AI Paper Atlas

Research map / 3D vision / 3D generation

Binge Watching: Scaling Affordance Learning From Sitcoms

CVPR 2017 · 3D vision › 3D generation · approach: Scene-aware human motion synthesis · 81 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Increase training data from 2.5K to 25K examples (ablation)Affordance pose classifier · Friends test setTop-1 accuracy: 11.7% -> 14.9%Helped
Increase training data from 2.5K to 25K examples (ablation)Affordance pose classifier · Friends test setTop-5 accuracy: 41.8% -> 50.9%Helped
Use the two-step pose-classification and VAE approach instead of heatmap regressionAffordance pose prediction · Friends test setTop-1 accuracy: 8.4 % -> 14.9%Helped
Use the two-step pose-classification and VAE approach instead of heatmap regressionAffordance pose prediction · Friends test setTop-5 accuracy: 47.3% -> 50.9%Helped
Use heatmap regression instead of the proposed approachAffordance pose plausibility scoring · Friends scenes with positive and negative posesRecall at high-recall regimesHelped

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