@inproceedings{reale-etal-2018-spot,
title = "Can You Spot the Semantic Predicate in this Video?",
author = "Reale, Christopher and
Bonial, Claire and
Kwon, Heesung and
Voss, Clare",
editor = "Caselli, Tommaso and
Miller, Ben and
van Erp, Marieke and
Vossen, Piek and
Palmer, Martha and
Hovy, Eduard and
Mitamura, Teruko and
Caswell, David and
Brown, Susan W. and
Bonial, Claire",
booktitle = "Proceedings of the Workshop Events and Stories in the News 2018",
month = aug,
year = "2018",
address = "Santa Fe, New Mexico, U.S.A",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-4307",
pages = "55--60",
abstract = "We propose a method to improve human activity recognition in video by leveraging semantic information about the target activities from an expert-defined linguistic resource, VerbNet. Our hypothesis is that activities that share similar event semantics, as defined by the semantic predicates of VerbNet, will be more likely to share some visual components. We use a deep convolutional neural network approach as a baseline and incorporate linguistic information from VerbNet through multi-task learning. We present results of experiments showing the added information has negligible impact on recognition performance. We discuss how this may be because the lexical semantic information defined by VerbNet is generally not visually salient given the video processing approach used here, and how we may handle this in future approaches.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="reale-etal-2018-spot">
<titleInfo>
<title>Can You Spot the Semantic Predicate in this Video?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Reale</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claire</namePart>
<namePart type="family">Bonial</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heesung</namePart>
<namePart type="family">Kwon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Clare</namePart>
<namePart type="family">Voss</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop Events and Stories in the News 2018</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tommaso</namePart>
<namePart type="family">Caselli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ben</namePart>
<namePart type="family">Miller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marieke</namePart>
<namePart type="family">van Erp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piek</namePart>
<namePart type="family">Vossen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Eduard</namePart>
<namePart type="family">Hovy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Teruko</namePart>
<namePart type="family">Mitamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Caswell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Susan</namePart>
<namePart type="given">W</namePart>
<namePart type="family">Brown</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claire</namePart>
<namePart type="family">Bonial</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Santa Fe, New Mexico, U.S.A</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We propose a method to improve human activity recognition in video by leveraging semantic information about the target activities from an expert-defined linguistic resource, VerbNet. Our hypothesis is that activities that share similar event semantics, as defined by the semantic predicates of VerbNet, will be more likely to share some visual components. We use a deep convolutional neural network approach as a baseline and incorporate linguistic information from VerbNet through multi-task learning. We present results of experiments showing the added information has negligible impact on recognition performance. We discuss how this may be because the lexical semantic information defined by VerbNet is generally not visually salient given the video processing approach used here, and how we may handle this in future approaches.</abstract>
<identifier type="citekey">reale-etal-2018-spot</identifier>
<location>
<url>https://aclanthology.org/W18-4307</url>
</location>
<part>
<date>2018-08</date>
<extent unit="page">
<start>55</start>
<end>60</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Can You Spot the Semantic Predicate in this Video?
%A Reale, Christopher
%A Bonial, Claire
%A Kwon, Heesung
%A Voss, Clare
%Y Caselli, Tommaso
%Y Miller, Ben
%Y van Erp, Marieke
%Y Vossen, Piek
%Y Palmer, Martha
%Y Hovy, Eduard
%Y Mitamura, Teruko
%Y Caswell, David
%Y Brown, Susan W.
%Y Bonial, Claire
%S Proceedings of the Workshop Events and Stories in the News 2018
%D 2018
%8 August
%I Association for Computational Linguistics
%C Santa Fe, New Mexico, U.S.A
%F reale-etal-2018-spot
%X We propose a method to improve human activity recognition in video by leveraging semantic information about the target activities from an expert-defined linguistic resource, VerbNet. Our hypothesis is that activities that share similar event semantics, as defined by the semantic predicates of VerbNet, will be more likely to share some visual components. We use a deep convolutional neural network approach as a baseline and incorporate linguistic information from VerbNet through multi-task learning. We present results of experiments showing the added information has negligible impact on recognition performance. We discuss how this may be because the lexical semantic information defined by VerbNet is generally not visually salient given the video processing approach used here, and how we may handle this in future approaches.
%U https://aclanthology.org/W18-4307
%P 55-60
Markdown (Informal)
[Can You Spot the Semantic Predicate in this Video?](https://aclanthology.org/W18-4307) (Reale et al., EventStory 2018)
ACL
- Christopher Reale, Claire Bonial, Heesung Kwon, and Clare Voss. 2018. Can You Spot the Semantic Predicate in this Video?. In Proceedings of the Workshop Events and Stories in the News 2018, pages 55–60, Santa Fe, New Mexico, U.S.A. Association for Computational Linguistics.