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 110 of 23 papers

TitleStatusHype
Interpretable Affordance Detection on 3D Point Clouds with Probabilistic Prototypes0
3D-AffordanceLLM: Harnessing Large Language Models for Open-Vocabulary Affordance Detection in 3D Worlds0
Which objects help me to act effectively? Reasoning about physically-grounded affordances0
Multi-label affordance mapping from egocentric visionCode1
Open-Vocabulary Affordance Detection in 3D Point CloudsCode1
Affordance detection with Dynamic-Tree Capsule NetworksCode0
Phrase-Based Affordance Detection via Cyclic Bilateral InteractionCode1
Detecting Object States vs Detecting Objects: A New Dataset and a Quantitative Experimental StudyCode0
One-Shot Object Affordance Detection in the WildCode1
One-Shot Affordance DetectionCode1
Show:102550
← PrevPage 1 of 3Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DGCNNAIOU0.13Unverified