mlsanityData to 14 Oct 2026

Relation Modeling in Spatio-Temporal Action Localization

arXiv 2106.08061 ↗First posted 15 Jun 2021cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

This paper presents our solution to the AVA-Kinetics Crossover Challenge of ActivityNet workshop at CVPR 2021. Our solution utilizes multiple types of relation modeling methods for spatio-temporal action detection and adopts a training strategy to integrate multiple relation modeling in end-to-end training over the two large-scale video datasets. Learning with memory bank and finetuning for long-tailed distribution are also investigated to further improve the performance. In this paper, we detail the implementations of our solution and provide experiments results and corresponding discussions. We finally achieve 40.67 mAP on the test set of AVA-Kinetics.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 23 of its 25 references that are in the map. First posted on arXiv 15 Jun 2021.

Builds on

23 of 25 references.

References · 23

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  4. 2017Mask R-CNNcited by 7,277
  5. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,270
  6. 2017Non-local Neural Networkscited by 2,293
  7. 2018SlowFast Networks for Video Recognitioncited by 1,867
  8. 2021ViViT: A Video Vision Transformercited by 1,620
  9. 2021Multiscale Vision Transformerscited by 897
  10. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 809
  11. 2017AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actionscited by 449
  12. 2019Video Classification with Channel-Separated Convolutional Networkscited by 290
11 more
  1. 2018Long-Term Feature Banks for Detailed Video Understandingcited by 239
  2. 2020Self-supervised Co-training for Video Representation Learningcited by 232
  3. 2021Temporal Context Aggregation Network for Temporal Action Proposal Refinementcited by 112
  4. 2020Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detectioncited by 104
  5. 2020Actor-Context-Actor Relation Network for Spatio-Temporal Action Localizationcited by 91
  6. 2020The AVA-Kinetics Localized Human Actions Video Datasetcited by 82
  7. 2020Asynchronous Interaction Aggregation for Action Detectioncited by 65
  8. 2018D3D: Distilled 3D Networks for Video Action Recognitioncited by 60
  9. 2019TACNet: Transition-Aware Context Network for Spatio-Temporal Action Detectioncited by 36
  10. 2021Self-supervised Motion Learning from Static Imagescited by 21
  11. 2020CBR-Net: Cascade Boundary Refinement Network for Action Detection: Submission to ActivityNet Challenge 2020 (Task 1)cited by 7

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2; 2024: 0; 2025: 2.

5 papers.

  1. 2022InternVideo: General Video Foundation Models via Generative and Discriminative Learningcited by 447
  2. 2023On the Benefits of 3D Pose and Tracking for Human Action Recognitioncited by 32
  3. 2025MVAFormer: RGB-based Multi-View Spatio-Temporal Action Recognition with Transformercited by 1
  4. 2023Learning Higher-order Object Interactions for Keypoint-based Video Understandingcited by 0
  5. 2025ProTAL: A Drag-and-Link Video Programming Framework for Temporal Action Localizationcited by 0