Wang, QitongFu, BinLi, MingHe, JunjunPeng, XiQiao, Yu2022-08-172022-08-172022-08-04Q. Wang, B. Fu, M. Li, J. He, X. Peng and Y. Qiao, "Region-aware Arbitrary-shaped Text Detection with Progressive Fusion," in IEEE Transactions on Multimedia, 2022, doi: 10.1109/TMM.2022.3181448.1941-0077https://udspace.udel.edu/handle/19716/31202© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. This article was originally published in IEEE Transactions on Multimedia. The version of record is available at: https://doi.org/10.1109/TMM.2022.3181448.Segmentation-based text detectors are flexible to capture arbitrary-shaped text regions. Due to large geometry variance, it is necessary to construct effective and robust representations to identify text regions with various shapes and scales. In this paper, we focus on designing effective multi-scale contextual features for locating text instances. Specially, we develop a Region Context Module (RCM) to summarize the semantic response and adaptively extract text-region-aware information in a limited local area. To construct complementary multi-scale contextual representations, multiple RCM branches with different scales are employed and integrated via Progressive Fusion Module (PFM). Our proposed RCM and PFM serve as the plug-and-play modules which can be incorporated into existing scene text detection platforms to further boost detection performance. Extensive experiments show that our methods achieve state-of-the-art performances on Total-Text, SCUT-CTW1500 and MSRA-TD500 datasets. The code with models will become publicly available at https://github.com/wqtwjt1996/RP-Text.en-USscene text detectionscene understandingdeep learningArticle