021No frame left behind: Full Video Action Recognitioncited by 24
  22. 2022C2F-TCN: A Framework for Semi and Fully Supervised Temporal Action Segmentationcited by 23
  23. 2024Video Token Merging for Long-form Video Understandingcited by 22
  24. 2023Training a Large Video Model on a Single Machine in a Daycited by 20
  25. 2023Diversifying Spatial-Temporal Perception for Video Domain Generalizationcited by 19
  26. 2025HierarQ: Task-Aware Hierarchical Q-Former for Enhanced Video Understandingcited by 17
  27. 2025BASKET: A Large-Scale Video Dataset for Fine-Grained Skill Estimationcited by 17
  28. 2021Temporal Action Segmentation with High-level Complex Activity Labelscited by 16
  29. 2021Unsupervised Motion Representation Learning with Capsule Autoencoderscited by 16
  30. 2022Video Question Answering with Iterative Video-Text Co-Tokenizationcited by 16
  31. 2022Gate-Shift-Fuse for Video Action Recognitioncited by 15
  32. 2021Coarse Temporal Attention Network (CTA-Net) for Driver's Activity Recognitioncited by 14
  33. 2022Turbo Training with Token Dropoutcited by 14
  34. 2024Enhancing Long Video Understanding via Hierarchical Event-Based Memorycited by 14
  35. 2022The Wisdom of Crowds: Temporal Progressive Attention for Early Action Predictioncited by 13
  36. 2021Beyond Short Clips: End-to-End Video-Level Learning with Collaborative Memoriescited by 11
  37. 2021Hierarchical Modeling for Task Recognition and Action Segmentation in Weakly-Labeled Instructional Videoscited by 11
  38. 2021Temporal-attentive Covariance Pooling Networks for Video Recognitioncited by 11

50 most cited of 89 All 89 (JSON)