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

• URL: http://arxiv.org/abs/2601.17391v1
• Date: Sat, 24 Jan 2026 09:24:42 GMT
• Title: SMV-EAR: Bring Spatiotemporal Multi-View Representation Learning into Efficient Event-Based Action Recognition
• Authors: Rui Fan, Weidong Hao,
• Abstract summary: Event action recognition (EAR) offers privacy-protecting and efficiency advantages where temporal motion dynamics is of great importance.<n>This paper reexamines the key SMVRL design stages for EAR and proposes a principled multi-view representation through translation-invariant dense conversion of sparse events.<n>We show that Top-1 accuracy gains over existing SMVRL EOR method with surprising 30.1% reduced parameters and 30.2% lower computations, establishing our framework as a novel and powerful EAR paradigm.
• Score: 4.322175390073132
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• HoloEv-Net: Efficient Event-based Action Recognition via Holographic Spatial Embedding and Global Spectral Gating [0.571097144710995]
  Event-based Action Recognition (EAR) has attracted significant attention due to high temporal resolution and high dynamic range of event cameras.<n>Existing methods typically suffer from (i) the computational redundancy of dense voxel representations, (ii) structural redundancy inherent in multi-branch architectures, and (iii) the under-utilization of spectral information in capturing global motion patterns.
  arXiv  Detail & Related papers  (2026-02-04T03:42:42Z)
• USV: Unified Sparsification for Accelerating Video Diffusion Models [11.011602744993942]
  Unified Sparsification for Video diffusion models is an end-to-end trainable framework.<n>It orchestrates sparsification across both the model's internal computation and its sampling process.<n>It achieves up to 83.3% speedup in the denoising process and 22.7% end-to-end acceleration, while maintaining high visual fidelity.
  arXiv  Detail & Related papers  (2025-12-05T14:40:06Z)
• Dual-Stream Diffusion for World-Model Augmented Vision-Language-Action Model [62.889356203346985]
  We propose DUal-STream diffusion (DUST), a world-model augmented VLA framework that handles the modality conflict.<n>DUST achieves up to 6% gains over a standard VLA baseline and implicit world-modeling methods.<n>On real-world tasks with the Franka Research 3, DUST outperforms baselines in success rate by 13%.
  arXiv  Detail & Related papers  (2025-10-31T16:32:12Z)
• Efficient Spatial-Temporal Modeling for Real-Time Video Analysis: A Unified Framework for Action Recognition and Object Tracking [0.0]
  Real-time video analysis remains a challenging problem in computer vision.<n>We present a unified framework that leverages advanced spatial-temporal modeling techniques for simultaneous action recognition and object tracking.<n>Our method achieves state-of-the-art performance on standard benchmarks while maintaining real-time inference speeds.
  arXiv  Detail & Related papers  (2025-07-30T06:49:11Z)
• Multi-Scale Spectral Attention Module-based Hyperspectral Segmentation in Autonomous Driving Scenarios [3.437245452211197]
  This paper introduces a Multi-scale Spectral Attention Module (MSAM) that enhances spectral feature extraction.<n>By integrating MSAM into UNet's skip connections (UNet-SC), our proposed UNet-MSAM achieves significant improvements in semantic segmentation performance.
  arXiv  Detail & Related papers  (2025-06-23T14:24:20Z)
• CRIA: A Cross-View Interaction and Instance-Adapted Pre-training Framework for Generalizable EEG Representations [52.251569042852815]
  CRIA is an adaptive framework that utilizes variable-length and variable-channel coding to achieve a unified representation of EEG data across different datasets.<n>The model employs a cross-attention mechanism to fuse temporal, spectral, and spatial features effectively.<n> Experimental results on the Temple University EEG corpus and the CHB-MIT dataset show that CRIA outperforms existing methods with the same pre-training conditions.
  arXiv  Detail & Related papers  (2025-06-19T06:31:08Z)
• Dual-Path Enhancements in Event-Based Eye Tracking: Augmented Robustness and Adaptive Temporal Modeling [0.0]
  Event-based eye tracking has become a pivotal technology for augmented reality and human-computer interaction.<n>Existing methods struggle with real-world challenges such as abrupt eye movements and environmental noise.<n>We introduce two key advancements. First, a robust data augmentation pipeline incorporating temporal shift, spatial flip, and event deletion improves model resilience.<n>Second, we propose KnightPupil, a hybrid architecture combining an EfficientNet-B3 backbone for spatial feature extraction, a bidirectional GRU for contextual temporal modeling, and a Linear Time-Varying State-Space Module.
  arXiv  Detail & Related papers  (2025-04-14T07:57:22Z)
• ReCoM: Realistic Co-Speech Motion Generation with Recurrent Embedded Transformer [58.49950218437718]
  We present ReCoM, an efficient framework for generating high-fidelity and generalizable human body motions synchronized with speech.<n>The core innovation lies in the Recurrent Embedded Transformer (RET), which integrates Dynamic Embedding Regularization (DER) into a Vision Transformer (ViT) core architecture.<n>To enhance model robustness, we incorporate the proposed DER strategy, which equips the model with dual capabilities of noise resistance and cross-domain generalization.
  arXiv  Detail & Related papers  (2025-03-27T16:39:40Z)
• Efficient High-Resolution Visual Representation Learning with State Space Model for Human Pose Estimation [60.80423207808076]
  Capturing long-range dependencies while preserving high-resolution visual representations is crucial for dense prediction tasks such as human pose estimation.<n>We propose the Dynamic Visual State Space (DVSS) block, which augments visual state space models with multi-scale convolutional operations.<n>We build HRVMamba, a novel model for efficient high-resolution representation learning.
  arXiv  Detail & Related papers  (2024-10-04T06:19:29Z)
• S^2Former-OR: Single-Stage Bi-Modal Transformer for Scene Graph Generation in OR [50.435592120607815]
  Scene graph generation (SGG) of surgical procedures is crucial in enhancing holistically cognitive intelligence in the operating room (OR) Previous works have primarily relied on multi-stage learning, where the generated semantic scene graphs depend on intermediate processes with pose estimation and object detection. In this study, we introduce a novel single-stage bi-modal transformer framework for SGG in the OR, termed S2Former-OR.
  arXiv  Detail & Related papers  (2024-02-22T11:40:49Z)
• Recurrent Vision Transformers for Object Detection with Event Cameras [62.27246562304705]
  We present Recurrent Vision Transformers (RVTs), a novel backbone for object detection with event cameras. RVTs can be trained from scratch to reach state-of-the-art performance on event-based object detection. Our study brings new insights into effective design choices that can be fruitful for research beyond event-based vision.
  arXiv  Detail & Related papers  (2022-12-11T20:28:59Z)
• HALSIE: Hybrid Approach to Learning Segmentation by Simultaneously Exploiting Image and Event Modalities [6.543272301133159]
  Event cameras detect changes in per-pixel intensity to generate asynchronous event streams. They offer great potential for accurate semantic map retrieval in real-time autonomous systems. Existing implementations for event segmentation suffer from sub-based performance. We propose hybrid end-to-end learning framework HALSIE to reduce inference cost by up to $20times$ versus art.
  arXiv  Detail & Related papers  (2022-11-19T17:09:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.