LLM4SGG: Large Language Model for Weakly Supervised Scene Graph Generation

arXiv:2310.10404v5 Announce Type: cross
Abstract: Weakly-Supervised Scene Graph Generation (WSSGG) research has recently emerged as an alternative to the fully-supervised approach that heavily relies on costly annotations. In this regard, studies on WSSGG have utilized image captions to obtain unlocalized triplets while primarily focusing on grounding the unlocalized triplets over image regions. However, they have overlooked the two issues involved in the triplet formation process from the captions: 1) Semantic over-simplification issue arises when extracting triplets from captions, where fine-grained …

abstract annotations arxiv captions cs.ai cs.cv cs.lg graph image language language model large language large language model regard research studies type weakly-supervised