@inproceedings{wiriyathammabhum-etal-2019-referring,
title = "Referring to Objects in Videos Using Spatio-Temporal Identifying Descriptions",
author = "Wiriyathammabhum, Peratham and
Shrivastava, Abhinav and
Morariu, Vlad and
Davis, Larry",
editor = "Bernardi, Raffaella and
Fernandez, Raquel and
Gella, Spandana and
Kafle, Kushal and
Kanan, Christopher and
Lee, Stefan and
Nabi, Moin",
booktitle = "Proceedings of the Second Workshop on Shortcomings in Vision and Language",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-1802",
doi = "10.18653/v1/W19-1802",
pages = "14--25",
abstract = "This paper presents a new task, the grounding of spatio-temporal identifying descriptions in videos. Previous work suggests potential bias in existing datasets and emphasizes the need for a new data creation schema to better model linguistic structure. We introduce a new data collection scheme based on grammatical constraints for surface realization to enable us to investigate the problem of grounding spatio-temporal identifying descriptions in videos. We then propose a two-stream modular attention network that learns and grounds spatio-temporal identifying descriptions based on appearance and motion. We show that motion modules help to ground motion-related words and also help to learn in appearance modules because modular neural networks resolve task interference between modules. Finally, we propose a future challenge and a need for a robust system arising from replacing ground truth visual annotations with automatic video object detector and temporal event localization.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wiriyathammabhum-etal-2019-referring">
<titleInfo>
<title>Referring to Objects in Videos Using Spatio-Temporal Identifying Descriptions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Peratham</namePart>
<namePart type="family">Wiriyathammabhum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhinav</namePart>
<namePart type="family">Shrivastava</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vlad</namePart>
<namePart type="family">Morariu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Larry</namePart>
<namePart type="family">Davis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Shortcomings in Vision and Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Raffaella</namePart>
<namePart type="family">Bernardi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raquel</namePart>
<namePart type="family">Fernandez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Spandana</namePart>
<namePart type="family">Gella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kushal</namePart>
<namePart type="family">Kafle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Kanan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Moin</namePart>
<namePart type="family">Nabi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents a new task, the grounding of spatio-temporal identifying descriptions in videos. Previous work suggests potential bias in existing datasets and emphasizes the need for a new data creation schema to better model linguistic structure. We introduce a new data collection scheme based on grammatical constraints for surface realization to enable us to investigate the problem of grounding spatio-temporal identifying descriptions in videos. We then propose a two-stream modular attention network that learns and grounds spatio-temporal identifying descriptions based on appearance and motion. We show that motion modules help to ground motion-related words and also help to learn in appearance modules because modular neural networks resolve task interference between modules. Finally, we propose a future challenge and a need for a robust system arising from replacing ground truth visual annotations with automatic video object detector and temporal event localization.</abstract>
<identifier type="citekey">wiriyathammabhum-etal-2019-referring</identifier>
<identifier type="doi">10.18653/v1/W19-1802</identifier>
<location>
<url>https://aclanthology.org/W19-1802</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>14</start>
<end>25</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Referring to Objects in Videos Using Spatio-Temporal Identifying Descriptions
%A Wiriyathammabhum, Peratham
%A Shrivastava, Abhinav
%A Morariu, Vlad
%A Davis, Larry
%Y Bernardi, Raffaella
%Y Fernandez, Raquel
%Y Gella, Spandana
%Y Kafle, Kushal
%Y Kanan, Christopher
%Y Lee, Stefan
%Y Nabi, Moin
%S Proceedings of the Second Workshop on Shortcomings in Vision and Language
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F wiriyathammabhum-etal-2019-referring
%X This paper presents a new task, the grounding of spatio-temporal identifying descriptions in videos. Previous work suggests potential bias in existing datasets and emphasizes the need for a new data creation schema to better model linguistic structure. We introduce a new data collection scheme based on grammatical constraints for surface realization to enable us to investigate the problem of grounding spatio-temporal identifying descriptions in videos. We then propose a two-stream modular attention network that learns and grounds spatio-temporal identifying descriptions based on appearance and motion. We show that motion modules help to ground motion-related words and also help to learn in appearance modules because modular neural networks resolve task interference between modules. Finally, we propose a future challenge and a need for a robust system arising from replacing ground truth visual annotations with automatic video object detector and temporal event localization.
%R 10.18653/v1/W19-1802
%U https://aclanthology.org/W19-1802
%U https://doi.org/10.18653/v1/W19-1802
%P 14-25
Markdown (Informal)
[Referring to Objects in Videos Using Spatio-Temporal Identifying Descriptions](https://aclanthology.org/W19-1802) (Wiriyathammabhum et al., NAACL 2019)
ACL