mlsanityData to 14 Oct 2026

A Stronger Baseline for Ego-Centric Action Detection

arXiv 2106.06942 ↗First posted 13 Jun 2021cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

This technical report analyzes an egocentric video action detection method we used in the 2021 EPIC-KITCHENS-100 competition hosted in CVPR2021 Workshop. The goal of our task is to locate the start time and the end time of the action in the long untrimmed video, and predict action category. We adopt sliding window strategy to generate proposals, which can better adapt to short-duration actions. In addition, we show that classification and proposals are conflict in the same network. The separation of the two tasks boost the detection performance with high efficiency. By simply employing these strategy, we achieved 16.10% performance on the test set of EPIC-KITCHENS-100 Action Detection challenge using a single model, surpassing the baseline method by 11.7% in terms of average mAP.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 25 of its 33 references that are in the map. First posted on arXiv 13 Jun 2021.

Builds on

25 of 33 references.

References · 25

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,270
  3. 2018SlowFast Networks for Video Recognitioncited by 1,867
  4. 2021Is Space-Time Attention All You Need for Video Understanding?cited by 1,620
  5. 2021ViViT: A Video Vision Transformercited by 1,620
  6. 2017A Closer Look at Spatiotemporal Convolutions for Action Recognitioncited by 1,143
  7. 2019End-to-End Learning of Visual Representations from Uncurated Instructional Videoscited by 507
  8. 2017Learning Spatio-Temporal Representation with Pseudo-3D Residual Networkscited by 387
  9. 2017Soft-NMS -- Improving Object Detection With One Line of Codecited by 382
  10. 2019BMN: Boundary-Matching Network for Temporal Action Proposal Generationcited by 329
  11. 2019A Short Note on the Kinetics-700 Human Action Datasetcited by 310
  12. 2019Video Classification with Channel-Separated Convolutional Networkscited by 290
13 more
  1. 2021DeepViT: Towards Deeper Vision Transformercited by 289
  2. 2018BSN: Boundary Sensitive Network for Temporal Action Proposal Generationcited by 271
  3. 2019G-TAD: Sub-Graph Localization for Temporal Action Detectioncited by 249
  4. 2020Self-supervised Co-training for Video Representation Learningcited by 232
  5. 2017TURN TAP: Temporal Unit Regression Network for Temporal Action Proposalscited by 113
  6. 2021Temporal Context Aggregation Network for Temporal Action Proposal Refinementcited by 112
  7. 2019Fast Learning of Temporal Action Proposal via Dense Boundary Generatorcited by 89
  8. 2020Boundary Content Graph Neural Network for Temporal Action Proposal Generationcited by 88
  9. 2021Self-Supervised Learning for Semi-Supervised Temporal Action Proposalcited by 39
  10. 2021Self-supervised Motion Learning from Static Imagescited by 21
  11. 2021Towards Training Stronger Video Vision Transformers for EPIC-KITCHENS-100 Action Recognitioncited by 11
  12. 2020CBR-Net: Cascade Boundary Refinement Network for Action Detection: Submission to ActivityNet Challenge 2020 (Task 1)cited by 7
  13. 2020Temporal Fusion Network for Temporal Action Localization:Submission to ActivityNet Challenge 2020 (Task E)cited by 2

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 1; 2023: 1.

3 papers.

  1. 2021TAda! Temporally-Adaptive Convolutions for Video Understandingcited by 36
  2. 2023Temporally-Adaptive Models for Efficient Video Understandingcited by 7
  3. 2022OWL (Observe, Watch, Listen): Audiovisual Temporal Context for Localizing Actions in Egocentric Videoscited by 4