AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

TESPEC: Temporally-Enhanced Self-Supervised Pretraining for Event Cameras

Mohammad Mohammadi, Ziyi Wu, Igor Gilitschenski

ICCV 2025 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Pretext-task visual pre-training · 2 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 masking (50%) versus autoencoding with 0% masking (ablation)TESPEC · DSEC semantic segmentationmIoU: 55.619 -> 62.774Improved
raise masking ratio from 25% to 50% (ablation)TESPEC · DSEC semantic segmentationmIoU: 61.625 -> 62.774Improved
raise masking ratio from 50% to 75% (ablation)TESPEC · DSEC semantic segmentationmIoU: 62.774 -> 61.812Hurt
reconstruct improved intensity video instead of event histograms (ablation)TESPEC · DSEC semantic segmentationmIoU: 60.430 -> 62.774Improved
use proposed global intensity estimation instead of prior per-pixel estimation (ablation)TESPEC · DSEC semantic segmentationmIoU: 60.493 -> 62.774Improved
use proposed global intensity estimation instead of prior per-pixel estimation (ablation)TESPEC · DDD17 semantic segmentationmIoU: 63.835 -> 65.187Improved
set normalization factor N to 5,000 instead of 200,000 (ablation)TESPEC · DSEC semantic segmentationmIoU: 60.059 -> 62.774Improved
set normalization factor N to 5,000 instead of 500 (ablation)TESPEC · DSEC semantic segmentationmIoU: 61.742 -> 62.774Improved
pre-train on 1Mpx instead of Gen1 (ablation)TESPEC · DSEC semantic segmentationmIoU: 60.128 -> 62.774Improved
compute MSE on normalized patches (ablation)TESPEC · DSEC semantic segmentationmIoU: 61.792 -> 62.774Improved
use MAE objective instead of CPC (ablation)TESPEC · DSEC semantic segmentationmIoU: 59.921 -> 62.774Improved
use MAE objective instead of ECDDP contrastive loss (ablation)TESPEC · DSEC semantic segmentationmIoU: 61.012 -> 62.774Improved

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