Entity-Enhanced Adaptive Reconstruction Network for Weakly Supervised Referring Expression Grounding

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 45; no. 3; pp. 3003 - 3018
• Main Authors: Liu, Xuejing, Li, Liang, Wang, Shuhui, Zha, Zheng-Jun, Li, Zechao, Tian, Qi, Huang, Qingming
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.03.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: adaptive reconstruction; Annotations; Collaboration; Context; Context modeling; Entity enhancement; Grounding; Image reconstruction; Mathematical analysis; Proposals; Ranking; Reconstruction; referring expression grounding; Training; Visualization

Weakly supervised Referring Expression Grounding (REG) aims to ground a particular target in an image described by a language expression while lacking the correspondence between target and expression. Two main problems exist in weakly supervised REG. First, the lack of region-level annotations intro...