AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

Visual Memorability for Robotic Interestingness via Unsupervised Online Learning

Chen Wang, Wenshan Wang, Yuheng Qiu, Yafei Hu, Sebastian Scherer

ECCV 2020 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Vision-language navigation agents

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 sparse writing protocol with tangent operator (ablation)Visual memorability interestingness model · SubT Normal (delta=2)AUC-OP: 0.633 -> 0.842Improved
add sparse writing protocol with tangent operator (ablation)Visual memorability interestingness model · SubT Difficult (delta=2)AUC-OP: 0.373 -> 0.585Improved
add translational invariance (cross-correlation) to memory reading (ablation)Visual memorability interestingness model · SubT Normal (delta=2)AUC-OP: 0.510 -> 0.842Improved
add translational invariance (cross-correlation) to memory reading (ablation)Visual memorability interestingness model · SubT Difficult (delta=2)AUC-OP: 0.268 -> 0.585Improved
add short-term learning with known uninteresting scenes (ablation)Visual memorability interestingness model · SubT Normal (delta=2)AUC-OP: 0.711 -> 0.842Improved
add short-term learning with known uninteresting scenes (ablation)Visual memorability interestingness model · SubT Difficult (delta=2)AUC-OP: 0.450 -> 0.585Improved
add online learning (ablation)Visual memorability interestingness model · SubTAUC-OP: about 20% higher overall performanceImproved
use proposed method instead of baseline interestingness methodVisual memorability interestingness model · SubT Normal (delta=1)AUC-OP: 0.622 -> 0.662Improved
use proposed method instead of baseline interestingness methodVisual memorability interestingness model · SubT Difficult (delta=1)AUC-OP: 0.352 -> 0.407Improved
use proposed method instead of baseline interestingness methodVisual memorability interestingness model · SubT Difficult (delta=4)AUC-OP: 0.700 -> 0.768Improved
increase memory capacity (ablation)Visual memorability interestingness model · random tensor recallAUC-OP: reading accuracy of first tensor drops less with larger capacityImproved
raise the writing rate gamma_w from 0.2 to 1.0Visual memorability interestingness model · Drone FilmingAUC-OP: 1.0 vs 0.2Mixed

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