mlsanityData to 7 Oct 2026

TriDet: Temporal Action Detection with Relative Boundary Modeling

arXiv 2303.07347 ↗First posted 13 Mar 2023cs.CV cs.AI cs.MMcited by 141

Not on the map. Why?

Abstract (arXiv)

In this paper, we present a one-stage framework TriDet for temporal action detection. Existing methods often suffer from imprecise boundary predictions due to the ambiguous action boundaries in videos. To alleviate this problem, we propose a novel Trident-head to model the action boundary via an estimated relative probability distribution around the boundary. In the feature pyramid of TriDet, we propose an efficient Scalable-Granularity Perception (SGP) layer to mitigate the rank loss problem of self-attention that takes place in the video features and aggregate information across different temporal granularities. Benefiting from the Trident-head and the SGP-based feature pyramid, TriDet achieves state-of-the-art performance on three challenging benchmarks: THUMOS14, HACS and EPIC-KITCHEN 100, with lower computational costs, compared to previous methods. For example, TriDet hits an average mAP of 69.3% on THUMOS14, outperforming the previous best by 2.5%, but with only 74.6% of its latency. The code is released to https://github.com/sssste/TriDet.

Key facts. Cited by 141 papers in the map (data through 7 Oct 2026). Builds on 48 of its 56 references that are in the map. First posted on arXiv 13 Mar 2023.

Builds on

48 of 56 references.

References · 48

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020End-to-End Object Detection with Transformerscited by 7,384
  3. 2016Layer Normalizationcited by 5,579
  4. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  5. 2017Squeeze-and-Excitation Networkscited by 4,763
  6. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  7. 2022A ConvNet for the 2020scited by 3,545
  8. 2020Longformer: The Long-Document Transformercited by 3,362
  9. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  10. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
  11. 2018SlowFast Networks for Video Recognitioncited by 1,862
  12. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
36 more
  1. 2018Group Normalizationcited by 1,514
  2. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
  3. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,361
  4. 2017Focal Loss for Dense Object Detectioncited by 749
  5. 2019Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selectioncited by 539
  6. 2020Rescaling Egocentric Visioncited by 529
  7. 2021Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depthcited by 411
  8. 2020Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detectioncited by 408
  9. 2017Soft-NMS -- Improving Object Detection With One Line of Codecited by 380
  10. 2019BMN: Boundary-Matching Network for Temporal Action Proposal Generationcited by 327
  11. 2022ActionFormer: Localizing Moments of Actions with Transformerscited by 308
  12. 2018BSN: Boundary Sensitive Network for Temporal Action Proposal Generationcited by 271
  13. 2017Temporal Action Detection with Structured Segment Networkscited by 265
  14. 2019G-TAD: Sub-Graph Localization for Temporal Action Detectioncited by 248
  15. 2019Graph Convolutional Networks for Temporal Action Localizationcited by 208
  16. 2021Learning Salient Boundary Feature for Anchor-free Temporal Action Localizationcited by 156
  17. 2021End-to-end Temporal Action Detection with Transformercited by 150
  18. 2019Gaussian Temporal Awareness Networks for Action Localizationcited by 135
  19. 2021Relaxed Transformer Decoders for Direct Action Proposal Generationcited by 116
  20. 2021Temporal Context Aggregation Network for Temporal Action Proposal Refinementcited by 111
  21. 2020Video Self-Stitching Graph Network for Temporal Action Localizationcited by 104
  22. 2019Fast Learning of Temporal Action Proposal via Dense Boundary Generatorcited by 89
  23. 2018W-TALC: Weakly-supervised Temporal Activity Localization and Classificationcited by 87
  24. 2022TALLFormer: Temporal Action Localization with a Long-memory Transformercited by 78
  25. 2020TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Taskscited by 77
  26. 2020Revisiting Anchor Mechanisms for Temporal Action Localizationcited by 75
  27. 2018Diagnosing Error in Temporal Action Detectorscited by 71
  28. 2021Enriching Local and Global Contexts for Temporal Action Localizationcited by 64
  29. 2020Multi-shot Temporal Event Localization: a Benchmarkcited by 52
  30. 2022ReAct: Temporal Action Detection with Relational Queriescited by 47
  31. 2022An Empirical Study of End-to-End Temporal Action Detectioncited by 40
  32. 2021Class Semantics-based Attention for Action Detectioncited by 36
  33. 2021DCAN: Improving Temporal Action Detection via Dual Context Aggregationcited by 36
  34. 2022BasicTAD: an Astounding RGB-Only Baseline for Temporal Action Detectioncited by 28
  35. 2021Low-Fidelity End-to-End Video Encoder Pre-training for Temporal Action Localizationcited by 20
  36. 2022An Efficient Spatio-Temporal Pyramid Transformer for Action Detectioncited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 20; 2024: 47; 2025: 45; 2026: 29.

141 papers.

