mlsanityData to 7 Oct 2026

Rethinking the Faster R-CNN Architecture for Temporal Action Localization

arXiv 1804.07667 ↗First posted 20 Apr 2018cs.CVcited by 194

Not on the map. Why?

Abstract (arXiv)

We propose TAL-Net, an improved approach to temporal action localization in video that is inspired by the Faster R-CNN object detection framework. TAL-Net addresses three key shortcomings of existing approaches: (1) we improve receptive field alignment using a multi-scale architecture that can accommodate extreme variation in action durations; (2) we better exploit the temporal context of actions for both proposal generation and action classification by appropriately extending receptive fields; and (3) we explicitly consider multi-stream feature fusion and demonstrate that fusing motion late is important. We achieve state-of-the-art performance for both action proposal and localization on THUMOS'14 detection benchmark and competitive performance on ActivityNet challenge.

Key facts. Cited by 194 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 65; 2022: 61; 2023: 29; 2024: 24; 2025: 13; 2026: 2.

194 papers.

Sort:

By area:

  1. 2021Prompting Visual-Language Models for Efficient Video Understandingcited by 309
  2. 2021Video Transformer Networkcited by 271
  3. 2021ASFormer: Transformer for Action Segmentationcited by 166
  4. 2021Learning Salient Boundary Feature for Anchor-free Temporal Action Localizationcited by 156
  5. 2021End-to-end Temporal Action Detection with Transformercited by 150
  6. 2021Relaxed Transformer Decoders for Direct Action Proposal Generationcited by 116
  7. 2021Temporal Context Aggregation Network for Temporal Action Proposal Refinementcited by 111
  8. 2022Temporal Alignment Networks for Long-term Videocited by 84
  9. 2021OadTR: Online Action Detection with Transformerscited by 83
  10. 2022TALLFormer: Temporal Action Localization with a Long-memory Transformercited by 78
  11. 2021Object-Region Video Transformerscited by 73
  12. 2021CoLA: Weakly-Supervised Temporal Action Localization with Snippet Contrastive Learningcited by 69
38 more
  1. 2023UnLoc: A Unified Framework for Video Localization Taskscited by 66
  2. 2021Generic Event Boundary Detection: A Benchmark for Event Segmentationcited by 64
  3. 2021Enriching Local and Global Contexts for Temporal Action Localizationcited by 64
  4. 2021FineAction: A Fine-Grained Video Dataset for Temporal Action Localizationcited by 60
  5. 2021Activity Graph Transformer for Temporal Action Localizationcited by 48
  6. 2021Unsupervised Action Segmentation by Joint Representation Learning and Online Clusteringcited by 48
  7. 2022ReAct: Temporal Action Detection with Relational Queriescited by 47
  8. 2021A Hybrid Attention Mechanism for Weakly-Supervised Temporal Action Localizationcited by 45
  9. 2023Implicit Temporal Modeling with Learnable Alignment for Video Recognitioncited by 44
  10. 2021Learning Action Completeness from Points for Weakly-supervised Temporal Action Localizationcited by 42
  11. 2022An Empirical Study of End-to-End Temporal Action Detectioncited by 40
  12. 2021Self-Supervised Learning for Semi-Supervised Temporal Action Proposalcited by 39
  13. 2022ASM-Loc: Action-aware Segment Modeling for Weakly-Supervised Temporal Action Localizationcited by 39
  14. 2023VidChapters-7M: Video Chapters at Scalecited by 39
  15. 2021Weakly Supervised Temporal Adjacent Network for Language Groundingcited by 37
  16. 2021Class Semantics-based Attention for Action Detectioncited by 36
  17. 2021DCAN: Improving Temporal Action Detection via Dual Context Aggregationcited by 36
  18. 2022Exploring Optical-Flow-Guided Motion and Detection-Based Appearance for Temporal Sentence Groundingcited by 35
  19. 2022Compound Prototype Matching for Few-shot Action Recognitioncited by 35
  20. 2021Cross-modal Consensus Network for Weakly Supervised Temporal Action Localizationcited by 34
  21. 2022Fine-grained Temporal Contrastive Learning for Weakly-supervised Temporal Action Localizationcited by 33
  22. 2021Learning an Augmented RGB Representation with Cross-Modal Knowledge Distillation for Action Detectioncited by 32
  23. 2021Deep Learning-based Action Detection in Untrimmed Videos: A Surveycited by 32
  24. 2022Weakly Supervised Temporal Action Localization via Representative Snippet Knowledge Propagationcited by 32
  25. 2022Unsupervised Pre-training for Temporal Action Localization Taskscited by 31
  26. 2021Hierarchical Object-oriented Spatio-Temporal Reasoning for Video Question Answeringcited by 29
  27. 2021Graph Convolutional Module for Temporal Action Localization in Videoscited by 29
  28. 2022Large-scale Robustness Analysis of Video Action Recognition Modelscited by 29
  29. 2022Proposal-Free Temporal Action Detection via Global Segmentation Mask Learningcited by 29
  30. 2021Support-Set Based Cross-Supervision for Video Groundingcited by 28
  31. 2022BasicTAD: an Astounding RGB-Only Baseline for Temporal Action Detectioncited by 28
  32. 2021Action Unit Memory Network for Weakly Supervised Temporal Action Localizationcited by 26
  33. 2021Foreground-Action Consistency Network for Weakly Supervised Temporal Action Localizationcited by 26
  34. 2021Augmented Transformer with Adaptive Graph for Temporal Action Proposal Generationcited by 25
  35. 2022RCL: Recurrent Continuous Localization for Temporal Action Detectioncited by 25
  36. 2022OpenTAL: Towards Open Set Temporal Action Localizationcited by 23
  37. 2021Towards Diverse Paragraph Captioning for Untrimmed Videoscited by 22
  38. 2022PointTAD: Multi-Label Temporal Action Detection with Learnable Query Pointscited by 22

50 most cited of 194 All 194 (JSON)