paper-with-me

Affordance Recognition

2개 벤치마크 · 논문 14편 · 이 태스크의 논문 보기 →

Benchmarks

HICO-DET

결과 8개

Most implemented

Papers

ENACT: Evaluating Embodied Cognition with World Modeling of Egocentric Interaction

2025-11-26 · Qineng Wang, Wenlong Huang, Yu Zhou, Hang Yin 외 arxiv

Embodied cognition argues that intelligence arises from sensorimotor interaction rather than passive observation. It raises an intriguing question: do modern vision-language models (VLMs), trained largely in a disembodie…

Visual Question AnsweringAffordance Recognition

RoboAfford++: A Generative AI-Enhanced Dataset for Multimodal Affordance Learning in Robotic Manipulation and Navigation

2025-11-16 · Xiaoshuai Hao, Yingbo Tang, Lingfeng Zhang, Yanbiao Ma 외 arxiv

Robotic manipulation and navigation are fundamental capabilities of embodied intelligence, enabling effective robot interactions with the physical world. Achieving these capabilities requires a cohesive understanding of …

Affordance RecognitionScene UnderstandingObject RecognitionQuestion Answering

Object Affordance Recognition and Grounding via Multi-scale Cross-modal Representation Learning

2025-08-02 · Xinhang Wan, Dongqiang Gou, Xinwang Liu, En Zhu 외 arxiv

A core problem of Embodied AI is to learn object manipulation from observation, as humans do. To achieve this, it is important to localize 3D object affordance areas through observation such as images (3D affordance grou…

Representation LearningAffordance Recognition

3DAffordSplat: Efficient Affordance Reasoning with 3D Gaussians

2025-04-15 · Zeming Wei, Junyi Lin, Yang Liu, Weixing Chen 외

3D affordance reasoning is essential in associating human instructions with the functional regions of 3D objects, facilitating precise, task-oriented manipulations in embodied AI. However, current methods, which predomin…

3DGSAffordance Recognition

Fine-grained Affordance Annotation for Egocentric Hand-Object Interaction Videos

2023-02-07 · Zecheng Yu, Yifei HUANG, Ryosuke Furuta, Takuma Yagi 외

Object affordance is an important concept in hand-object interaction, providing information on action possibilities based on human motor capacity and objects' physical property thus benefiting tasks such as action antici…

Action AnticipationAction RecognitionAffordance RecognitionHuman-Object Interaction Detection+2

AROS: Affordance Recognition with One-Shot Human Stances

2022-10-21 · Abel Pacheco-Ortega, Walterio Mayol-Cuevas

We present AROS, a one-shot learning approach that uses an explicit representation of interactions between highly-articulated human poses and 3D scenes. The approach is one-shot as the method does not require re-training…

Affordance RecognitionOne-Shot Learning

전체 14편 보기 →