Saved in:
Bibliographic Details
Main Authors: Fan, Rui, Hao, Weidong
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.17391
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918303677546496
author Fan, Rui
Hao, Weidong
author_facet Fan, Rui
Hao, Weidong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_17391
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SMV-EAR: Bring Spatiotemporal Multi-View Representation Learning into Efficient Event-Based Action Recognition
Fan, Rui
Hao, Weidong
Computer Vision and Pattern Recognition
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.
title SMV-EAR: Bring Spatiotemporal Multi-View Representation Learning into Efficient Event-Based Action Recognition
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.17391