mlsanityData to 14 Oct 2026

Cross-view Action Recognition via Contrastive View-invariant Representation

arXiv 2305.01733 ↗First posted 2 May 2023cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Cross view action recognition (CVAR) seeks to recognize a human action when observed from a previously unseen viewpoint. This is a challenging problem since the appearance of an action changes significantly with the viewpoint. Applications of CVAR include surveillance and monitoring of assisted living facilities where is not practical or feasible to collect large amounts of training data when adding a new camera. We present a simple yet efficient CVAR framework to learn invariant features from either RGB videos, 3D skeleton data, or both. The proposed approach outperforms the current state-of-the-art achieving similar levels of performance across input modalities: 99.4% (RGB) and 99.9% (3D skeletons), 99.4% (RGB) and 99.9% (3D Skeletons), 97.3% (RGB), and 99.2% (3D skeletons), and 84.4%(RGB) for the N-UCLA, NTU-RGB+D 60, NTU-RGB+D 120, and UWA3DII datasets, respectively.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 31 of its 68 references that are in the map. First posted on arXiv 2 May 2023.

Builds on

31 of 68 references.

References · 31

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,270
  3. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,209
  4. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,064
  5. 2014Long-term Recurrent Convolutional Networks for Visual Recognition and Descriptioncited by 484
  6. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 403
  7. 2018A Short Note about Kinetics-600cited by 333
  8. 2021Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognitioncited by 322
  9. 2021Revisiting Skeleton-based Action Recognitioncited by 257
  10. 2014Cross-view Action Modeling, Learning and Recognitioncited by 134
  11. 2017A New Representation of Skeleton Sequences for 3D Action Recognitioncited by 126
  12. 2020A Short Note on the Kinetics-700-2020 Human Action Datasetcited by 92
19 more
  1. 2018View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognitioncited by 84
  2. 2022PYSKL: Towards Good Practices for Skeleton Action Recognitioncited by 83
  3. 2021Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learningcited by 58
  4. 2017Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gatescited by 54
  5. 2019Synthetic Humans for Action Recognition from Unseen Viewpointscited by 46
  6. 2017Unsupervised Learning of Long-Term Motion Dynamics for Videoscited by 37
  7. 2021VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Livingcited by 35
  8. 2018Glimpse Clouds: Human Activity Recognition from Unstructured Feature Pointscited by 33
  9. 2018Unsupervised Learning of View-invariant Action Representationscited by 32
  10. 2021Learning an Augmented RGB Representation with Cross-Modal Knowledge Distillation for Action Detectioncited by 32
  11. 2021GeomNet: A Neural Network Based on Riemannian Geometries of SPD Matrix Space and Cholesky Space for 3D Skeleton-Based Interaction Recognitioncited by 27
  12. 2016Deep Multimodal Feature Analysis for Action Recognition in RGB+D Videoscited by 26
  13. 2017Scene Flow to Action Map: A New Representation for RGB-D based Action Recognition with Convolutional Neural Networkscited by 20
  14. 2018Hierarchically Learned View-Invariant Representations for Cross-View Action Recognitioncited by 16
  15. 2016Learning a Deep Model for Human Action Recognition from Novel Viewpointscited by 12
  16. 2022Skeleton-based Action Recognition via Adaptive Cross-Form Learningcited by 12
  17. 2018DYAN: A Dynamical Atoms-Based Network for Video Predictioncited by 11
  18. 2018Adding Attentiveness to the Neurons in Recurrent Neural Networkscited by 11
  19. 2020Hierarchical Action Classification with Network Pruningcited by 7

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Cross-View Cross-Modal Unsupervised Domain Adaptation for Driver Monitoring Systemcited by 0