method: GoMatching2024-01-24
Authors: HeHaibin, YeMaoyuan, ZhangJing, LiuJuhua, TaoDacheng
Affiliation: Wuhan University
Description: We extend off-the-shelf image text spotter DeepSolo to video text spotter via long-short term matching module.
method: LOGO2024-05-30
Authors: Hongen Liu, Di Sun, Jiahao Wang, Yi Liu, Gang Pan
Affiliation: College of Intelligence and Computing, Tianjin University；Tianjin University of Science and Technology; Baidu Inc.
Description: We propose a Language Collaboration and Glyph Perception Model, termed LOGO to enhance the performance of conventional text spotters through the integration of a synergy module. To achieve this goal, a language synergy classifier (LSC) is designed to explicitly discern text instances from background noise in the recognition stage. Besides, the glyph supervision and visual position mixture module are proposed to enhance the recognition accuracy of noisy text regions, and acquire more discriminative tracking features, respectively.
method: Semantic-Aware Video Text Detection2022-01-26
Authors: Wei Feng, Fei Yin, Xu-Yao Zhang, Cheng-Lin Liu
Affiliation: CASIA
Description: This is based on our CVPR2021 paper 'Semantic-Aware Video Text Detection'.
| Date | Method | MOTA | MOTP | IDF1 | Mostly Matched | Partially Matched | Mostly Lost | |||
|---|---|---|---|---|---|---|---|---|---|---|
| 2024-01-24 | GoMatching | 60.02% | 77.85% | 70.85% | 1095 | 345 | 476 | |||
| 2024-05-30 | LOGO | 55.92% | 71.89% | 68.27% | 953 | 455 | 508 | |||
| 2022-01-26 | Semantic-Aware Video Text Detection | 48.41% | 76.31% | 63.65% | 693 | 500 | 723 |