A survey of visual affordance recognition based on deep learning

D Chen, D Kong, J Li, S Wang… - IEEE Transactions on Big …, 2023 - ieeexplore.ieee.org
Visual affordance recognition is an important research topic in robotics, human-computer
interaction, and other computer vision tasks. In recent years, deep learning-based …

Learning affordance grounding from exocentric images

H Luo, W Zhai, J Zhang, Y Cao… - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
Affordance grounding, a task to ground (ie, localize) action possibility region in objects,
which faces the challenge of establishing an explicit link with object parts due to the diversity …

Grounding 3d object affordance from 2d interactions in images

Y Yang, W Zhai, H Luo, Y Cao… - Proceedings of the …, 2023 - openaccess.thecvf.com
Grounding 3D object affordance seeks to locate objects'" action possibilities" regions in the
3D space, which serves as a link between perception and operation for embodied agents …

One-shot transfer of affordance regions? AffCorrs!

D Hadjivelichkov, S Zwane, L Agapito… - … on Robot Learning, 2023 - proceedings.mlr.press
In this work, we tackle one-shot visual search of object parts. Given a single reference image
of an object with annotated affordance regions, we segment semantically corresponding …

RIO: A benchmark for reasoning intention-oriented objects in open environments

M Qu, Y Wu, W Liu, X Liang, J Song… - Advances in Neural …, 2024 - proceedings.neurips.cc
Intention-oriented object detection aims to detect desired objects based on specific
intentions or requirements. For instance, when we desire to" lie down and rest", we …

Noir: Neural signal operated intelligent robots for everyday activities

R Zhang, S Lee, M Hwang, A Hiranaka, C Wang… - arXiv preprint arXiv …, 2023 - arxiv.org
We present Neural Signal Operated Intelligent Robots (NOIR), a general-purpose, intelligent
brain-robot interface system that enables humans to command robots to perform everyday …

One-shot open affordance learning with foundation models

G Li, D Sun, L Sevilla-Lara… - Proceedings of the IEEE …, 2024 - openaccess.thecvf.com
Abstract We introduce One-shot Open Affordance Learning (OOAL) where a model is trained
with just one example per base object category but is expected to identify novel objects and …

Leverage interactive affinity for affordance learning

H Luo, W Zhai, J Zhang, Y Cao… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Perceiving potential" action possibilities"(ie, affordance) regions of images and learning
interactive functionalities of objects from human demonstration is a challenging task due to …

One-shot object affordance detection in the wild

W Zhai, H Luo, J Zhang, Y Cao, D Tao - International Journal of Computer …, 2022 - Springer
Affordance detection refers to identifying the potential action possibilities of objects in an
image, which is a crucial ability for robot perception and manipulation. To empower robots …

Grounded affordance from exocentric view

H Luo, W Zhai, J Zhang, Y Cao, D Tao - International Journal of Computer …, 2024 - Springer
Affordance grounding aims to locate objects'“action possibilities” regions, an essential step
toward embodied intelligence. Due to the diversity of interactive affordance, ie, the …