AI Paper Atlas

Research map / Architectures and efficiency / Spiking networks

Time-Ordered Recent Event (TORE) Volumes for Event Cameras

R. Wes Baldwin, Ruixu Liu, Mohammed Almatrafi, Vijayan K. Asari, Keigo Hirakawa

TPAMI 2022 · Architectures and efficiency › Spiking networks · approach: Event-camera spiking networks · 141 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 EDnCNN representation with a 9x9x14 TORE volumedenoising CNN · DVSNOISE20RPMD: 50.0 -> 43.6Improved
use TORE denoiser instead of raw noisy eventsevent denoising · DVSNOISE20RPMD: 222.0 -> 43.6Improved
TORE vs EDnCNN on LabFast scenedenoising CNN · DVSNOISE20 LabFastRPMD: 61 -> 67Hurt
TORE-based U-Net instead of E2VIDimage reconstruction · ECDMSE: 0.06 -> 0.05Improved
TORE-based U-Net instead of E2VIDimage reconstruction · ECDSSIM: 0.56 -> 0.55No clear effect
use TORE volumes with GoogLeNet instead of IETSclassification · N-CARSaccuracy: 0.976 -> 0.977Improved
use TORE volumes instead of SLAYER SNNclassification · SL-ANIMALS-DVSaccuracy: 0.780 -> 0.851Improved
use TORE volumes instead of RG-CNNclassification · ASL-DVSaccuracy: 0.901 -> 0.996Improved
use TORE volumes instead of Event Cloudsclassification · DVS128 Gestureaccuracy: 0.953 -> 0.962Improved
percentage split instead of 15 samples per class testTORE classifier · N-Caltech101accuracy: 79.8% -> 83.4%Improved
replace DHP19 representation with TORE volumes (camera 2)2D pose CNN · DHP19MPJPE (pixels): 7.18 -> 5.07Improved
replace DHP19 representation with TORE volumes (camera 3)2D pose CNN · DHP19MPJPE (pixels): 6.87 -> 5.77Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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