{"id":"https://openalex.org/W4406460326","doi":"https://doi.org/10.1109/bigdata62323.2024.10825835","title":"Visual Lifelog Retrieval through Captioning-Enhanced Interpretation","display_name":"Visual Lifelog Retrieval through Captioning-Enhanced Interpretation","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406460326","doi":"https://doi.org/10.1109/bigdata62323.2024.10825835"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825835","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825835","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.04010","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yu-Fei Shih","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Yu-Fei Shih","raw_affiliation_strings":["National Taiwan University,Department of Computer Science and Information Engineering,Taipei,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,Department of Computer Science and Information Engineering,Taipei,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012131890","display_name":"An-Zi Yen","orcid":"https://orcid.org/0000-0001-5304-7230"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"An-Zi Yen","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Department of Computer Science,Hsinchu,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Department of Computer Science,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053932280","display_name":"Hen\u2010Hsen Huang","orcid":"https://orcid.org/0000-0001-9169-3081"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hen-Hsen Huang","raw_affiliation_strings":["Institute of Information Science Academia Sinica,Taipei,Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science Academia Sinica,Taipei,Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000334344","display_name":"Hsin\u2010Hsi Chen","orcid":"https://orcid.org/0000-0001-9757-9423"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Hsi Chen","raw_affiliation_strings":["AI Research Center (AINTU) National Taiwan University,Department of Computer Science and Information Engineering,Taipei,Taiwan"],"affiliations":[{"raw_affiliation_string":"AI Research Center (AINTU) National Taiwan University,Department of Computer Science and Information Engineering,Taipei,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25087873,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"479","last_page":"486"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9994000196456909,"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":0.9897000193595886,"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":0.960372805595398},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.9470112323760986},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8126693964004517},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.7243214249610901},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6015617847442627},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5269219279289246},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.515182375907898},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.44634294509887695},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4275134205818176},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.19826599955558777},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.18818187713623047}],"concepts":[{"id":"https://openalex.org/C176168674","wikidata":"https://www.wikidata.org/wiki/Q763835","display_name":"Lifelog","level":2,"score":0.960372805595398},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9470112323760986},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8126693964004517},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.7243214249610901},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6015617847442627},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5269219279289246},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.515182375907898},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.44634294509887695},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4275134205818176},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.19826599955558777},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.18818187713623047},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825835","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825835","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.04010","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.04010","pdf_url":"https://arxiv.org/pdf/2510.04010","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.04010","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.04010","pdf_url":"https://arxiv.org/pdf/2510.04010","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311649","display_name":"Ministry of Education","ror":"https://ror.org/036nq5137"},{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2030329769","https://openalex.org/W2971066994","https://openalex.org/W3113422133","https://openalex.org/W3155721152","https://openalex.org/W3166396011","https://openalex.org/W3173242475","https://openalex.org/W3210442340","https://openalex.org/W4283378943","https://openalex.org/W4283381985","https://openalex.org/W4321104198","https://openalex.org/W4366208220","https://openalex.org/W4379141473","https://openalex.org/W4379179700","https://openalex.org/W4379179712","https://openalex.org/W4385681674","https://openalex.org/W4387294596","https://openalex.org/W4390873312","https://openalex.org/W4391377114","https://openalex.org/W4391591467","https://openalex.org/W4396786216","https://openalex.org/W4402726946","https://openalex.org/W4404784276","https://openalex.org/W4406371524","https://openalex.org/W6726253183","https://openalex.org/W6791353385","https://openalex.org/W6851800889","https://openalex.org/W6855618270","https://openalex.org/W6857172037","https://openalex.org/W6858543224","https://openalex.org/W6861503643","https://openalex.org/W6861737864","https://openalex.org/W6866878626"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2805113808","https://openalex.org/W1981938961","https://openalex.org/W2051159811","https://openalex.org/W1998053","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W2963177403","https://openalex.org/W4290852288","https://openalex.org/W2949362007"],"abstract_inverted_index":{"People":[0],"often":[1],"struggle":[2],"to":[3,13,16,34,38,89,153],"remember":[4],"specific":[5,59],"details":[6],"of":[7,115,118,158,174],"past":[8],"experiences,":[9],"which":[10],"can":[11],"lead":[12],"the":[14,92,113,116,119,122,128,138,142,147,155,172],"need":[15],"revisit":[17],"these":[18],"memories.":[19],"Consequently,":[20],"lifelog":[21,65,175],"retrieval":[22],"has":[23],"emerged":[24],"as":[25],"a":[26,50,62,85,98,109,180],"crucial":[27],"application.":[28],"Various":[29],"studies":[30],"have":[31],"explored":[32],"methods":[33],"facilitate":[35],"rapid":[36],"access":[37],"personal":[39,191],"lifelogs":[40,81,186],"for":[41,57,79],"memory":[42],"recall":[43],"assistance.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48,133,178],"propose":[49],"Captioning-Integrated":[51],"Visual":[52,102],"Lifelog":[53],"(CIVIL)":[54],"Retrieval":[55],"System":[56],"extracting":[58],"images":[60],"from":[61],"user\u2019s":[63],"visual":[64,80,169,185],"based":[66],"on":[67],"textual":[68,181],"queries.":[69],"Unlike":[70],"traditional":[71],"embedding-based":[72],"methods,":[73],"our":[74,164],"system":[75],"first":[76],"generates":[77],"captions":[78,93],"and":[82,94,146],"then":[83],"utilizes":[84],"text":[86],"embedding":[87],"model":[88],"project":[90],"both":[91],"user":[95],"queries":[96],"into":[97,187],"shared":[99],"vector":[100],"space.":[101],"lifelogs,":[103],"captured":[104],"through":[105],"wearable":[106],"cameras,":[107],"provide":[108],"first-person":[110,168],"viewpoint,":[111],"necessitating":[112],"interpretation":[114],"activities":[117],"individual":[120],"behind":[121],"camera":[123],"rather":[124],"than":[125],"merely":[126],"describing":[127],"scene.":[129],"To":[130],"address":[131],"this,":[132],"introduce":[134],"three":[135],"distinct":[136],"approaches:":[137],"single":[139],"caption":[140,144,149],"method,":[141,145,150],"collective":[143],"merged":[148],"each":[151],"designed":[152],"interpret":[154],"life":[156,192],"experiences":[157],"lifeloggers.":[159],"Experimental":[160],"results":[161],"show":[162],"that":[163,183],"method":[165],"effectively":[166],"describes":[167],"images,":[170],"enhancing":[171],"outcomes":[173],"retrieval.":[176],"Furthermore,":[177],"construct":[179],"dataset":[182],"converts":[184],"captions,":[188],"thereby":[189],"reconstructing":[190],"experiences.":[193]},"counts_by_year":[],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}
