mlsanityData to 14 Oct 2026

Weakly-Supervised Temporal Action Localization Through Local-Global Background Modeling

arXiv 2106.11811 ↗First posted 20 Jun 2021cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Weakly-Supervised Temporal Action Localization (WS-TAL) task aims to recognize and localize temporal starts and ends of action instances in an untrimmed video with only video-level label supervision. Due to lack of negative samples of background category, it is difficult for the network to separate foreground and background, resulting in poor detection performance. In this report, we present our 2021 HACS Challenge - Weakly-supervised Learning Track solution that based on BaSNet to address above problem. Specifically, we first adopt pre-trained CSN, Slowfast, TDN, and ViViT as feature extractors to get feature sequences. Then our proposed Local-Global Background Modeling Network (LGBM-Net) is trained to localize instances by using only video-level labels based on Multi-Instance Learning (MIL). Finally, we ensemble multiple models to get the final detection results and reach 22.45% mAP on the test set

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 22 of its 24 references that are in the map. First posted on arXiv 20 Jun 2021.

Builds on

22 of 24 references.

References · 22

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,270
  4. 2017Non-local Neural Networkscited by 2,293
  5. 2018SlowFast Networks for Video Recognitioncited by 1,867
  6. 2021ViViT: A Video Vision Transformercited by 1,620
  7. 2019BMN: Boundary-Matching Network for Temporal Action Proposal Generationcited by 329
  8. 2015LSTM: A Search Space Odysseycited by 316
  9. 2019A Short Note on the Kinetics-700 Human Action Datasetcited by 310
  10. 2019Video Classification with Channel-Separated Convolutional Networkscited by 290
  11. 2017Temporal Segment Networks for Action Recognition in Videoscited by 279
  12. 2019G-TAD: Sub-Graph Localization for Temporal Action Detectioncited by 249
10 more
  1. 2020TDN: Temporal Difference Networks for Efficient Action Recognitioncited by 183
  2. 2021Temporal Context Aggregation Network for Temporal Action Proposal Refinementcited by 112
  3. 2017Weakly Supervised Action Localization by Sparse Temporal Pooling Networkcited by 100
  4. 2018W-TALC: Weakly-supervised Temporal Activity Localization and Classificationcited by 87
  5. 2019Background Suppression Network for Weakly-supervised Temporal Action Localizationcited by 73
  6. 2020Weakly-Supervised Action Localization with Expectation-Maximization Multi-Instance Learningcited by 48
  7. 2021A Hybrid Attention Mechanism for Weakly-Supervised Temporal Action Localizationcited by 45
  8. 2021Self-Supervised Learning for Semi-Supervised Temporal Action Proposalcited by 39
  9. 2019TACNet: Transition-Aware Context Network for Spatio-Temporal Action Detectioncited by 36
  10. 2021Self-supervised Motion Learning from Static Imagescited by 21

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 2.

4 papers.

  1. 2022Hybrid Relation Guided Set Matching for Few-shot Action Recognitioncited by 50
  2. 2023MoLo: Motion-augmented Long-short Contrastive Learning for Few-shot Action Recognitioncited by 37
  3. 2023HR-Pro: Point-supervised Temporal Action Localization via Hierarchical Reliability Propagationcited by 16
  4. 2022Context-aware Proposal Network for Temporal Action Detectioncited by 3