Referring image segmentation aims to segment the objects referred by a natural language expression. Previous methods usually focus on designing an implicit and recurrent feature …
J Tang, G Zheng, C Shi, S Yang - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Referring image segmentation aims to segment the target referent in an image conditioning on a natural language expression. Existing one-stage methods employ per-pixel …
In this work, we address the challenging task of referring segmentation. The query expression in referring segmentation typically indicates the target object by describing its …
Z Wang, Y Lu, Q Li, X Tao, Y Guo… - Proceedings of the …, 2022 - openaccess.thecvf.com
Referring image segmentation aims to segment a referent via a natural linguistic expression. Due to the distinct data properties between text and image, it is challenging for a network to …
L Ye, Z Liu, Y Wang - IEEE Transactions on Multimedia, 2020 - ieeexplore.ieee.org
We consider referring image segmentation. It is a problem at the intersection of computer vision and natural language understanding. Given an input image and a referring …
We consider the problem of referring image segmentation. Given an input image and a natural language expression, the goal is to segment the object referred by the language …
G Feng, Z Hu, L Zhang, H Lu - Proceedings of the IEEE/CVF …, 2021 - openaccess.thecvf.com
Recently, referring image segmentation has aroused widespread interest. Previous methods perform the multi-modal fusion between language and vision at the decoding side of the …
Most existing methods do not explicitly formulate the mutual guidance between vision and language. In this work, we propose a bi-directional relationship inferring network (BRINet) to …
S Yang, M Xia, G Li, HY Zhou… - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
Referring image segmentation aims to segment the referent that is the corresponding object or stuff referred by a natural language expression in an image. Its main challenge lies in how …