Decoupling Multimodal Transformers for Referring Video Object Segmentation

• Published in: IEEE transactions on circuits and systems for video technology Vol. 33; no. 9; p. 1
• Main Authors: Gao, Mingqi, Yang, Jinyu, Han, Jungong, Lu, Ke, Zheng, Feng, Montana, Giovanni
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.09.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Alignment; Decoupled multimodal transformers; Decoupling; Referring video object segmentation; Segmentation; Transformers; Vision; Vision-language pre-training

Referring Video Object Segmentation (RVOS) aims to segment the text-depicted object from video sequences. With excellent capabilities in long-range modelling and information interaction, transformers have been increasingly applied in existing RVOS architectures. To better leverage multimodal data, m...