mlsanityData to 7 Oct 2026

Hierarchical Graph-RNNs for Action Detection of Multiple Activities

arXiv 2101.08581 ↗First posted 21 Jan 2021cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose an approach that spatially localizes the activities in a video frame where each person can perform multiple activities at the same time. Our approach takes the temporal scene context as well as the relations of the actions of detected persons into account. While the temporal context is modeled by a temporal recurrent neural network (RNN), the relations of the actions are modeled by a graph RNN. Both networks are trained together and the proposed approach achieves state of the art results on the AVA dataset.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 24 of its 29 references that are in the map. First posted on arXiv 21 Jan 2021.

Builds on

24 of 29 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  5. 2015Fast R-CNNcited by 2,930
  6. 2015Gated Graph Sequence Neural Networkscited by 792
  7. 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 751
  8. 2017Focal Loss for Dense Object Detectioncited by 749
  9. 2017AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actionscited by 449
  10. 2018Graph R-CNN for Scene Graph Generationcited by 296
  11. 2015Structural-RNN: Deep Learning on Spatio-Temporal Graphscited by 234
  12. 2018Rethinking the Faster R-CNN Architecture for Temporal Action Localizationcited by 194
12 more
  1. 2018Learning Human-Object Interactions by Graph Parsing Neural Networkscited by 176
  2. 2016Graph-Structured Representations for Visual Question Answeringcited by 123
  3. 2016Hierarchical Deep Temporal Models for Group Activity Recognitioncited by 89
  4. 2018Actor-Centric Relation Networkcited by 87
  5. 2017Action Tubelet Detector for Spatio-Temporal Action Localizationcited by 77
  6. 2018D3D: Distilled 3D Networks for Video Action Recognitioncited by 60
  7. 2016Online Real-time Multiple Spatiotemporal Action Localisation and Predictioncited by 57
  8. 2014Finding Action Tubescited by 50
  9. 2017Tube Convolutional Neural Network (T-CNN) for Action Detection in Videoscited by 50
  10. 2018A Better Baseline for AVAcited by 16
  11. 2016Human Action Localization with Sparse Spatial Supervisioncited by 8
  12. 2018Structural Recurrent Neural Network (SRNN) for Group Activity Analysiscited by 3

Built on by

Not cited yet.