{"id":"https://openalex.org/W4413156284","doi":"https://doi.org/10.1109/cvpr52734.2025.01330","title":"Is \u2018Right\u2019 Right? Enhancing Object Orientation Understanding in Multimodal Large Language Models through Egocentric Instruction Tuning","display_name":"Is \u2018Right\u2019 Right? Enhancing Object Orientation Understanding in Multimodal Large Language Models through Egocentric Instruction Tuning","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413156284","doi":"https://doi.org/10.1109/cvpr52734.2025.01330"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.01330","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01330","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101893302","display_name":"Jaewook Jung","orcid":"https://orcid.org/0000-0002-8742-007X"},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ji Hyeok Jung","raw_affiliation_strings":["Sogang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sogang University","institution_ids":["https://openalex.org/I148751991"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065415014","display_name":"Euntai Kim","orcid":"https://orcid.org/0000-0002-0975-8390"},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Eun Tae Kim","raw_affiliation_strings":["Sogang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sogang University","institution_ids":["https://openalex.org/I148751991"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043441823","display_name":"Seoyeon Kim","orcid":"https://orcid.org/0000-0001-6027-0887"},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seoyeon Kim","raw_affiliation_strings":["Sogang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sogang University","institution_ids":["https://openalex.org/I148751991"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003450797","display_name":"Joo Ho Lee","orcid":"https://orcid.org/0000-0001-7307-7744"},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joo Ho Lee","raw_affiliation_strings":["Sogang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sogang University","institution_ids":["https://openalex.org/I148751991"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107114089","display_name":"Bumsoo Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I9272278","display_name":"Chung Cheong University","ror":"https://ror.org/04s3waj07","country_code":"KR","type":"education","lineage":["https://openalex.org/I9272278"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Bumsoo Kim","raw_affiliation_strings":["Chungang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chungang University","institution_ids":["https://openalex.org/I9272278"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068698319","display_name":"Buru Chang","orcid":"https://orcid.org/0000-0002-7595-9035"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Buru Chang","raw_affiliation_strings":["Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.673,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.84082418,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"14257","last_page":"14267"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9923999905586243,"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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9923999905586243,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.984000027179718,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9627000093460083,"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/orientation","display_name":"Orientation (vector space)","score":0.7382710576057434},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.692416787147522},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5784414410591125},{"id":"https://openalex.org/keywords/object-orientation","display_name":"Object-orientation","score":0.5628741979598999},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5172260999679565},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49744513630867004},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.46031519770622253},{"id":"https://openalex.org/keywords/object-oriented-programming","display_name":"Object-oriented programming","score":0.19726485013961792},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13699498772621155},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09849515557289124},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.07353100180625916}],"concepts":[{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.7382710576057434},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.692416787147522},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5784414410591125},{"id":"https://openalex.org/C120968358","wikidata":"https://www.wikidata.org/wiki/Q2011845","display_name":"Object-orientation","level":3,"score":0.5628741979598999},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5172260999679565},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49744513630867004},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.46031519770622253},{"id":"https://openalex.org/C73752529","wikidata":"https://www.wikidata.org/wiki/Q79872","display_name":"Object-oriented programming","level":2,"score":0.19726485013961792},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13699498772621155},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09849515557289124},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.07353100180625916}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.01330","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01330","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1964741907","https://openalex.org/W1994382987","https://openalex.org/W2025807224","https://openalex.org/W2031454541","https://openalex.org/W2070862239","https://openalex.org/W2108560551","https://openalex.org/W2108598243","https://openalex.org/W2128942651","https://openalex.org/W2139783272","https://openalex.org/W2743406267","https://openalex.org/W2763549966","https://openalex.org/W2981720610","https://openalex.org/W3205786327","https://openalex.org/W4226321491","https://openalex.org/W4386113267","https://openalex.org/W4389519014","https://openalex.org/W4389520792","https://openalex.org/W4389523832","https://openalex.org/W4390871800","https://openalex.org/W4401417048","https://openalex.org/W4402670774","https://openalex.org/W4402713111","https://openalex.org/W4402716477","https://openalex.org/W4402727495","https://openalex.org/W4402727669","https://openalex.org/W4402727916","https://openalex.org/W4402753889","https://openalex.org/W4402754020","https://openalex.org/W4402754023","https://openalex.org/W4403780703"],"related_works":["https://openalex.org/W1443935849","https://openalex.org/W2055707201","https://openalex.org/W2347745895","https://openalex.org/W2073846564","https://openalex.org/W2084029475","https://openalex.org/W2146798260","https://openalex.org/W133142268","https://openalex.org/W4206087077","https://openalex.org/W639881615","https://openalex.org/W2157278770"],"abstract_inverted_index":{"Multimodal":[0],"large":[1],"language":[2],"models":[3],"(MLLMs)":[4],"act":[5],"as":[6],"essential":[7],"interfaces,":[8],"connecting":[9],"humans":[10],"with":[11,58],"AI":[12],"technologies":[13],"in":[14,22,27,34],"multimodal":[15],"applications.":[16],"However,":[17],"current":[18],"MLLMs":[19],"face":[20],"challenges":[21],"accurately":[23],"interpreting":[24],"object":[25,86],"orientation":[26,32,43,56,93,109,121,144],"images":[28,127],"due":[29],"to":[30,84,102],"inconsistent":[31],"annotations":[33],"training":[35],"data,":[36,97],"hindering":[37],"the":[38,59,70,104],"development":[39],"of":[40],"a":[41,64,116],"coherent":[42],"understanding.":[44,94],"To":[45],"overcome":[46],"this,":[47],"we":[48,98,113],"propose":[49],"egocentric":[50,72,77,139],"instruction":[51,78,100,140,152],"tuning,":[52],"which":[53],"aligns":[54],"MLLMs\u2019":[55,82,120],"understanding":[57,122,145],"user\u2019s":[60,71],"perspective,":[61],"based":[62],"on":[63,134,159],"consistent":[65],"annotation":[66],"standard":[67],"derived":[68],"from":[69,129],"viewpoint.":[73],"We":[74],"first":[75],"generate":[76],"data":[79,153],"that":[80,118,138],"leverages":[81],"ability":[83],"recognize":[85],"details":[87],"and":[88,154],"applies":[89],"prior":[90],"knowledge":[91],"for":[92,107],"Using":[95],"this":[96,135],"perform":[99],"tuning":[101,141],"enhance":[103],"model\u2019s":[105],"capability":[106],"accurate":[108],"interpretation.":[110],"In":[111],"addition,":[112],"introduce":[114],"EgoOrientBench,":[115],"benchmark":[117,136,155],"evaluates":[119],"across":[123],"three":[124],"tasks":[125],"using":[126],"collected":[128],"diverse":[130],"domains.":[131],"Experimental":[132],"results":[133],"show":[137],"significantly":[142],"improves":[143],"without":[146],"compromising":[147],"overall":[148],"MLLM":[149],"performance.":[150],"The":[151],"dataset":[156],"are":[157],"available":[158],"our":[160],"project":[161],"page":[162],"at":[163],"https://github.com/jhCOR/EgoOrientBench.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}