3 accepted papers
We consider the problem of generating mobile manipulation instructions based on a target object image and receptacle image. Conventional image captioning models are not able to generate appropriate instructions because their architectures are typically optimized for single-image. In this study, we p…
We focus on the task of identifying the location of target regions from a natural language instruction and a front camera image captured by a mobility. This task is challenging because it requires both existence prediction and segmentation mask generation, particularly for stuff-type target regions…
We consider the problem of generating free-form mobile manipulation instructions based on a target object image and receptacle image. Conventional image captioning models are not able to generate appropriate instructions because their architectures are typically optimized for single-image. In this s