AI Paper Atlas

Research map / Video / Video segmentation and tracking

S2N: Suppression-Strengthen Network for Event-Based Recognition under Variant Illuminations

Zengyu Wan, Yang Wang, Ganchao Tan, Yang Cao, Zheng-Jun Zha

ECCV 2022 · Video › Video segmentation and tracking · approach: Event-based video reconstruction · 6 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add exposure loss Le to NSN training (ablation)S2N · DVSGesture ablation (train S4, test S2 natural)accuracy (%): 67.0 -> 92.1Improved
add Ln loss to NSN training (ablation)S2N · DVSGesture ablation (train S4, test S2 natural)accuracy (%): 86.6 -> 92.1Improved
add Lc loss to NSN training (ablation)S2N · DVSGesture ablation (train S4, test S2 natural)accuracy (%): 88.2 -> 92.1Improved
add Noise Suppression Network in front of FSN (ablation)S2N · DVSGesture ablation (train S4, test S2 natural)accuracy (%): 84.1 -> 92.1Improved
replace I3D with Feature Strengthen Network after NSN (ablation)S2N · DVSGesture ablation (train S4, test S2 natural)accuracy (%): 75.5 -> 92.1Improved
add Evolution-aware Module to FSN (ablation)FSN · DVSGesture ablation (train S4, test S2 natural)accuracy (%): 77.4 -> 84.1Improved
use density-adaptive CDC instead of CDC (ablation)FSN · DVSGesture ablation (train S4, test S2 natural)accuracy (%): 74.5 -> 77.4Improved
add NSN denoising to I3DI3D · DVSGesture (train S4, test S3)accuracy (%): 78.4 -> 82.0Improved
add VN denoising to I3DI3D · DVSGesture (train S4, test S3)accuracy (%): 78.4 -> 76.2Hurt
add YN denoising to I3DI3D · DVSGesture (train S4, test S0)accuracy (%): 90.3 -> 83.7Hurt
add VN denoising to ESTEST · DAVIS346Character (train L0 300lux, test all)accuracy (%): 29.4 -> 47.7Improved
replace denoise+recognizer pipelines with S2NS2N · DVSGesture (train S4 lab, test all 5 scenes)accuracy (%): 85.3 -> 94.7Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy