VLPrompt: Vision-Language Prompting for Panoptic Scene Graph Generation

arXiv:2311.16492v2 Announce Type: replace
Abstract: Panoptic Scene Graph Generation (PSG) aims at achieving a comprehensive image understanding by simultaneously segmenting objects and predicting relations among objects. However, the long-tail problem among relations leads to unsatisfactory results in real-world applications. Prior methods predominantly rely on vision information or utilize limited language information, such as object or relation names, thereby overlooking the utility of language information. Leveraging the recent progress in Large Language Models (LLMs), we propose to use language information to …

arxiv cs.cv graph language prompting replace type vision vision-language