@inproceedings{fu-etal-2017-video,
title = "Video Highlight Prediction Using Audience Chat Reactions",
author = "Fu, Cheng-Yang and
Lee, Joon and
Bansal, Mohit and
Berg, Alexander",
editor = "Palmer, Martha and
Hwa, Rebecca and
Riedel, Sebastian",
booktitle = "Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing",
month = sep,
year = "2017",
address = "Copenhagen, Denmark",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D17-1102",
doi = "10.18653/v1/D17-1102",
pages = "972--978",
abstract = "Sports channel video portals offer an exciting domain for research on multimodal, multilingual analysis. We present methods addressing the problem of automatic video highlight prediction based on joint visual features and textual analysis of the real-world audience discourse with complex slang, in both English and traditional Chinese. We present a novel dataset based on League of Legends championships recorded from North American and Taiwanese Twitch.tv channels (will be released for further research), and demonstrate strong results on these using multimodal, character-level CNN-RNN model architectures.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fu-etal-2017-video">
<titleInfo>
<title>Video Highlight Prediction Using Audience Chat Reactions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cheng-Yang</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joon</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Berg</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 2017 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Martha</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rebecca</namePart>
<namePart type="family">Hwa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Riedel</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>Sports channel video portals offer an exciting domain for research on multimodal, multilingual analysis. We present methods addressing the problem of automatic video highlight prediction based on joint visual features and textual analysis of the real-world audience discourse with complex slang, in both English and traditional Chinese. We present a novel dataset based on League of Legends championships recorded from North American and Taiwanese Twitch.tv channels (will be released for further research), and demonstrate strong results on these using multimodal, character-level CNN-RNN model architectures.</abstract>
<identifier type="citekey">fu-etal-2017-video</identifier>
<identifier type="doi">10.18653/v1/D17-1102</identifier>
<location>
<url>https://aclanthology.org/D17-1102</url>
</location>
<part>
<date>2017-09</date>
<extent unit="page">
<start>972</start>
<end>978</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Video Highlight Prediction Using Audience Chat Reactions
%A Fu, Cheng-Yang
%A Lee, Joon
%A Bansal, Mohit
%A Berg, Alexander
%Y Palmer, Martha
%Y Hwa, Rebecca
%Y Riedel, Sebastian
%S Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
%D 2017
%8 September
%I Association for Computational Linguistics
%C Copenhagen, Denmark
%F fu-etal-2017-video
%X Sports channel video portals offer an exciting domain for research on multimodal, multilingual analysis. We present methods addressing the problem of automatic video highlight prediction based on joint visual features and textual analysis of the real-world audience discourse with complex slang, in both English and traditional Chinese. We present a novel dataset based on League of Legends championships recorded from North American and Taiwanese Twitch.tv channels (will be released for further research), and demonstrate strong results on these using multimodal, character-level CNN-RNN model architectures.
%R 10.18653/v1/D17-1102
%U https://aclanthology.org/D17-1102
%U https://doi.org/10.18653/v1/D17-1102
%P 972-978
Markdown (Informal)
[Video Highlight Prediction Using Audience Chat Reactions](https://aclanthology.org/D17-1102) (Fu et al., EMNLP 2017)
ACL
- Cheng-Yang Fu, Joon Lee, Mohit Bansal, and Alexander Berg. 2017. Video Highlight Prediction Using Audience Chat Reactions. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 972–978, Copenhagen, Denmark. Association for Computational Linguistics.