Event-based Action Recognition by Pre-Training on Multi-Frame Representations

cs.CV

Submitted: 2026-10-09

Updated: 2026-10-09

Code: https://github.com/nrthby/event-action-mae

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• BEiT: BERT Pre-Training of Image Transformers
• HoloEv-Net: Efficient Event-based Action Recognition via Holographic Spatial Embedding and Global Spectral Gating
• Decoupled Weight Decay Regularization
• Rethinking Efficient and Effective Point-based Networks for Event Camera Classification and Regression: EventMamba
• Event Masked Autoencoder: Point-wise Action Recognition with Event-Based Cameras
• DailyDVS-200: A Comprehensive Benchmark Dataset for Event-Based Action Recognition
• Event Stream based Human Action Recognition: A High-Definition Benchmark Dataset and Algorithms
• EventBind: Learning a Unified Representation to Bind Them All for Event-based Open-world Understanding

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models