Conrad Albrecht, Jannik Schneider, et al.
CVPR 2025
Superimposed text and scene text in video, i.e. videotext, brings important semantic clues into content analysis. In this paper we present a videotext description scheme and automatic methods for detection and representation of text in video segments. One of the methods is based on edge characterization while the other is based on region analysis. Applications of the videotext description scheme are numerous ranging from video indexing and annotation, ticker-tape anaylsis, commercial detection, transcript analysis to cross-modal querying using text and face information.
Conrad Albrecht, Jannik Schneider, et al.
CVPR 2025
Xiaohui Shen, Gang Hua, et al.
FG 2011
Guangnan Ye, Dong Liu, et al.
ICCV 2013
Graham Mann, Indulis Bernsteins
DIMEA 2007