HyText - A Scene-Text Extraction Method for Video Retrieval

被引：2
|
作者：
Theus, Alexander [1 ]
Rossetto, Luca [1 ]
Bernstein, Abraham [1 ]
机构：
[1] Univ Zurich, Dept Informat, Zurich, Switzerland
来源：
MULTIMEDIA MODELING, MMM 2022, PT II | 2022年 / 13142卷
关键词：
Scene-text extraction; Video text extraction; Video retrieval; RECOGNITION; SEQUENCE;
D O I：
10.1007/978-3-030-98355-0_16
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Scene-text has been shown to be an effective query target for video retrieval applications in a known-item search context. While much progress has been made in scene-text extraction from individual pictures, the special case of video has so far received less attention. This paper introduces HyText, a scene-text extraction method for video with a focus on retrieval applications. HyText uses intermittent scene-text detection in combination with bi-directional tracking in order to increase throughput without reducing detection accuracy.
引用
收藏
页码：182 / 193
页数：12
相关论文
共 50 条
  • [1] Review of Text Extraction Algorithms for Scene-text and Document Images
    Sahare, Parul
    Dhok, Sanjay B.
    IETE TECHNICAL REVIEW, 2017, 34 (02) : 144 - 164
  • [2] Scene-Text Aware Image and Text Retrieval with Dual-Encoder
    Miyawaki, Shumpei
    Hasegawa, Taku
    Nishida, Kyosuke
    Kato, Takuma
    Suzuki, Jun
    PROCEEDINGS OF THE 60TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2022): STUDENT RESEARCH WORKSHOP, 2022, : 422 - 433
  • [3] StacMR: Scene-Text Aware Cross-Modal Retrieval
    Mafla, Andres
    Rezende, Rafael S.
    Gomez, Lluis
    Larlus, Diane
    Karatzas, Dimosthenis
    2021 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION WACV 2021, 2021, : 2219 - 2229
  • [4] A Method of Effective Text Extraction for Complex Video Scene
    Guo, Zhe
    Li, Yuan
    Wang, Yi
    Liu, Shu
    Lei, Tao
    Fan, Yangyu
    MATHEMATICAL PROBLEMS IN ENGINEERING, 2016, 2016
  • [5] Scene-Text Oriented Referring Expression Comprehension
    Bu, Yuqi
    Li, Liuwu
    Xie, Jiayuan
    Liu, Qiong
    Cai, Yi
    Huang, Qingbao
    Li, Qing
    IEEE TRANSACTIONS ON MULTIMEDIA, 2023, 25 : 7208 - 7221
  • [6] A novel method for spoken text feature extraction in semantic video retrieval
    Cao, Juan
    Li, Jintao
    Zhang, Yongdong
    Tang, Sheng
    Advances in Multimedia Information Processing - PCM 2006, Proceedings, 2006, 4261 : 270 - 278
  • [7] GLASS: Global to Local Attention for Scene-Text Spotting
    Ronen, Roi
    Tsiper, Shahar
    Anschel, Oron
    Lavi, Inbal
    Markovitz, Amir
    Manmatha, R.
    COMPUTER VISION - ECCV 2022, PT XXVIII, 2022, 13688 : 249 - 266
  • [8] Adaptive scene-text binarisation on images captured by smartphones
    Belhedi, Amira
    Marcotegui, Beatriz
    IET IMAGE PROCESSING, 2016, 10 (07) : 515 - 523
  • [9] PreSTU: Pre-Training for Scene-Text Understanding
    Kil, Jihyung
    Changpinyo, Soravit
    Chen, Xi
    Hu, Hexiang
    Goodman, Sebastian
    Chao, Wei-Lun
    Soricut, Radu
    2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2023), 2023, : 15224 - 15234
  • [10] Scene-text aware cross-modal retrieval based on semantic matching (ChinaMM2024)
    Cheng, Suyan
    Zhang, Feifei
    Zhang, Xi
    Sun, Zhuo
    MULTIMEDIA SYSTEMS, 2024, 30 (05)
12345