Caption Detection, Localization and Type Recognition in Arabic News Video

Zedan, Ibrahim A.; Elsayed, Khaled M.; Emary, Eid

doi:10.1145/2908446.2908472

Cited by 8 publications

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Captions, therefore, have different characteristics from scene texts. We can find many attempts on this task, such as [4,5,6,7,8,9,10,11,12,13]. Most of them deal with the static captions (i.e., captions without motions), while Zedan [10] deals with moving captions; they assume the vertical or horizontal scrolling of caption text, in addition to the static captions.…”

Section: Related Workmentioning

confidence: 99%

Lyric Video Analysis Using Text Detection and Tracking

Sakaguchi

Kato

Goto

et al. 2020

Preprint

View full text Add to dashboard Cite

We attempt to recognize and track lyric words in lyric videos. Lyric video is a music video showing the lyric words of a song. The main characteristic of lyric videos is that the lyric words are shown at frames synchronously with the music. The difficulty of recognizing and tracking the lyric words is that (1) the words are often decorated and geometrically distorted and (2) the words move arbitrarily and drastically in the video frame. The purpose of this paper is to analyze the motion of the lyric words in lyric videos, as the first step of automatic lyric video generation. In order to analyze the motion of lyric words, we first apply a state-of-the-art scene text detector and recognizer to each video frame. Then, lyric-frame matching is performed to establish the optimal correspondence between lyric words and the frames. After fixing the motion trajectories of individual lyric words from correspondence, we analyze the trajectories of the lyric words by k-medoids clustering and dynamic time warping (DTW).

show abstract