@inproceedings{ping-chen-2017-video,
title = "Video Highlights Detection and Summarization with Lag-Calibration based on Concept-Emotion Mapping of Crowdsourced Time-Sync Comments",
author = "Ping, Qing and
Chen, Chaomei",
editor = "Wang, Lu and
Cheung, Jackie Chi Kit and
Carenini, Giuseppe and
Liu, Fei",
booktitle = "Proceedings of the Workshop on New Frontiers in Summarization",
month = sep,
year = "2017",
address = "Copenhagen, Denmark",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W17-4501",
doi = "10.18653/v1/W17-4501",
pages = "1--11",
abstract = "With the prevalence of video sharing, there are increasing demands for automatic video digestion such as highlight detection. Recently, platforms with crowdsourced time-sync video comments have emerged worldwide, providing a good opportunity for highlight detection. However, this task is non-trivial: (1) time-sync comments often lag behind their corresponding shot; (2) time-sync comments are semantically sparse and noisy; (3) to determine which shots are highlights is highly subjective. The present paper aims to tackle these challenges by proposing a framework that (1) uses concept-mapped lexical-chains for lag-calibration; (2) models video highlights based on comment intensity and combination of emotion and concept concentration of each shot; (3) summarize each detected highlight using improved SumBasic with emotion and concept mapping. Experiments on large real-world datasets show that our highlight detection method and summarization method both outperform other benchmarks with considerable margins.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ping-chen-2017-video">
<titleInfo>
<title>Video Highlights Detection and Summarization with Lag-Calibration based on Concept-Emotion Mapping of Crowdsourced Time-Sync Comments</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qing</namePart>
<namePart type="family">Ping</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chaomei</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on New Frontiers in Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jackie</namePart>
<namePart type="given">Chi</namePart>
<namePart type="given">Kit</namePart>
<namePart type="family">Cheung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giuseppe</namePart>
<namePart type="family">Carenini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Copenhagen, Denmark</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>With the prevalence of video sharing, there are increasing demands for automatic video digestion such as highlight detection. Recently, platforms with crowdsourced time-sync video comments have emerged worldwide, providing a good opportunity for highlight detection. However, this task is non-trivial: (1) time-sync comments often lag behind their corresponding shot; (2) time-sync comments are semantically sparse and noisy; (3) to determine which shots are highlights is highly subjective. The present paper aims to tackle these challenges by proposing a framework that (1) uses concept-mapped lexical-chains for lag-calibration; (2) models video highlights based on comment intensity and combination of emotion and concept concentration of each shot; (3) summarize each detected highlight using improved SumBasic with emotion and concept mapping. Experiments on large real-world datasets show that our highlight detection method and summarization method both outperform other benchmarks with considerable margins.</abstract>
<identifier type="citekey">ping-chen-2017-video</identifier>
<identifier type="doi">10.18653/v1/W17-4501</identifier>
<location>
<url>https://aclanthology.org/W17-4501</url>
</location>
<part>
<date>2017-09</date>
<extent unit="page">
<start>1</start>
<end>11</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Video Highlights Detection and Summarization with Lag-Calibration based on Concept-Emotion Mapping of Crowdsourced Time-Sync Comments
%A Ping, Qing
%A Chen, Chaomei
%Y Wang, Lu
%Y Cheung, Jackie Chi Kit
%Y Carenini, Giuseppe
%Y Liu, Fei
%S Proceedings of the Workshop on New Frontiers in Summarization
%D 2017
%8 September
%I Association for Computational Linguistics
%C Copenhagen, Denmark
%F ping-chen-2017-video
%X With the prevalence of video sharing, there are increasing demands for automatic video digestion such as highlight detection. Recently, platforms with crowdsourced time-sync video comments have emerged worldwide, providing a good opportunity for highlight detection. However, this task is non-trivial: (1) time-sync comments often lag behind their corresponding shot; (2) time-sync comments are semantically sparse and noisy; (3) to determine which shots are highlights is highly subjective. The present paper aims to tackle these challenges by proposing a framework that (1) uses concept-mapped lexical-chains for lag-calibration; (2) models video highlights based on comment intensity and combination of emotion and concept concentration of each shot; (3) summarize each detected highlight using improved SumBasic with emotion and concept mapping. Experiments on large real-world datasets show that our highlight detection method and summarization method both outperform other benchmarks with considerable margins.
%R 10.18653/v1/W17-4501
%U https://aclanthology.org/W17-4501
%U https://doi.org/10.18653/v1/W17-4501
%P 1-11
Markdown (Informal)
[Video Highlights Detection and Summarization with Lag-Calibration based on Concept-Emotion Mapping of Crowdsourced Time-Sync Comments](https://aclanthology.org/W17-4501) (Ping & Chen, 2017)
ACL