TACO: Benchmarking Generalizable Bimanual Tool-ACtion-Object Understanding

arXiv:2401.08399v2 Announce Type: replace
Abstract: Humans commonly work with multiple objects in daily life and can intuitively transfer manipulation skills to novel objects by understanding object functional regularities. However, existing technical approaches for analyzing and synthesizing hand-object manipulation are mostly limited to handling a single hand and object due to the lack of data support. To address this, we construct TACO, an extensive bimanual hand-object-interaction dataset spanning a large variety of tool-action-object compositions for daily human activities. TACO contains 2.5K …

arxiv benchmarking cs.cv object tool type understanding