Fine-grained Affordance Annotation for Egocentric Hand-Object Interaction Videos

Object affordance is an important concept in hand-object interaction, providing information on action possibilities based on human motor capacity and objects' physical property thus benefiting tasks such as action anticipation and robot imitation learning. However, the definition of affordance...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2023-02
Hauptverfasser: Yu, Zecheng, Huang, Yifei, Furuta, Ryosuke, Yagi, Takuma, Goutsu, Yusuke, Sato, Yoichi
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Yu, Zecheng
Huang, Yifei
Furuta, Ryosuke
Yagi, Takuma
Goutsu, Yusuke
Sato, Yoichi
description Object affordance is an important concept in hand-object interaction, providing information on action possibilities based on human motor capacity and objects' physical property thus benefiting tasks such as action anticipation and robot imitation learning. However, the definition of affordance in existing datasets often: 1) mix up affordance with object functionality; 2) confuse affordance with goal-related action; and 3) ignore human motor capacity. This paper proposes an efficient annotation scheme to address these issues by combining goal-irrelevant motor actions and grasp types as affordance labels and introducing the concept of mechanical action to represent the action possibilities between two objects. We provide new annotations by applying this scheme to the EPIC-KITCHENS dataset and test our annotation with tasks such as affordance recognition, hand-object interaction hotspots prediction, and cross-domain evaluation of affordance. The results show that models trained with our annotation can distinguish affordance from other concepts, predict fine-grained interaction possibilities on objects, and generalize through different domains.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2774362737</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2774362737</sourcerecordid><originalsourceid>FETCH-proquest_journals_27743627373</originalsourceid><addsrcrecordid>eNqNirEKwjAUAIMgWLT_EHAO1KRtXIu01EkHcS0xeSkp8qJJ-v8W8QOcDu5uRTIuxIEdS843JI9xKoqC15JXlcjItXMIbAxqgaGNtT4YhRpog-iTSs4jXRxtR68BU3Ca9goNuzwm0ImeMUFQ-rvdnQEfd2Rt1TNC_uOW7Lv2durZK_j3DDENk58DLmngUpai5lJI8d_1AUWHPtU</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2774362737</pqid></control><display><type>article</type><title>Fine-grained Affordance Annotation for Egocentric Hand-Object Interaction Videos</title><source>Freely Accessible Journals</source><creator>Yu, Zecheng ; Huang, Yifei ; Furuta, Ryosuke ; Yagi, Takuma ; Goutsu, Yusuke ; Sato, Yoichi</creator><creatorcontrib>Yu, Zecheng ; Huang, Yifei ; Furuta, Ryosuke ; Yagi, Takuma ; Goutsu, Yusuke ; Sato, Yoichi</creatorcontrib><description>Object affordance is an important concept in hand-object interaction, providing information on action possibilities based on human motor capacity and objects' physical property thus benefiting tasks such as action anticipation and robot imitation learning. However, the definition of affordance in existing datasets often: 1) mix up affordance with object functionality; 2) confuse affordance with goal-related action; and 3) ignore human motor capacity. This paper proposes an efficient annotation scheme to address these issues by combining goal-irrelevant motor actions and grasp types as affordance labels and introducing the concept of mechanical action to represent the action possibilities between two objects. We provide new annotations by applying this scheme to the EPIC-KITCHENS dataset and test our annotation with tasks such as affordance recognition, hand-object interaction hotspots prediction, and cross-domain evaluation of affordance. The results show that models trained with our annotation can distinguish affordance from other concepts, predict fine-grained interaction possibilities on objects, and generalize through different domains.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Annotations ; Datasets ; Domains ; Object recognition</subject><ispartof>arXiv.org, 2023-02</ispartof><rights>2023. This work is published under http://creativecommons.org/licenses/by-nc-sa/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>776,780</link.rule.ids></links><search><creatorcontrib>Yu, Zecheng</creatorcontrib><creatorcontrib>Huang, Yifei</creatorcontrib><creatorcontrib>Furuta, Ryosuke</creatorcontrib><creatorcontrib>Yagi, Takuma</creatorcontrib><creatorcontrib>Goutsu, Yusuke</creatorcontrib><creatorcontrib>Sato, Yoichi</creatorcontrib><title>Fine-grained Affordance Annotation for Egocentric Hand-Object Interaction Videos</title><title>arXiv.org</title><description>Object affordance is an important concept in hand-object interaction, providing information on action possibilities