AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Act the Part: Learning Interaction Strategies for Articulated Object Part Discovery

Samir Yitzhak Gadre, Kiana Ehsani, Shuran Song

ICCV 2021 · Detection and segmentation › Open-set and few-shot detection · approach: Hand-object and articulated interaction · 37 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 hold action (bimanual hold+push instead of push only) (ablation)Act the Part · PartNet-Mobility MultilinkmIoU (%): 19.9 -> 54.7Improved
add hold action (bimanual hold+push instead of push only) (ablation)Act the Part · PartNet-Mobility ScissorsmIoU (%): 28.5 -> 65.6Improved
add part-aware interaction network (part memory input) vs Act-NoPart (ablation)Act the Part · PartNet-Mobility USBmIoU (%): 47.6 -> 75.3Improved
add part-aware interaction network (part memory input) vs Act-NoPart (ablation)Act the Part · PartNet-Mobility EyeglassesmIoU (%): 34.4 -> 43.0Improved
add touch feedback reward (ablation)Act the Part · PartNet-Mobility ScissorsmIoU (%): 58.0 -> 65.6Improved
add touch feedback reward (ablation)Act the Part · PartNet-Mobility MultilinkmIoU (%): 46.6 -> 54.7Improved
add touch feedback reward (ablation)Act the Part · PartNet-Mobility LightermIoU (%): 64.4 -> 62.8Hurt
add touch feedback reward (ablation)Act the Part · PartNet-Mobility KnifemIoU (%): 66.2 -> 65.9No clear effect
learned interaction policy instead of random actionsAct the Part · PartNet-Mobility MultilinkmIoU (%): 10.7 -> 54.7Improved
train on unseen categories: test on categories not seen in trainingAct the Part (Ours-Touch) · PartNet-Mobility Pliers vs ScissorsmIoU (%): 65.6 -> 64.9No clear effect
evaluate objects with three links when trained only on two-link objectsAct the Part (Ours-Touch) · PartNet-Mobility MultilinkMAPE: 0.22Mixed
use ground-truth optical-flow motion masks and optimal actions (oracle)Act the Part · PartNet-Mobility MultilinkmIoU (%): 54.7 -> 86.9Improved

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