AI Paper Atlas

Research map / Video / Action recognition

Joint Discovery of Object States and Manipulation Actions

Jean-Baptiste Alayrac, Ivan Laptev, Josef Sivic, Simon Lacoste-Julien

ICCV 2017 · Video › Action recognition · approach: Action anticipation and latent actions · 80 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
use the at-least-one-state constraint instead of exactly-one (ablation)state-only discovery · State discovery (weakly supervised clips, average over 7 actions)precision: 0.38 -> 0.44Improved
add ordering and non-overlap constraints with learned features instead of random features (ablation)state discovery · State discovery (weakly supervised clips, average over 7 actions)precision: 0.35 -> 0.44Improved
add joint modeling with actions to state-only discoverystate discovery · State discovery (weakly supervised clips, average over 7 actions)precision: 0.44 -> 0.48Improved
add object detection score to the joint objectivejoint model · State discovery (weakly supervised clips, average over 7 actions)precision: 0.48 -> 0.51Improved
use ground-truth action features instead of predicted actions (ablation)joint model · State discovery (weakly supervised clips, average over 7 actions)precision: 0.48 -> 0.51No clear effect
add object-state term to action localization (joint model) over salient action onlyaction localization · Action localization (weakly supervised clips, average over 7 actions)precision: 0.20 -> 0.55Improved
constrain action to lie within first and last frame of object detection (ablation)action localization baseline · Action localization (weakly supervised clips, average over 7 actions)precision: 0.20 -> 0.32Improved
use ground-truth state labels as tracklet features (ablation)joint action localization · Action localization (weakly supervised clips, average over 7 actions)precision: 0.55 -> 0.59Improved
add joint modeling over state-only with detection scores in the wildstate discovery · State discovery (weakly supervised clips, average over 7 actions) in the wildprecision: 0.32 -> 0.36Improved
use curated clips instead of automatically retrieved clips (ablation)joint model · State discovery in the wildprecision: 0.36 -> 0.62Improved
use curated clips instead of automatically retrieved clips (ablation)joint model · Action localization in the wildprecision: 0.24 -> 0.44Improved
add joint modeling to action-only localization in the wildaction localization · Action localization in the wildprecision: 0.11 -> 0.24Improved

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