Visual Commonsense Causal Reasoning From a Still Image

Even from a still image, humans exhibit the ability to ratiocinate diverse visual cause-and-effect relationships of events preceding, succeeding, and extending beyond the given image scope. Previous work on commonsense causal reasoning (CCR) aimed at understanding general causal dependencies among c...

תיאור מלא

מידע ביבליוגרפי

Principais autores:	Xiaojing Wu, Rui Guo, Qin Li, Ning Zhu
פורמט:	Artigo
שפה:	Inglês
יצא לאור:	IEEE 2025-01-01
סדרה:	IEEE Access
נושאים:	Visual commonsense reasoning commonsense reasoning visual event reasoning multimodal large language model
גישה מקוונת:	https://ieeexplore.ieee.org/document/10950140/
תגים:	הוספת תג אין תגיות, היה/י הראשונ/ה לתייג את הרשומה!