mlsanityData to 7 Oct 2026

Winning the CVPR'2021 Kinetics-GEBD Challenge: Contrastive Learning Approach

arXiv 2106.11549 ↗First posted 22 Jun 2021cs.CVcited by 13

Not on the map. Why?

Abstract (arXiv)

Generic Event Boundary Detection (GEBD) is a newly introduced task that aims to detect "general" event boundaries that correspond to natural human perception. In this paper, we introduce a novel contrastive learning based approach to deal with the GEBD. Our intuition is that the feature similarity of the video snippet would significantly vary near the event boundaries, while remaining relatively the same in the remaining part of the video. In our model, Temporal Self-similarity Matrix (TSM) is utilized as an intermediate representation which takes on a role as an information bottleneck. With our model, we achieved significant performance boost compared to the given baselines. Our code is available at https://github.com/hello-jinwoo/LOVEU-CVPR2021.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 18 of its 25 references that are in the map. First posted on arXiv 22 Jun 2021.

Builds on

18 of 25 references.

References · 18

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  2. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  3. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  4. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  5. 2018SlowFast Networks for Video Recognitioncited by 1,862
  6. 2016Temporal Segment Networks: Towards Good Practices for Deep Action Recognitioncited by 899
  7. 2019G-TAD: Sub-Graph Localization for Temporal Action Detectioncited by 248
  8. 2019Graph Convolutional Networks for Temporal Action Localizationcited by 208
  9. 2017CDC: Convolutional-De-Convolutional Networks for Precise Temporal Action Localization in Untrimmed Videoscited by 112
  10. 2015End-to-end Learning of Action Detection from Frame Glimpses in Videoscited by 101
  11. 2019Fast Learning of Temporal Action Proposal via Dense Boundary Generatorcited by 89
  12. 2020Boundary Content Graph Neural Network for Temporal Action Proposal Generationcited by 88
6 more
  1. 2018Temporal Recurrent Networks for Online Action Detectioncited by 79
  2. 2020TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Taskscited by 77
  3. 2016Online Action Detectioncited by 68
  4. 2020Counting Out Time: Class Agnostic Video Repetition Counting in the Wildcited by 67
  5. 2021Generic Event Boundary Detection: A Benchmark for Event Segmentationcited by 64
  6. 2016CUHK & ETHZ & SIAT Submission to ActivityNet Challenge 2016cited by 53

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 5; 2023: 3; 2024: 3; 2025: 1.

13 papers.

Sort:

  1. 2021Progressive Attention on Multi-Level Dense Difference Maps for Generic Event Boundary Detectioncited by 19
  2. 2022End-to-End Compressed Video Representation Learning for Generic Event Boundary Detectioncited by 15
  3. 2022Structured Context Transformer for Generic Event Boundary Detectioncited by 10
  4. 2024Rethinking the Architecture Design for Efficient Generic Event Boundary Detectioncited by 7
  5. 2022Soft-Landing Strategy for Alleviating the Task Discrepancy Problem in Temporal Action Localization Taskscited by 5
  6. 2024What's in the Flow? Exploiting Temporal Motion Cues for Unsupervised Generic Event Boundary Detectioncited by 4
  7. 2024Fine-grained Dynamic Network for Generic Event Boundary Detectioncited by 4
  8. 2022Masked Autoencoders for Generic Event Boundary Detection CVPR'2022 Kinetics-GEBD Challengecited by 3
  9. 2022Motion Aware Self-Supervision for Generic Event Boundary Detectioncited by 3
  10. 2023AutoMatch: A Large-scale Audio Beat Matching Benchmark for Boosting Deep Learning Assistant Video Editingcited by 3
  11. 2023Local Compressed Video Stream Learning for Generic Event Boundary Detectioncited by 3
  12. 2023MAE-GEBD:Winning the CVPR'2023 LOVEU-GEBD Challengecited by 1
1 more
  1. 2025Structured Context Learning for Generic Event Boundary Detectioncited by 1