2018 IEEE Fourth International Conference on Multimedia Big Data (BigMM) 2018
DOI: 10.1109/bigmm.2018.8499465
|View full text |Cite
|
Sign up to set email alerts
|

Automatic Generation of Textual Advertisement for Video Advertising

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
3
0

Year Published

2019
2019
2023
2023

Publication Types

Select...
5

Relationship

0
5

Authors

Journals

citations
Cited by 5 publications
(3 citation statements)
references
References 13 publications
0
3
0
Order By: Relevance
“…Zhang et al 49) used eye-gaze tracking data to minimize the user disturbance because of advertisement insertion while enhancing the user engagement with the advertising content. Similar works aiming at text insertion onto videos can also be found 50) .…”
Section: Advertisement Affectsmentioning
confidence: 96%
“…Zhang et al 49) used eye-gaze tracking data to minimize the user disturbance because of advertisement insertion while enhancing the user engagement with the advertising content. Similar works aiming at text insertion onto videos can also be found 50) .…”
Section: Advertisement Affectsmentioning
confidence: 96%
“…Example 2. Consider the instance  = ( [1,12], , 7) of the ASDP, for some distance matrix . Suppose that the solution to  can be obtained by splitting  as  4 1,6 ∪  3 7,12 and by computing the partition…”
Section: A Novel Heuristic For the Asdpmentioning
confidence: 99%
“…In the context of a sport event, it may be often necessary to highlight the precise points of a video in which a specific athlete shows up, so as to enable faster video browsing [1,6,7]. In the context of advertising insertions, spots are usually placed in a video in such a way to be as less intrusive as possible; it is therefore necessary to automatically identify which specific points of the considered video may minimize intrusiveness [12]. In all of these contexts, scene detection algorithms prove of fundamental assistance: by segmenting a video into semantic units, these algorithms enable the extraction of metadata that can be subsequently used to manipulate and classify it.…”
Section: Introductionmentioning
confidence: 99%