based on human motor capacity and objects' physical property thus benefiting tasks such as action anticipation and robot imitation learning. However, the definition of affordance in existing datasets often: 1) mix up affordance with object functionality; 2) confuse affordance with goal-related action; and 3) ignore human motor capacity. This paper proposes an efficient annotation scheme to address these issues by combining goal-irrelevant motor actions and grasp types as affordance labels and introducing the concept of mechanical action to represent the action possibilities between two objects. We provide new annotations by applying this scheme to the EPIC-KITCHENS dataset and test our annotation with tasks such as affordance recognition, hand-object interaction hotspots prediction, and cross-domain evaluation of affordance. The results show that models trained with our annotation can distinguish affordance from other concepts, predict fine-grained interaction possibilities on objects, and generalize through different domains.</description><subject>Annotations</subject><subject>Datasets</subject><subject>Domains</subject><subject>Object recognition</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNqNirEKwjAUAIMgWLT_EHAO1KRtXIu01EkHcS0xeSkp8qJJ-v8W8QOcDu5uRTIuxIEdS843JI9xKoqC15JXlcjItXMIbAxqgaGNtT4YhRpog-iTSs4jXRxtR68BU3Ca9goNuzwm0ImeMUFQ-rvdnQEfd2Rt1TNC_uOW7Lv2durZK_j3DDENk58DLmngUpai5lJI8d_1AUWHPtU</recordid><startdate>20230210</startdate><enddate>20230210</enddate><creator>Yu, Zecheng</creator><creator>Huang, Yifei</creator><creator>Furuta, Ryosuke</creator><creator>Yagi, Takuma</creator><creator>Goutsu, Yusuke</creator><creator>Sato, Yoichi</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20230210</creationdate><title>Fine-grained Affordance Annotation for Egocentric Hand-Object Interaction Videos</title><author>Yu, Zecheng ; Huang, Yifei ; Furuta, Ryosuke ; Yagi, Takuma ; Goutsu, Yusuke ; Sato, Yoichi</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_27743627373</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Annotations</topic><topic>Datasets</topic><topic>Domains</topic><topic>Object recognition</topic><toplevel>online_resources</toplevel><creatorcontrib>Yu, Zecheng</creatorcontrib><creatorcontrib>Huang, Yifei</creatorcontrib><creatorcontrib>Furuta, Ryosuke</creatorcontrib><creatorcontrib>Yagi, Takuma</creatorcontrib><creatorcontrib>Goutsu, Yusuke</creatorcontrib><creatorcontrib>Sato, Yoichi</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Yu, Zecheng</au><au>Huang, Yifei</au><au>Furuta, Ryosuke</au><au>Yagi, Takuma</au><au>Goutsu, Yusuke</au><au>Sato, Yoichi</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Fine-grained Affordance Annotation for Egocentric Hand-Object Interaction Videos</atitle><jtitle>arXiv.org</jtitle><date>2023-02-10</date><risdate>2023</risdate><eissn>2331-8422</eissn><abstract>Object affordance is an important concept in hand-object interaction, providing information on action possibilities based on human motor capacity and objects' physical property thus benefiting tasks such as action anticipation and robot imitation learning. However, the definition of affordance in existing datasets often: 1) mix up affordance with object functionality; 2) confuse affordance with goal-related action; and 3) ignore human motor capacity. This paper proposes an efficient annotation scheme to address these issues by combining goal-irrelevant motor actions and grasp types as affordance labels and introducing the concept of mechanical action to represent the action possibilities between two objects. We provide new annotations by applying this scheme to the EPIC-KITCHENS dataset and test our annotation with tasks such as affordance recognition, hand-object interaction hotspots prediction, and cross-domain evaluation of affordance. The results show that models trained with our annotation can distinguish affordance from other concepts, predict fine-grained interaction possibilities on objects, and generalize through different domains.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2023-02
issn 2331-8422
language eng
recordid cdi_proquest_journals_2774362737
source Freely Accessible Journals
subjects Annotations
Datasets
Domains
Object recognition
title Fine-grained Affordance Annotation for Egocentric Hand-Object Interaction Videos
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-08T06%3A04%3A25IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Fine-grained%20Affordance%20Annotation%20for%20Egocentric%20Hand-Object%20Interaction%20Videos&rft.jtitle=arXiv.org&rft.au=Yu,%20Zecheng&rft.date=2023-02-10&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2774362737%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2774362737&rft_id=info:pmid/&rfr_iscdi=true