Human-Centric Spatio-Temporal Video Grounding With Visual Transformers

• Published in: IEEE transactions on circuits and systems for video technology Vol. 32; no. 12; pp. 8238 - 8249
• Main Authors: Tang, Zongheng, Liao, Yue, Liu, Si, Li, Guanbin, Jin, Xiaojie, Jiang, Hongxu, Yu, Qian, Xu, Dong
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.12.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: dataset; Datasets; Electron tubes; Grounding; Localization; Location awareness; Power transformers; Spatial temporal resolution; Spatio-temporal grounding; transformer; Transformers; Video; Visualization

In this work, we introduce a novel task - Human-centric Spatio-Temporal Video Grounding (HC-STVG). Unlike the existing referring expression tasks in images or videos, by focusing on humans, HC-STVG aims to localize a spatio-temporal tube of the target person from an untrimmed video based on a given...