mlsanityData to 7 Oct 2026

Spatial-Temporal Alignment Network for Action Recognition

arXiv 2308.09897 ↗First posted 19 Aug 2023cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

This paper studies introducing viewpoint invariant feature representations in existing action recognition architecture. Despite significant progress in action recognition, efficiently handling geometric variations in large-scale datasets remains challenging. To tackle this problem, we propose a novel Spatial-Temporal Alignment Network (STAN), which explicitly learns geometric invariant representations for action recognition. Notably, the STAN model is light-weighted and generic, which could be plugged into existing action recognition models (e.g., MViTv2) with a low extra computational cost. We test our STAN model on widely-used datasets like UCF101 and HMDB51. The experimental results show that the STAN model can consistently improve the state-of-the-art models in action recognition tasks in trained-from-scratch settings.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 28 of its 45 references that are in the map. First posted on arXiv 19 Aug 2023.

Builds on

28 of 45 references.

References · 28

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  4. 2017Non-local Neural Networkscited by 2,290
  5. 2018SlowFast Networks for Video Recognitioncited by 1,862
  6. 2017Deformable Convolutional Networkscited by 1,481
  7. 2015Spatial Transformer Networkscited by 1,423
  8. 2017A Closer Look at Spatiotemporal Convolutions for Action Recognitioncited by 1,139
  9. 2014Two-Stream Convolutional Networks for Action Recognition in Videoscited by 1,067
  10. 2021Multiscale Vision Transformerscited by 896
  11. 2021MViTv2: Improved Multiscale Vision Transformers for Classification and Detectioncited by 516
  12. 2018Videos as Space-Time Region Graphscited by 221
16 more
  1. 2018Rethinking the Faster R-CNN Architecture for Temporal Action Localizationcited by 194
  2. 2018Learning Human-Object Interactions by Graph Parsing Neural Networkscited by 176
  3. 2017R-C3D: Region Convolutional 3D Network for Temporal Activity Detectioncited by 161
  4. 2018Graph-Based Global Reasoning Networkscited by 120
  5. 2016Spatiotemporal Residual Networks for Video Action Recognitioncited by 91
  6. 2020Actor-Context-Actor Relation Network for Spatio-Temporal Action Localizationcited by 91
  7. 2019Stacked Capsule Autoencoderscited by 82
  8. 2019STEP: Spatio-Temporal Progressive Learning for Video Action Detectioncited by 51
  9. 2017Tube Convolutional Neural Network (T-CNN) for Action Detection in Videoscited by 50
  10. 2018A Structured Model For Action Detectioncited by 43
  11. 2018VideoCapsuleNet: A Simplified Network for Action Detectioncited by 30
  12. 2016Inverse Compositional Spatial Transformer Networkscited by 29
  13. 2016Asynchronous Temporal Fields for Action Recognitioncited by 21
  14. 2014Bag of Visual Words and Fusion Methods for Action Recognition: Comprehensive Study and Good Practicecited by 13
  15. 2022Multi-dataset Training of Transformers for Robust Action Recognitioncited by 10
  16. 2020Spatial-Temporal Alignment Network for Action Recognition and Detectioncited by 3

Built on by

Cited by year

Citing papers per year: 2023: 1.

1 paper.

  1. 2023GeoDeformer: Geometric Deformable Transformer for Action Recognitioncited by 1