{"id":"https://openalex.org/W4399323584","doi":"https://doi.org/10.1145/3643832.3661407","title":"Poster: Translating Vision into Words: Advancing Object Recognition with Visual-Language Models","display_name":"Poster: Translating Vision into Words: Advancing Object Recognition with Visual-Language Models","publication_year":2024,"publication_date":"2024-06-03","ids":{"openalex":"https://openalex.org/W4399323584","doi":"https://doi.org/10.1145/3643832.3661407"},"language":"en","primary_location":{"id":"doi:10.1145/3643832.3661407","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3643832.3661407","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3643832.3661407","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd Annual International Conference on Mobile Systems, Applications and Services","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3643832.3661407","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023279673","display_name":"Haruki Yonekura","orcid":"https://orcid.org/0000-0001-8184-3883"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Haruki Yonekura","raw_affiliation_strings":["Information Science and Technology, Osaka University, Suita, Osaka, Japan"],"raw_orcid":"https://orcid.org/0000-0001-8184-3883","affiliations":[{"raw_affiliation_string":"Information Science and Technology, Osaka University, Suita, Osaka, Japan","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013317917","display_name":"Hamada Rizk","orcid":"https://orcid.org/0000-0002-8278-8801"},"institutions":[{"id":"https://openalex.org/I21376657","display_name":"Tanta University","ror":"https://ror.org/016jp5b92","country_code":"EG","type":"education","lineage":["https://openalex.org/I21376657"]},{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["EG","JP"],"is_corresponding":false,"raw_author_name":"Hamada Rizk","raw_affiliation_strings":["Information Science and Technology, Osaka University, Suita, Osaka, Japan","the Department of Computer and Control Engineering, Tanta University, Tanta, Gharbia, Egypt","Information Science and Technology, Osaka University, Suita, Osaka, Japan the Department of Computer and Control Engineering, Tanta University, Tanta, Gharbia, Egypt"],"raw_orcid":"https://orcid.org/0000-0002-8278-8801","affiliations":[{"raw_affiliation_string":"Information Science and Technology, Osaka University, Suita, Osaka, Japan","institution_ids":["https://openalex.org/I98285908"]},{"raw_affiliation_string":"the Department of Computer and Control Engineering, Tanta University, Tanta, Gharbia, Egypt","institution_ids":["https://openalex.org/I21376657"]},{"raw_affiliation_string":"Information Science and Technology, Osaka University, Suita, Osaka, Japan the Department of Computer and Control Engineering, Tanta University, Tanta, Gharbia, Egypt","institution_ids":["https://openalex.org/I21376657","https://openalex.org/I98285908"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084448172","display_name":"Hirozumi Yamaguchi","orcid":"https://orcid.org/0000-0003-2273-4876"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hirozumi Yamaguchi","raw_affiliation_strings":["Information Science and Technology, Osaka University, Suita, Osaka, Japan"],"raw_orcid":"https://orcid.org/0000-0003-2273-4876","affiliations":[{"raw_affiliation_string":"Information Science and Technology, Osaka University, Suita, Osaka, Japan","institution_ids":["https://openalex.org/I98285908"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"740","last_page":"741"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7120000123977661,"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":0.7120000123977661,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.6227999925613403,"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/computer-science","display_name":"Computer science","score":0.7959259152412415},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.677223265171051},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.572849690914154},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.5612702369689941},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5161693692207336},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4622156023979187}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7959259152412415},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.677223265171051},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.572849690914154},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.5612702369689941},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5161693692207336},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4622156023979187}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3643832.3661407","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3643832.3661407","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3643832.3661407","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd Annual International Conference on Mobile Systems, Applications and Services","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3643832.3661407","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3643832.3661407","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3643832.3661407","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd Annual International Conference on Mobile Systems, Applications and Services","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6200000047683716,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G3995237540","display_name":"\u5730\u57df\u3092\u652f\u3048\u308b\u77e5\u306e\u30c7\u30b8\u30bf\u30e9\u30a4\u30bc\u30fc\u30b7\u30e7\u30f3\u3068\u5171\u6709\u57fa\u76e4","funder_award_id":"JPMJCR21M5","funder_id":"https://openalex.org/F4320334789","funder_display_name":"Japan Science and Technology Agency"},{"id":"https://openalex.org/G7116398426","display_name":"Towards The First Global Indoor Positioning System Using Geometric Modeling and Advanced Artificial Intelligence Techniques","funder_award_id":"22K12011","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"},{"id":"https://openalex.org/F4320334789","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4399323584.pdf"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W3135367836","https://openalex.org/W4285502568","https://openalex.org/W4309156381","https://openalex.org/W4310430488","https://openalex.org/W4392159278","https://openalex.org/W6764040762"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Poster:":[0],"This":[1,52],"study":[2],"focuses":[3],"on":[4,56],"automatically":[5],"identifying":[6],"and":[7,29,67,106,114],"classifying":[8],"objects":[9],"within":[10],"indoor":[11,58],"environments.":[12],"Traditional":[13],"methods":[14],"struggle":[15],"with":[16,108],"this":[17],"task":[18],"due":[19],"to":[20,87],"the":[21,30,78,83,96],"high":[22],"cost":[23],"of":[24,33],"manually":[25],"labeling":[26],"each":[27],"object":[28],"inherent":[31],"ambiguity":[32],"written":[34],"descriptions.":[35],"To":[36],"overcome":[37],"these":[38],"limitations,":[39],"we":[40],"propose":[41],"a":[42,49],"novel":[43],"instance":[44],"segmentation":[45],"approach":[46],"that":[47],"utilizes":[48],"visual-language":[50],"model.":[51],"system":[53,84],"is":[54],"trained":[55],"extensive":[57],"environment":[59],"data,":[60],"including":[61],"detailed":[62],"point":[63],"clouds":[64],"(3D":[65],"representations)":[66],"RGB":[68],"images,":[69],"readily":[70],"collected":[71],"by":[72],"modern":[73],"smartphone":[74],"sensors.":[75],"By":[76],"eliminating":[77],"need":[79],"for":[80,89],"pre-defined":[81],"labels,":[82],"allows":[85],"users":[86],"search":[88],"items":[90],"using":[91],"natural":[92],"language.":[93],"We":[94],"evaluate":[95],"system's":[97],"effectiveness":[98],"through":[99],"experiments":[100],"analyzing":[101],"performance":[102],"metrics":[103],"like":[104],"accuracy":[105],"efficiency":[107],"public":[109],"datasets,":[110],"demonstrating":[111],"its":[112],"practicality":[113],"potential":[115],"usefulness.":[116]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}