Detecting Object States vs Detecting Objects: A New Dataset and a Quantitative Experimental Study
This work addresses the understudied problem of detecting object states in images, which is crucial for robotics and intelligent agents, but it is incremental as it primarily provides a dataset and baseline study.
The authors tackled the problem of object state detection (SD) by introducing the Object State Detection Dataset (OSDD) with over 19,000 annotations and conducted experiments showing that SD is harder than object detection (OD), establishing a baseline for future research.
The detection of object states in images (State Detection - SD) is a problem of both theoretical and practical importance and it is tightly interwoven with other important computer vision problems, such as action recognition and affordance detection. It is also highly relevant to any entity that needs to reason and act in dynamic domains, such as robotic systems and intelligent agents. Despite its importance, up to now, the research on this problem has been limited. In this paper, we attempt a systematic study of the SD problem. First, we introduce the Object State Detection Dataset (OSDD), a new publicly available dataset consisting of more than 19,000 annotations for 18 object categories and 9 state classes. Second, using a standard deep learning framework used for Object Detection (OD), we conduct a number of appropriately designed experiments, towards an in-depth study of the behavior of the SD problem. This study enables the setup of a baseline on the performance of SD, as well as its relative performance in comparison to OD, in a variety of scenarios. Overall, the experimental outcomes confirm that SD is harder than OD and that tailored SD methods need to be developed for addressing effectively this significant problem.