TextPSG: Panoptic Scene Graph Generation from Textual Descriptions.

Chengyang Zhao Yikang Shen Zhenfang Chen Mingyu Ding Chuang Gan

Published in: ICCV (2023)

Keyphrases

textual descriptions
video sequences
graph structure
semantic representation
image sequences
directed graph
computer vision
metadata
keywords
semantic information
image set
semantic concepts