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 1–10 of 23 papers

TitleStatusHype
Open-Vocabulary Affordance Detection in 3D Point CloudsCode1
Multi-label affordance mapping from egocentric visionCode1
One-Shot Affordance DetectionCode1
One-Shot Object Affordance Detection in the WildCode1
Phrase-Based Affordance Detection via Cyclic Bilateral InteractionCode1
Affordance Transfer Learning for Human-Object Interaction DetectionCode1
3D AffordanceNet: A Benchmark for Visual Object Affordance UnderstandingCode1
Detecting Affordances by Visuomotor Simulation—0
Detect, anticipate and generate: Semi-supervised recurrent latent variable models for human activity modeling—0
3D-AffordanceLLM: Harnessing Large Language Models for Open-Vocabulary Affordance Detection in 3D Worlds—0
Show:102550
← PrevPage 1 of 3Next →

Benchmark Results

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