Code supporting the paper "Making Every Event Count: Balancing Data Efficiency and Accuracy in Event Camera Subsampling"
Code supporting the paper "Making Every Event Count: Balancing Data Efficiency and Accuracy in Event Camera Subsampling"
Description
Official codebase for the CVPR 2025 workshop paper:
> Making Every Event Count: Balancing Data Efficiency and Accuracy in Event Camera Subsampling
> Hesam Araghi, Jan van Gemert, Nergis Tomen
> Delft University of Technology
> [Paper PDF: http://arxiv.org/abs/2505.21187
🔍 Overview
Event cameras offer high temporal resolution and power efficiency, but their high event rates can overload processing systems. We explore six hardware-friendly event subsampling methods and assess their impact on event-based video classification.
🔑 Key Contributions
📊 Systematic evaluation of 6 causal, hardware-friendly subsampling methods.
🧠 Proposal of a causal density-based subsampling technique to test the hypothesis that dense regions contain more information.
📉 Analysis of accuracy–efficiency trade-offs across three benchmark datasets.
Reference papers
Mentions
- 1.Author(s): Ethan Delaney, Roshan George, Tim Brophy, Imad Ali Shah, Enda Ward, Edward Jones, Brian Deegan, Martin GlavinPublished in 202610.1109/ojvt.2026.3744802
- 2.Author(s): Raj Adhikari, Tao Han, Nirwan AnsariPublished in IEEE Communications Magazine by Institute of Electrical and Electronics Engineers (IEEE) in 2026, page: 92-9810.1109/mcom.001.2500776
- 3.Author(s): Kyeongpil Min, Jongin Choi, Woojoo LeePublished in Micromachines by MDPI AG in 2026, page: 17610.3390/mi17020176
- 1.Author(s): Chowdhury, Sayeed Shafayet, Sharmin, Ruhi, Ahmed, Syed IshtiaquePublished in 202610.48550/arxiv.2609.22295
- 2.Author(s): Araghi, Hesam, van Gemert, Jan, Tomen, NergisPublished in 202610.48550/arxiv.2608.11075
- 3.Author(s): Wani, Mohd Ubaid, Atito, Sara, Kittler, Josef, Awais, MuhammadPublished in 202610.48550/arxiv.2610.01754
- 4.Author(s): Fang, Wei, Panda, PriyadarshiniPublished in 202510.48550/arxiv.2504.15371