Effect of occlusion on deaf and hard of hearing users' perception of captioned video quality
While the availability of captioned television programming has increased, the quality of this
captioning is not always acceptable to Deaf and Hard of Hearing (DHH) viewers, especially …
captioning is not always acceptable to Deaf and Hard of Hearing (DHH) viewers, especially …
Fonts that fit the music: A multimodal design trend analysis of lyric videos
Lyric videos, or kinetic typography videos, are music videos showing lyric text in
synchronization with the music. The purpose of this paper is to quantitatively and …
synchronization with the music. The purpose of this paper is to quantitatively and …
News videos segmentation using dominant colors representation
In this chapter, we propose a new representation of images. We called that representation
as “Dominant Colors”. We defined the dissimilarity of two images as a vector contains the …
as “Dominant Colors”. We defined the dissimilarity of two images as a vector contains the …
Multi-Script Video Caption Localization Based on Visual Rhythms
MR Souza, HA Maia, ACS Santos… - Applied Artificial …, 2022 - Taylor & Francis
Localization of video caption plays an important role in information retrieval in multimedia
applications. In this work, we present and evaluate a novel method for localizing video …
applications. In this work, we present and evaluate a novel method for localizing video …
[PDF][PDF] Visual Design Informatics: Revealing Design Tendencies by Machine Learning
原口大地 - 2024 - catalog.lib.kyushu-u.ac.jp
This thesis aims to tackle visual design informatics, which is a research field analyzing visual
designs and revealing unseen design tendencies using informatics approaches. When …
designs and revealing unseen design tendencies using informatics approaches. When …
Abrupt cut detection in news videos using dominant colors representation
In this paper, we propose a new representation of images. We called that representation as
“Dominant Colors”. We defined the dissimilarity of two images as a vector contains the …
“Dominant Colors”. We defined the dissimilarity of two images as a vector contains the …
An innovative method for key frames extraction in news videos
The process of key frames extraction is facing human subjectivity. The objectives of key
frames extraction are mainly two objectives. The first objective is minimizing the number of …
frames extraction are mainly two objectives. The first objective is minimizing the number of …
Lyric video analysis using text detection and tracking
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 …
showing the lyric words of a song. The main characteristic of lyric videos is that the lyric …