AI Paper Atlas

Research map / Video / Video segmentation and tracking

End-to-End Learning of Representations for Asynchronous Event-Based Data

Daniel Gehrig, Antonio Loquercio, Konstantinos G. Derpanis, Davide Scaramuzza

ICCV 2019 · Video › Video segmentation and tracking · approach: Event-based video reconstruction · 424 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
learn the temporal kernel end-to-end instead of the trilinear kernel (ablation)EST (time stamps) · N-Carsaccuracy: 0.917 -> 0.925Improved
learn the temporal kernel end-to-end instead of the trilinear kernel (ablation)EST (time stamps) · N-Caltech101accuracy: 0.787 -> 0.817Improved
use handcrafted alpha kernel instead of trilinear kernel (ablation)EST (time stamps) · N-Caltech101accuracy: 0.787 -> 0.739Hurt
use handcrafted exponential kernel instead of trilinear kernel (ablation)EST (time stamps) · N-Carsaccuracy: 0.917 -> 0.909Hurt
learn the temporal kernel end-to-end instead of the trilinear kernel (ablation)EST (time stamps) · MVSEC indoor_flying2AEE: 1.71 -> 1.38Improved
learn the temporal kernel end-to-end instead of the trilinear kernel (ablation)EST (time stamps) · MVSEC indoor_flying3% outlier: 8.29 -> 6.47Improved
use alpha or exponential kernel instead of trilinear kernel (ablation)EST (time stamps) · MVSEC indoor_flying2AEE: 1.71 -> 1.52Improved
retain temporal dimension (Voxel Grid) instead of summing over it (Two-Channel Image) (ablation)event representation with time stamp measurements · MVSEC indoor_flying2AEE: 1.97 -> 1.70Improved
separate polarity instead of summing over polarities (ablation)event representations · N-Cars / N-Caltech101accuracy: decrease in accuracy of up to 7%Improved
use time stamps as measurement in EST instead of polarity (ablation)EST (trilinear) · N-Caltech101accuracy: 0.789 -> 0.787No clear effect
increase temporal bins from 9 to 16 (ablation)learned EST · N-Carsaccuracy: 0.925 -> 0.923No clear effect
increase temporal bins from 9 to 16 (ablation)learned EST · N-Caltech101accuracy: 0.817 -> 0.837Improved

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