{"id":"https://openalex.org/W4392910543","doi":"https://doi.org/10.1109/icassp48485.2024.10445969","title":"Caption Unification for Multi-View Lifelogging Images Based on In-Context Learning with Heterogeneous Semantic Contents","display_name":"Caption Unification for Multi-View Lifelogging Images Based on In-Context Learning with Heterogeneous Semantic Contents","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392910543","doi":"https://doi.org/10.1109/icassp48485.2024.10445969"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10445969","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10445969","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101079991","display_name":"Masaya Sato","orcid":"https://orcid.org/0000-0002-3944-2012"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masaya Sato","raw_affiliation_strings":["Hokkaido University,School of Engineering,Japan","School of Engineering, Hokkaido University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokkaido University,School of Engineering,Japan","institution_ids":["https://openalex.org/I205349734"]},{"raw_affiliation_string":"School of Engineering, Hokkaido University, Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033215072","display_name":"Keisuke Maeda","orcid":"https://orcid.org/0000-0001-8039-3462"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keisuke Maeda","raw_affiliation_strings":["Hokkaido University,Faculty of Information Science and Technology,Japan","Faculty of Information Science and Technology, Hokkaido University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokkaido University,Faculty of Information Science and Technology,Japan","institution_ids":["https://openalex.org/I205349734"]},{"raw_affiliation_string":"Faculty of Information Science and Technology, Hokkaido University, Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002757875","display_name":"Ren Togo","orcid":"https://orcid.org/0000-0002-4474-3995"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ren Togo","raw_affiliation_strings":["Hokkaido University,Faculty of Information Science and Technology,Japan","Faculty of Information Science and Technology, Hokkaido University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokkaido University,Faculty of Information Science and Technology,Japan","institution_ids":["https://openalex.org/I205349734"]},{"raw_affiliation_string":"Faculty of Information Science and Technology, Hokkaido University, Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009032240","display_name":"Takahiro Ogawa","orcid":"https://orcid.org/0000-0001-5332-8112"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takahiro Ogawa","raw_affiliation_strings":["Hokkaido University,Faculty of Information Science and Technology,Japan","Faculty of Information Science and Technology, Hokkaido University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokkaido University,Faculty of Information Science and Technology,Japan","institution_ids":["https://openalex.org/I205349734"]},{"raw_affiliation_string":"Faculty of Information Science and Technology, Hokkaido University, Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"last","author":{"id":null,"display_name":"Miki Haseyama","orcid":null},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Miki Haseyama","raw_affiliation_strings":["Hokkaido University,Faculty of Information Science and Technology,Japan","Faculty of Information Science and Technology, Hokkaido University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokkaido University,Faculty of Information Science and Technology,Japan","institution_ids":["https://openalex.org/I205349734"]},{"raw_affiliation_string":"Faculty of Information Science and Technology, Hokkaido University, Japan","institution_ids":["https://openalex.org/I205349734"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I205349734"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"8085","last_page":"8089"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9908999800682068,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9851999878883362,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/lifelog","display_name":"Lifelog","score":0.8985766172409058},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8666484355926514},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8352261781692505},{"id":"https://openalex.org/keywords/unification","display_name":"Unification","score":0.8247302174568176},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6201463341712952},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5674757957458496},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5475935339927673},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5291650295257568},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5025289058685303},{"id":"https://openalex.org/keywords/viewpoints","display_name":"Viewpoints","score":0.4745936095714569},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.4729433059692383},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.45227015018463135},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.2878636121749878},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.13018766045570374}],"concepts":[{"id":"https://openalex.org/C176168674","wikidata":"https://www.wikidata.org/wiki/Q763835","display_name":"Lifelog","level":2,"score":0.8985766172409058},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8666484355926514},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8352261781692505},{"id":"https://openalex.org/C96146094","wikidata":"https://www.wikidata.org/wiki/Q609057","display_name":"Unification","level":2,"score":0.8247302174568176},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6201463341712952},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5674757957458496},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5475935339927673},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5291650295257568},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5025289058685303},{"id":"https://openalex.org/C2776035091","wikidata":"https://www.wikidata.org/wiki/Q7928819","display_name":"Viewpoints","level":2,"score":0.4745936095714569},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.4729433059692383},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.45227015018463135},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.2878636121749878},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.13018766045570374},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10445969","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10445969","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7580542989","display_name":null,"funder_award_id":"JP23K11211","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8739887802","display_name":null,"funder_award_id":"JP21H03456","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1998053","https://openalex.org/W1895577753","https://openalex.org/W2803408761","https://openalex.org/W2970641574","https://openalex.org/W3205786327","https://openalex.org/W4225323055","https://openalex.org/W4226352076","https://openalex.org/W4229042118","https://openalex.org/W4235343256","https://openalex.org/W4254415482","https://openalex.org/W4283378943","https://openalex.org/W4283381985","https://openalex.org/W4292199884","https://openalex.org/W4292779060","https://openalex.org/W4312878367","https://openalex.org/W4320458302","https://openalex.org/W4366850747","https://openalex.org/W4367367040","https://openalex.org/W4388720704","https://openalex.org/W6778883912","https://openalex.org/W6789753369","https://openalex.org/W6791353385","https://openalex.org/W6810334672","https://openalex.org/W6839015040"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2805113808","https://openalex.org/W1981938961","https://openalex.org/W2529344883","https://openalex.org/W3195986301","https://openalex.org/W3186150303","https://openalex.org/W4362577851","https://openalex.org/W4321104198","https://openalex.org/W3033566819","https://openalex.org/W2950500537"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,10,35,127],"new":[4,128],"task":[5,129],"of":[6,28,73,85,97,117],"caption":[7,12,124,167],"unification":[8,13,125],"and":[9,38,88,122,147,155],"novel":[11],"method":[14,78,106,164],"for":[15,55,130],"multi-view":[16,56,131],"lifelogging":[17,57,132],"images":[18,58,66,87,99],"based":[19,100,139],"on":[20,101,140],"in-context":[21,102,141],"learning":[22,142],"with":[23,143],"heterogeneous":[24,144],"semantic":[25,44,70,83,95,145],"contents.":[26],"Most":[27],"the":[29,42,61,65,74,81,94,98,108,115,149,162],"existing":[30,118],"image":[31,37,119],"captioning":[32,54,120],"models":[33,121],"target":[34],"single":[36],"do":[39],"not":[40],"consider":[41,123],"common":[43,69,82],"contents":[45,71,84,96,146],"among":[46],"multiple":[47,86],"images.":[48,133],"Therefore,":[49],"they":[50],"suffer":[51],"from":[52,151],"inconsistent":[53],"taken":[59],"in":[60],"same":[62],"scene,":[63],"i.e.,":[64],"that":[67,91,161],"have":[68],"regardless":[72],"viewpoints.":[75],"The":[76,104,157],"proposed":[77,105,163],"enables":[79],"training":[80],"generating":[89],"captions":[90,138,150],"comprehensively":[92],"contain":[93],"learning.":[103],"has":[107],"following":[109],"two":[110,152],"contributions.":[111],"First,":[112],"we":[113,135],"identify":[114],"problem":[116],"as":[126],"Second,":[134],"generate":[136],"unified":[137],"evaluate":[148],"perspectives,":[153],"uniformity":[154],"retainability.":[156],"experimental":[158],"results":[159],"demonstrate":[160],"realizes":[165],"successful":[166],"unification.":[168]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
