Grounded situation recognition under data scarcity

• Published in: Scientific reports Vol. 14; no. 1; pp. 25195 - 16
• Main Authors: Zhou, Jing, Liu, Zhiqiang, Hu, Siying, Li, Xiaoxue, Wang, Zhiguang, Lu, Qiang
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 24.10.2024; Nature Publishing Group; Nature Portfolio
• Subjects: 639/705/117; 639/705/258; Accuracy; Classification; CLIP; Data Scarcity; Grounded Situation Recognition; Humanities and Social Sciences; Localization; multidisciplinary; Scarcity; Science; Science (multidisciplinary); Transformer; Transformer; Grounded Situation Recognition; Data Scarcity; CLIP

Grounded Situation Recognition (GSR) aims to generate structured image descriptions. For a given image, GSR needs to identify the key verb, the nouns corresponding to roles, and their bounding-box groundings. However, current GSR research demands numerous meticulously labeled images, which are labor...