Supplementing Missing Visions via Dialog for Scene Graph Generations

arXiv:2204.11143v2 Announce Type: replace
Abstract: Most current AI systems rely on the premise that the input visual data are sufficient to achieve competitive performance in various computer vision tasks. However, the classic task setup rarely considers the challenging, yet common practical situations where the complete visual data may be inaccessible due to various reasons (e.g., restricted view range and occlusions). To this end, we investigate a computer vision task setting with incomplete visual input data. Specifically, we exploit the Scene …

abstract ai systems arxiv computer computer vision cs.cv current data dialog graph however performance practical setup systems tasks type via vision visual visual data