@inproceedings{jiang-riloff-2023-exploiting,
title = "Exploiting Commonsense Knowledge about Objects for Visual Activity Recognition",
author = "Jiang, Tianyu and
Riloff, Ellen",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.457",
doi = "10.18653/v1/2023.findings-acl.457",
pages = "7277--7285",
abstract = "Situation recognition is the task of recognizing the activity depictedin an image, including the people and objects involved. Previousmodels for this task typically train a classifier to identify theactivity using a backbone image feature extractor. We propose thatcommonsense knowledge about the objects depicted in an image can alsobe a valuable source of information for activity identification. Previous NLP research has argued that knowledge about the prototypicalfunctions of physical objects is important for language understanding,and NLP techniques have been developed to acquire this knowledge. Our work investigates whether this prototypical function knowledgecan also be beneficial for visual situation recognition. Webuild a framework that incorporates this type of commonsense knowledgein a transformer-based model that is trained to predict the actionverb for situation recognition. Our experimental results show thatadding prototypical function knowledge about physical objects doesimprove performance for the visual activity recognition task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jiang-riloff-2023-exploiting">
<titleInfo>
<title>Exploiting Commonsense Knowledge about Objects for Visual Activity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tianyu</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ellen</namePart>
<namePart type="family">Riloff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Situation recognition is the task of recognizing the activity depictedin an image, including the people and objects involved. Previousmodels for this task typically train a classifier to identify theactivity using a backbone image feature extractor. We propose thatcommonsense knowledge about the objects depicted in an image can alsobe a valuable source of information for activity identification. Previous NLP research has argued that knowledge about the prototypicalfunctions of physical objects is important for language understanding,and NLP techniques have been developed to acquire this knowledge. Our work investigates whether this prototypical function knowledgecan also be beneficial for visual situation recognition. Webuild a framework that incorporates this type of commonsense knowledgein a transformer-based model that is trained to predict the actionverb for situation recognition. Our experimental results show thatadding prototypical function knowledge about physical objects doesimprove performance for the visual activity recognition task.</abstract>
<identifier type="citekey">jiang-riloff-2023-exploiting</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.457</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.457</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>7277</start>
<end>7285</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploiting Commonsense Knowledge about Objects for Visual Activity Recognition
%A Jiang, Tianyu
%A Riloff, Ellen
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F jiang-riloff-2023-exploiting
%X Situation recognition is the task of recognizing the activity depictedin an image, including the people and objects involved. Previousmodels for this task typically train a classifier to identify theactivity using a backbone image feature extractor. We propose thatcommonsense knowledge about the objects depicted in an image can alsobe a valuable source of information for activity identification. Previous NLP research has argued that knowledge about the prototypicalfunctions of physical objects is important for language understanding,and NLP techniques have been developed to acquire this knowledge. Our work investigates whether this prototypical function knowledgecan also be beneficial for visual situation recognition. Webuild a framework that incorporates this type of commonsense knowledgein a transformer-based model that is trained to predict the actionverb for situation recognition. Our experimental results show thatadding prototypical function knowledge about physical objects doesimprove performance for the visual activity recognition task.
%R 10.18653/v1/2023.findings-acl.457
%U https://aclanthology.org/2023.findings-acl.457
%U https://doi.org/10.18653/v1/2023.findings-acl.457
%P 7277-7285
Markdown (Informal)
[Exploiting Commonsense Knowledge about Objects for Visual Activity Recognition](https://aclanthology.org/2023.findings-acl.457) (Jiang & Riloff, Findings 2023)
ACL