AI Paper Atlas

Research map / Detection and segmentation / Tracking

Learning Object Permanence from Video

Aviv Shamsian, Ofri Kleinfeld, Amir Globerson, Gal Chechik

ECCV 2020 · Detection and segmentation › Tracking · approach: Transformer-based video object tracking · 20 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 the second LSTM module (Where is it) instead of an MLP (ablation)OPNet · LA-CATER (detector perception)Overall mean IoU: 78.85 -> 81.94Improved
add the second LSTM module instead of an MLP (ablation)OPNet · LA-CATER (detector perception)Occluded mean IoU: 55.32 -> 78.83Improved
add OPNet two-module design over Transformer + LSTMTransformer + LSTM · LA-CATER (detector perception)Carried mean IoU: 28.25 -> 56.04Improved
add OPNet two-module design over Transformer + LSTMTransformer + LSTM · LA-CATER (detector perception)Occluded mean IoU: 80.40 -> 78.83Mixed
replace detector with ground-truth boxes and visibility bits (ablation)OPNet (LSTM + LSTM) · LA-CATEROverall mean IoU: 81.94 -> 85.44Improved
replace detector with ground-truth boxes and visibility bits (ablation)OPNet (LSTM + LSTM) · LA-CATERCarried mean IoU: 56.04 -> 76.42Improved
replace detector with ground-truth boxes (ablation)Detector + Heuristic · LA-CATEROccluded mean IoU: 47.03 -> 30.40Hurt
remove second module under perfect perception (ablation)OPNet (LSTM + MLP) · LA-CATER (perfect perception)Occluded mean IoU: 67.79 -> 19.39Hurt
train with only visible-frame supervision plus consistency loss instead of full supervision (ablation)OPNet (LSTM + LSTM) · LA-CATERCarried mean IoU: 56.04 -> 27.50Hurt
train with only visible-frame supervision plus consistency loss (ablation)OPNet (LSTM + MLP) · LA-CATEROverall mean IoU: 78.85 -> 61.18Hurt
train with only visible-frame supervision plus consistency loss (ablation)Baseline LSTM · LA-CATEROverall mean IoU: 67.20 -> 78.09Improved
use OPNet instead of R3D + LSTMCATER snitch localization · CATERAccuracy: 60.2 -> 74.8Improved

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