SOTAVerified

Affordance Detection

Affordance detection refers to identifying the potential action possibilities of objects in an image, which is an important ability for robot perception and manipulation.

Image source: Object-Based Affordances Detection with Convolutional Neural Networks and Dense Conditional Random Fields

Unlike other visual or physical properties that mainly describe the object alone, affordances indicate functional interactions of object parts with humans.

Papers

Showing 11–20 of 23 papers

TitleStatusHype
Affordance detection with Dynamic-Tree Capsule NetworksCode0
Detecting Object States vs Detecting Objects: A New Dataset and a Quantitative Experimental StudyCode0
Weakly Supervised Affordance DetectionCode0
Which objects help me to act effectively? Reasoning about physically-grounded affordances—0
Detect, anticipate and generate: Semi-supervised recurrent latent variable models for human activity modeling—0
Detecting Affordances by Visuomotor Simulation—0
Egocentric affordance detection with the one-shot geometry-driven Interaction Tensor—0
Interpretable Affordance Detection on 3D Point Clouds with Probabilistic Prototypes—0
Multi-Modal Trip Hazard Affordance Detection On Construction Sites—0
Scene Understanding for Autonomous Manipulation with Deep Learning—0
Show:102550
← PrevPage 2 of 3Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DGCNNAIOU0.18—Unverified
#ModelMetricClaimedVerifiedStatus
1DGCNNAIOU0.14—Unverified
#ModelMetricClaimedVerifiedStatus
1DGCNNAIOU0.13—Unverified
#ModelMetricClaimedVerifiedStatus
1DGCNNAIOU0.16—Unverified