{"id":"https://openalex.org/W4387968258","doi":"https://doi.org/10.1145/3581783.3612351","title":"Generating Explanations for Embodied Action Decision from Visual Observation","display_name":"Generating Explanations for Embodied Action Decision from Visual Observation","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968258","doi":"https://doi.org/10.1145/3581783.3612351"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612351","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612351","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075662067","display_name":"Xiaohan Wang","orcid":"https://orcid.org/0000-0003-2396-0824"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaohan Wang","raw_affiliation_strings":["Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101438777","display_name":"Yuehu Liu","orcid":"https://orcid.org/0000-0002-1048-5115"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuehu Liu","raw_affiliation_strings":["Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055504013","display_name":"Xinhang Song","orcid":"https://orcid.org/0000-0002-0895-1076"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinhang Song","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences &amp; University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences &amp; University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030739017","display_name":"Beibei Wang","orcid":"https://orcid.org/0009-0008-5537-5869"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Beibei Wang","raw_affiliation_strings":["Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085719285","display_name":"Shuqiang Jiang","orcid":"https://orcid.org/0000-0002-1596-4326"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuqiang Jiang","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences &amp; University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences &amp; University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5075662067"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":0.246,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.53668332,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2838","last_page":"2846"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.9431965947151184},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8061720728874207},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.7638541460037231},{"id":"https://openalex.org/keywords/embodied-agent","display_name":"Embodied agent","score":0.7511979937553406},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6025316715240479},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.5485504269599915},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5434442162513733},{"id":"https://openalex.org/keywords/gaze","display_name":"Gaze","score":0.5360868573188782},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5299761295318604},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5288541913032532},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5091149210929871},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.47360706329345703},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.4719742238521576},{"id":"https://openalex.org/keywords/cognitive-robotics","display_name":"Cognitive robotics","score":0.44213730096817017},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.37010759115219116},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14007988572120667},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.09593901038169861}],"concepts":[{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.9431965947151184},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8061720728874207},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.7638541460037231},{"id":"https://openalex.org/C103683099","wikidata":"https://www.wikidata.org/wiki/Q5370102","display_name":"Embodied agent","level":3,"score":0.7511979937553406},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6025316715240479},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.5485504269599915},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5434442162513733},{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.5360868573188782},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5299761295318604},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5288541913032532},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5091149210929871},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.47360706329345703},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.4719742238521576},{"id":"https://openalex.org/C192327766","wikidata":"https://www.wikidata.org/wiki/Q1038799","display_name":"Cognitive robotics","level":3,"score":0.44213730096817017},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.37010759115219116},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14007988572120667},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.09593901038169861},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612351","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612351","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.8299999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1593271688","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W2185175083","https://openalex.org/W2332488709","https://openalex.org/W2339652278","https://openalex.org/W2398118205","https://openalex.org/W2475223347","https://openalex.org/W2533598788","https://openalex.org/W2732026016","https://openalex.org/W2883512601","https://openalex.org/W2953127211","https://openalex.org/W2963150697","https://openalex.org/W2963800628","https://openalex.org/W2965597639","https://openalex.org/W2982053164","https://openalex.org/W2998903229","https://openalex.org/W3000226596","https://openalex.org/W3034201026","https://openalex.org/W3034655362","https://openalex.org/W3103651098","https://openalex.org/W3104752576","https://openalex.org/W3106859150","https://openalex.org/W3138516171","https://openalex.org/W3184282957","https://openalex.org/W3207872317","https://openalex.org/W4214643368","https://openalex.org/W4386076477"],"related_works":["https://openalex.org/W2062160780","https://openalex.org/W2012804445","https://openalex.org/W2212007970","https://openalex.org/W1576176190","https://openalex.org/W2068486122","https://openalex.org/W2044346275","https://openalex.org/W2888297397","https://openalex.org/W2964506265","https://openalex.org/W2513760693","https://openalex.org/W2169574110"],"abstract_inverted_index":{"Getting":[0],"trust":[1],"is":[2,27,87,143],"crucial":[3],"for":[4,24,38,67,151,165],"embodied":[5,46,126],"agents":[6],"(such":[7],"as":[8],"robots":[9],"and":[10,58,136,148,169,187],"autonomous":[11],"vehicles)":[12],"to":[13,65,73,93],"collaborate":[14],"with":[15,95,131],"human":[16],"beings,":[17],"especially":[18],"non-experts.":[19],"The":[20,116],"most":[21],"direct":[22],"way":[23],"mutual":[25],"understanding":[26,83],"through":[28],"natural":[29],"language":[30],"explanation.":[31],"Existing":[32],"researches":[33],"consider":[34],"generating":[35,55],"visual":[36,62],"explanations":[37,59,66],"object":[39],"recognition,":[40,68],"while":[41],"the":[42,82,90,96,132,171,174,188,191],"exploration":[43],"of":[44,84,119,124,176,190],"explaining":[45],"decisions":[47,57],"remains":[48],"vacant.":[49],"In":[50],"this":[51],"paper,":[52],"we":[53],"study":[54],"action":[56,71,134,149,158],"based":[60,112],"on":[61,113,181],"observation.":[63],"Distinct":[64],"justifying":[69,170],"an":[70],"needs":[72,92],"show":[74],"why":[75],"it's":[76],"better":[77],"than":[78],"other":[79],"actions.":[80],"Besides,":[81],"scene":[85,146],"structure":[86],"required":[88],"since":[89],"agent":[91],"interact":[94],"environment":[97],"(e.g.":[98],"navigation,":[99],"moving":[100],"objects).":[101],"We":[102,154],"introduce":[103],"a":[104,156],"new":[105],"dataset":[106,117,183],"THOR-EAE":[107,182],"(Embodied":[108],"Action":[109],"Explanation)":[110],"collected":[111],"AI2-THOR":[114],"simulator.":[115],"consists":[118],"over":[120],"840,000":[121],"egocentric":[122],"images":[123],"indoor":[125],"observation":[127],"which":[128],"are":[129],"annotated":[130],"optimal":[133],"labels":[135],"explanation":[137],"sentences.":[138],"An":[139],"explainable":[140],"decision-making":[141],"criterion":[142],"developed":[144],"considering":[145],"layout":[147],"attributes":[150],"efficient":[152],"annotation.":[153],"propose":[155],"graph":[157,162],"justification":[159],"model,":[160],"exploiting":[161],"neural":[163],"networks":[164],"obstacle-surroundings":[166],"relations":[167],"representation":[168],"actions":[172],"under":[173],"guidance":[175],"decision":[177],"results.":[178],"Experimental":[179],"results":[180],"showcase":[184],"its":[185],"challenge":[186],"effectiveness":[189],"proposed":[192],"method.":[193]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
