AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

The Curious Robot: Learning Visual Representations via Physical Interactions

Lerrel Pinto, Dhiraj Gandhi, Yuanfeng Han, Yong-Lae Park, Abhinav Gupta

ECCV 2016 · Vision-language and multimodal › Human and embodied modeling · approach: Language-grounded visual concept learning · 162 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 grasp task (ablation)robot multi-task ConvNet · ImageNet Householdaccuracy: 0.309 -> 0.354Improved
add the grasp task (ablation)robot multi-task ConvNet · UW RGB-Daccuracy: 0.632 -> 0.693Improved
add the grasp task (ablation)robot multi-task ConvNet · Caltech-256accuracy: 0.263 -> 0.317Improved
add the push task (ablation)robot multi-task ConvNet · UW RGB-Daccuracy: 0.710 -> 0.693Hurt
add the push task (ablation)robot multi-task ConvNet · Caltech-256accuracy: 0.279 -> 0.317Improved
add the push task (ablation)robot multi-task ConvNet · ImageNet Householdaccuracy: 0.356 -> 0.354No clear effect
add the poke task (ablation)robot multi-task ConvNet · ImageNet Householdaccuracy: 0.342 -> 0.354Improved
add the poke task (ablation)robot multi-task ConvNet · Caltech-256accuracy: 0.289 -> 0.317Improved
add the identity task (ablation)robot multi-task ConvNet · ImageNet Householdaccuracy: 0.324 -> 0.354Improved
add the identity task (ablation)robot multi-task ConvNet · UW RGB-Daccuracy: 0.711 -> 0.693Hurt
train on robot interaction data instead of random initAlexNet-style root network · ImageNet Householdaccuracy: 0.250 -> 0.354Improved
train on robot interaction data instead of random initAlexNet-style root network · UW RGBDaccuracy: 0.468 -> 0.693Improved

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