mlsanityData to 14 Oct 2026

SMV-EAR: Bring Spatiotemporal Multi-View Representation Learning into Efficient Event-Based Action Recognition

arXiv 2601.17391 ↗First posted 24 Jan 2026cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Event cameras action recognition (EAR) offers compelling privacy-protecting and efficiency advantages, where temporal motion dynamics is of great importance. Existing spatiotemporal multi-view representation learning (SMVRL) methods for event-based object recognition (EOR) offer promising solutions by projecting H-W-T events along spatial axis H and W, yet are limited by its translation-variant spatial binning representation and naive early concatenation fusion architecture. This paper reexamines the key SMVRL design stages for EAR and propose: (i) a principled spatiotemporal multi-view representation through translation-invariant dense conversion of sparse events, (ii) a dual-branch, dynamic fusion architecture that models sample-wise complementarity between motion features from different views, and (iii) a bio-inspired temporal warping augmentation that mimics speed variability of real-world human actions. On three challenging EAR datasets of HARDVS, DailyDVS-200 and THU-EACT-50-CHL, we show +7.0%, +10.7%, and +10.2% Top-1 accuracy gains over existing SMVRL EOR method with surprising 30.1% reduced parameters and 35.7% lower computations, establishing our framework as a novel and powerful EAR paradigm.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 42 of its 64 references that are in the map. First posted on arXiv 24 Jan 2026.

Builds on

42 of 64 references.

References · 42

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  5. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  6. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  7. 2018SlowFast Networks for Video Recognitioncited by 1,867
  8. 2021Is Space-Time Attention All You Need for Video Understanding?cited by 1,620
  9. 2017A Closer Look at Spatiotemporal Convolutions for Action Recognitioncited by 1,143
  10. 2021Video Swin Transformercited by 1,091
  11. 2019Event-based Vision: A Surveycited by 1,016
  12. 2018TSM: Temporal Shift Module for Efficient Video Understandingcited by 856
30 more
  1. 2017Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networkscited by 406
  2. 2018Unsupervised Event-based Learning of Optical Flow, Depth, and Egomotioncited by 307
  3. 2021Video Transformer Networkcited by 272
  4. 2022Spikformer: When Spiking Neural Network Meets Transformercited by 271
  5. 2018Deep Learning in Spiking Neural Networkscited by 263
  6. 2019End-to-End Learning of Representations for Asynchronous Event-Based Datacited by 217
  7. 2017SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernelscited by 161
  8. 2023Spike-driven Transformercited by 146
  9. 2022AEGNN: Asynchronous Event-based Graph Neural Networkscited by 118
  10. 2023GET: Group Event Transformer for Event-Based Visioncited by 73
  11. 2024Recent Event Camera Innovations: A Surveycited by 68
  12. 2021ACTION-Net: Multipath Excitation for Action Recognitioncited by 63
  13. 2023From Chaos Comes Order: Ordering Event Representations for Object Recognition and Detectioncited by 52
  14. 2022HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensorscited by 47
  15. 2020MVFNet: Multi-View Fusion Network for Efficient Video Recognitioncited by 36
  16. 2024ExACT: Language-guided Conceptual Reasoning and Uncertainty Estimation for Event-based Action Recognition and Morecited by 33
  17. 2023SpikePoint: An Efficient Point-based Spiking Neural Network for Event Cameras Action Recognitioncited by 30
  18. 2021EventDrop: data augmentation for event-based learningcited by 28
  19. 2019Collaborative Spatio-temporal Feature Learning for Video Action Recognitioncited by 24
  20. 2024Hypergraph-based Multi-View Action Recognition using Event Camerascited by 19
  21. 2023Event Voxel Set Transformer for Spatiotemporal Representation Learning on Event Streamscited by 17
  22. 2024DailyDVS-200: A Comprehensive Benchmark Dataset for Event-Based Action Recognitioncited by 17
  23. 2025Temporal Regularization Makes Your Video Generator Strongercited by 10
  24. 2023A Dynamic Graph CNN with Cross-Representation Distillation for Event-Based Recognitioncited by 7
  25. 2025RGB-Event based Pedestrian Attribute Recognition: A Benchmark Dataset and An Asymmetric RWKV Fusion Frameworkcited by 7
  26. 2024ShapeAug: Occlusion Augmentation for Event Camera Datacited by 6
  27. 2025Event Masked Autoencoder: Point-wise Action Recognition with Event-Based Camerascited by 4
  28. 2024EventZoom: A Progressive Approach to Event-Based Data Augmentation for Enhanced Neuromorphic Visioncited by 2
  29. 2024Fourier-based Action Recognition for Wildlife Behavior Quantification with Event Camerascited by 2
  30. 2024Efficient Gesture Recognition on Spiking Convolutional Networks Through Sensor Fusion of Event-Based and Depth Datacited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Event-based Action Recognition by Pre-Training on Multi-Frame Representationscited by 0