mlsanityData to 7 Oct 2026

Faster-TAD: Towards Temporal Action Detection with Proposal Generation and Classification in a Unified Network

arXiv 2204.02674 ↗First posted 6 Apr 2022cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

Temporal action detection (TAD) aims to detect the semantic labels and boundaries of action instances in untrimmed videos. Current mainstream approaches are multi-step solutions, which fall short in efficiency and flexibility. In this paper, we propose a unified network for TAD, termed Faster-TAD, by re-purposing a Faster-RCNN like architecture. To tackle the unique difficulty in TAD, we make important improvements over the original framework. We propose a new Context-Adaptive Proposal Module and an innovative Fake-Proposal Generation Block. What's more, we use atomic action features to improve the performance. Faster-TAD simplifies the pipeline of TAD and gets remarkable performance on lots of benchmarks, i.e., ActivityNet-1.3 (40.01% mAP), HACS Segments (38.39% mAP), SoccerNet-Action Spotting (54.09% mAP). It outperforms existing single-network detector by a large margin.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 32 of its 41 references that are in the map. First posted on arXiv 6 Apr 2022.

Builds on

32 of 41 references.

References · 32

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2017Mask R-CNNcited by 7,259
  6. 2016Layer Normalizationcited by 5,579
  7. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  8. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  9. 2018SlowFast Networks for Video Recognitioncited by 1,862
  10. 2017Soft-NMS -- Improving Object Detection With One Line of Codecited by 380
  11. 2019BMN: Boundary-Matching Network for Temporal Action Proposal Generationcited by 327
  12. 2019Video Classification with Channel-Separated Convolutional Networkscited by 290
20 more
  1. 2018BSN: Boundary Sensitive Network for Temporal Action Proposal Generationcited by 271
  2. 2017Temporal Action Detection with Structured Segment Networkscited by 265
  3. 2019G-TAD: Sub-Graph Localization for Temporal Action Detectioncited by 248
  4. 2019Graph Convolutional Networks for Temporal Action Localizationcited by 208
  5. 2018Rethinking the Faster R-CNN Architecture for Temporal Action Localizationcited by 194
  6. 2017R-C3D: Region Convolutional 3D Network for Temporal Activity Detectioncited by 161
  7. 2021Learning Salient Boundary Feature for Anchor-free Temporal Action Localizationcited by 156
  8. 2021End-to-end Temporal Action Detection with Transformercited by 150
  9. 2018SoccerNet: A Scalable Dataset for Action Spotting in Soccer Videoscited by 148
  10. 2019Gaussian Temporal Awareness Networks for Action Localizationcited by 135
  11. 2017UntrimmedNets for Weakly Supervised Action Recognition and Detectioncited by 129
  12. 2021Relaxed Transformer Decoders for Direct Action Proposal Generationcited by 116
  13. 2017TURN TAP: Temporal Unit Regression Network for Temporal Action Proposalscited by 113
  14. 2021Temporal Context Aggregation Network for Temporal Action Proposal Refinementcited by 111
  15. 2020TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Taskscited by 77
  16. 2021Enriching Local and Global Contexts for Temporal Action Localizationcited by 64
  17. 2016CUHK & ETHZ & SIAT Submission to ActivityNet Challenge 2016cited by 53
  18. 2021Class Semantics-based Attention for Action Detectioncited by 36
  19. 2021Feature Combination Meets Attention: Baidu Soccer Embeddings and Transformer based Temporal Detectioncited by 27
  20. 2021Proposal Relation Network for Temporal Action Detectioncited by 18

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 3; 2024: 4.

10 papers.

  1. 2022SoccerNet 2022 Challenges Resultscited by 28
  2. 2022Temporally Precise Action Spotting in Soccer Videos Using Dense Detection Anchorscited by 27
  3. 2023COMEDIAN: Self-Supervised Learning and Knowledge Distillation for Action Spotting using Transformerscited by 17
  4. 2023Adapting Short-Term Transformers for Action Detection in Untrimmed Videoscited by 16
  5. 2022Action Spotting using Dense Detection Anchors Revisited: Submission to the SoccerNet Challenge 2022cited by 14
  6. 2024Unifying Global and Local Scene Entities Modelling for Precise Action Spottingcited by 8
  7. 2023Survey of Action Recognition, Spotting and Spatio-Temporal Localization in Soccer -- Current Trends and Research Perspectivescited by 7
  8. 2024Deep learning for action spotting in association football videoscited by 7
  9. 2024Technical Report for SoccerNet Challenge 2022 -- Replay Grounding Taskcited by 0
  10. 2024Technical Report for ActivityNet Challenge 2022 -- Temporal Action Localizationcited by 0