Integrating Language-Derived Appearance Elements with Visual Cues in Pedestrian Detection

arXiv:2311.01025v2 Announce Type: replace
Abstract: Large language models (LLMs) have shown their capabilities in understanding contextual and semantic information regarding knowledge of instance appearances. In this paper, we introduce a novel approach to utilize the strengths of LLMs in understanding contextual appearance variations and to leverage this knowledge into a vision model (here, pedestrian detection). While pedestrian detection is considered one of the crucial tasks directly related to our safety (e.g., intelligent driving systems), it is challenging because of varying …

abstract arxiv capabilities cs.cv detection information instance knowledge language language models large language large language models llms novel paper pedestrian semantic type understanding visual visual cues