Sort:

By area:

  1. 2023AV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Datasetcited by 79
  2. 2023End-to-End Temporal Action Detection with 1B Parameters Across 1000 Framescited by 47
  3. 2023Glitch in the Matrix: A Large Scale Benchmark for Content Driven Audio-Visual Forgery Detection and Localizationcited by 42
  4. 2024360+x: A Panoptic Multi-modal Scene Understanding Datasetcited by 35
  5. 2024HIMO: A New Benchmark for Full-Body Human Interacting with Multiple Objectscited by 34
  6. 2024OphNet: A Large-Scale Video Benchmark for Ophthalmic Surgical Workflow Understandingcited by 31
  7. 2023WEAR: An Outdoor Sports Dataset for Wearable and Egocentric Activity Recognitioncited by 30
  8. 2023BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videoscited by 29
  9. 2024Task-Driven Exploration: Decoupling and Inter-Task Feedback for Joint Moment Retrieval and Highlight Detectioncited by 25
  10. 2024T-DEED: Temporal-Discriminability Enhancer Encoder-Decoder for Precise Event Spotting in Sports Videoscited by 21
  11. 2023NurViD: A Large Expert-Level Video Database for Nursing Procedure Activity Understandingcited by 20
  12. 2024MMAD: Multi-label Micro-Action Detection in Videoscited by 20
38 more
  1. 2025Challenges and Trends in Egocentric Vision: A Surveycited by 20
  2. 2024LinVT: Empower Your Image-level Large Language Model to Understand Videoscited by 19
  3. 2024Dual DETRs for Multi-Label Temporal Action Detectioncited by 18
  4. 2024DyFADet: Dynamic Feature Aggregation for Temporal Action Detectioncited by 18
  5. 2023Adapting Short-Term Transformers for Action Detection in Untrimmed Videoscited by 16
  6. 2024UniMD: Towards Unifying Moment Retrieval and Temporal Action Detectioncited by 16
  7. 2023Temporal Action Localization with Enhanced Instant Discriminabilitycited by 13
  8. 2024TE-TAD: Towards Full End-to-End Temporal Action Detection via Time-Aligned Coordinate Expressioncited by 13
  9. 2023SurgPLAN: Surgical Phase Localization Network for Phase Recognitioncited by 12
  10. 2024Benchmarking the Robustness of Temporal Action Detection Models Against Temporal Corruptionscited by 12
  11. 2024DiMoDif: Discourse Modality-information Differentiation for Audio-visual Deepfake Detection and Localizationcited by 12
  12. 2023ENIGMA-51: Towards a Fine-Grained Understanding of Human-Object Interactions in Industrial Scenarioscited by 11
  13. 2024Action Detection via an Image Diffusion Processcited by 11
  14. 2024Computer Vision for Primate Behavior Analysis in the Wildcited by 10
  15. 2024Locality-aware Cross-modal Correspondence Learning for Dense Audio-Visual Events Localizationcited by 10
  16. 2025OpenTAD: A Unified Framework and Comprehensive Study of Temporal Action Detectioncited by 10
  17. 2025Online Micro-gesture Recognition Using Data Augmentation and Spatial-Temporal Attentioncited by 10
  18. 2025XRF V2: A Dataset for Action Summarization with Wi-Fi Signals, and IMUs in Phones, Watches, Earbuds, and Glassescited by 9
  19. 2024Every Shot Counts: Using Exemplars for Repetition Counting in Videoscited by 8
  20. 2024Harnessing Temporal Causality for Advanced Temporal Action Detectioncited by 8
  21. 2024Online Temporal Action Localization with Memory-Augmented Transformercited by 8
  22. 2025VidEvent: A Large Dataset for Understanding Dynamic Evolution of Events in Videoscited by 8
  23. 2025A Multimodal Deviation Perceiving Framework for Weakly-Supervised Temporal Forgery Localizationcited by 8
  24. 2025From Pretrain to Pain: Adversarial Vulnerability of Video Foundation Models Without Task Knowledgecited by 8
  25. 2023Temporal Action Localization for Inertial-based Human Activity Recognitioncited by 7
  26. 2024Rethinking the Architecture Design for Efficient Generic Event Boundary Detectioncited by 7
  27. 2025Rethinking Pseudo-Label Guided Learning for Weakly Supervised Temporal Action Localization from the Perspective of Noise Correctioncited by 7
  28. 2025F3Set: Towards Analyzing Fast, Frequent, and Fine-grained Events from Videoscited by 7
  29. 2025DisTime: Distribution-based Time Representation for Video Large Language Modelscited by 7
  30. 2024WiFi CSI Based Temporal Activity Detection via Dual Pyramid Networkcited by 6
  31. 2024Prediction-Feedback DETR for Temporal Action Detectioncited by 5
  32. 2024Open-Vocabulary Action Localization with Iterative Visual Promptingcited by 5
  33. 2025ALBAR: Adversarial Learning approach to mitigate Biases in Action Recognitioncited by 5
  34. 2025Temporal Action Detection Model Compression by Progressive Block Dropcited by 5
  35. 2025Bridge the Gap: From Weak to Full Supervision for Temporal Action Localization with PseudoFormercited by 5
  36. 2024LoSA: Long-Short-range Adapter for Scaling End-to-End Temporal Action Localizationcited by 4
  37. 2024UniAV: Unified Audio-Visual Perception for Multi-Task Video Event Localizationcited by 4
  38. 2024STAT: Towards Generalizable Temporal Action Localizationcited by 4

50 most cited of 141 All 141 (JSON)