Self-Explainable Affordance Learning with Embodied Caption

arXiv:2404.05603v1 Announce Type: new
Abstract: In the field of visual affordance learning, previous methods mainly used abundant images or videos that delineate human behavior patterns to identify action possibility regions for object manipulation, with a variety of applications in robotic tasks. However, they encounter a main challenge of action ambiguity, illustrated by the vagueness like whether to beat or carry a drum, and the complexities involved in processing intricate scenes. Moreover, it is important for human intervention to rectify robot …

abstract applications arxiv behavior challenge cs.ai cs.cv embodied however human identify images manipulation object patterns possibility robotic tasks type videos visual