AI Paper Atlas

Research map / Video / Video segmentation and tracking

A Differentiable Recurrent Surface for Asynchronous Event-Based Data

Marco Cannici, Marco Ciccone, Andrea Romanoni, Matteo Matteucci

ECCV 2020 · Video › Video segmentation and tracking · approach: Event-based video reconstruction · 129 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
replace Events-to-Video reconstruction with Matrix-LSTMResNet18-Ev2Vid · N-Carsaccuracy: 91.0 -> 95.80Improved
replace Events-to-Video reconstruction with Matrix-LSTMResNet18-Ev2Vid · N-Caltech101accuracy: 86.6 -> 84.12Hurt
replace hand-crafted EV-FlowNet surface with Matrix-LSTM (2 bins)EV-FlowNet · MVSEC indoor_flying2AEE: 1.72 -> 1.194Improved
apply ImageNet frame normalization to Matrix-LSTM output (ablation)ResNet18-Ev2Vid ts absolute · N-Carsaccuracy: 95.75 -> 95.22No clear effect
use ts relative instead of ts absolute time feature (ablation)ResNet18-Ev2Vid · N-Carsaccuracy: 95.32 -> 94.77No clear effect
add global ts feature to local ts (2 bins) (ablation)ResNet18-EST · N-Carsaccuracy: 92.75 -> 93.46Improved
add SELayer (2 bins) (ablation)ResNet18-EST · N-Carsaccuracy: 93.46 -> 93.71Improved
increase bins from 2 to 16 (ablation)ResNet18-EST · N-Carsaccuracy: 93.46 -> 92.01Hurt
increase output channels from 4 to 16 (1 bin) (ablation)ResNet18-EST · N-Carsaccuracy: 93.88 -> 94.37Improved
use Matrix-LSTM instead of ConvLSTM (3x3, delay relative) (ablation)ResNet18-Ev2Vid · N-Carsaccuracy: 92.33 -> 95.05Improved
use 2 bins instead of 1 bin (ablation)Matrix-LSTM + EV-FlowNet · MVSEC indoor_flying2AEE: 1.642 -> 1.194Improved
increase bins from 2 to 4 (ablation)Matrix-LSTM + EV-FlowNet · MVSEC indoor_flying2AEE: 1.194 -> 1.505Hurt

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