{"id":"https://openalex.org/W4319780335","doi":"https://doi.org/10.1109/imcom56909.2023.10035642","title":"End-To-End Training Of Object Segmentation Task And Video Question-Answering Task","display_name":"End-To-End Training Of Object Segmentation Task And Video Question-Answering Task","publication_year":2023,"publication_date":"2023-01-03","ids":{"openalex":"https://openalex.org/W4319780335","doi":"https://doi.org/10.1109/imcom56909.2023.10035642"},"language":"en","primary_location":{"id":"doi:10.1109/imcom56909.2023.10035642","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/imcom56909.2023.10035642","pdf_url":null,"source":{"id":"https://openalex.org/S4363608560","display_name":"2023 17th International Conference on Ubiquitous Information Management and Communication (IMCOM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 17th International Conference on Ubiquitous Information Management and Communication (IMCOM)","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/A5027931271","display_name":"Hidemoto Nakada","orcid":"https://orcid.org/0000-0002-8901-2504"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hidemoto Nakada","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology,Artificial Intelligence Research Center,Tukuba,Japan","Artificial Intelligence Research Center, National Institute of Advanced Industrial Science and Technology, Tukuba, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology,Artificial Intelligence Research Center,Tukuba,Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"Artificial Intelligence Research Center, National Institute of Advanced Industrial Science and Technology, Tukuba, Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073671259","display_name":"Hideki Asoh","orcid":"https://orcid.org/0000-0002-0891-3782"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hideki Asoh","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology,Artificial Intelligence Research Center,Tukuba,Japan","Artificial Intelligence Research Center, National Institute of Advanced Industrial Science and Technology, Tukuba, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology,Artificial Intelligence Research Center,Tukuba,Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"Artificial Intelligence Research Center, National Institute of Advanced Industrial Science and Technology, Tukuba, Japan","institution_ids":["https://openalex.org/I73613424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I73613424"],"apc_list":null,"apc_paid":null,"fwci":0.2428,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.52411881,"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":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9994999766349792,"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/task","display_name":"Task (project management)","score":0.842971920967102},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7890981435775757},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.74962317943573},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7441709637641907},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.7073910236358643},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6340522170066833},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6077668070793152},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.42004796862602234},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3499550223350525},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08121931552886963}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.842971920967102},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7890981435775757},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.74962317943573},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7441709637641907},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.7073910236358643},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6340522170066833},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6077668070793152},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42004796862602234},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3499550223350525},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08121931552886963},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/imcom56909.2023.10035642","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/imcom56909.2023.10035642","pdf_url":null,"source":{"id":"https://openalex.org/S4363608560","display_name":"2023 17th International Conference on Ubiquitous Information Management and Communication (IMCOM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 17th International Conference on Ubiquitous Information Management and Communication (IMCOM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W3177225079","https://openalex.org/W4288093753","https://openalex.org/W4295246696","https://openalex.org/W6640963894","https://openalex.org/W6755207826","https://openalex.org/W6758420182","https://openalex.org/W6768853884","https://openalex.org/W6769024994","https://openalex.org/W6793462482","https://openalex.org/W6798359198"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3179968364","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W2349927912","https://openalex.org/W2732813147","https://openalex.org/W2143460112"],"abstract_inverted_index":{"For":[0],"complicated":[1],"Visual":[2],"Question":[3],"Answering(VQA)":[4],"tasks":[5],"that":[6,100],"incorporates":[7],"multiple":[8],"objects,":[9],"to":[10,23,35,92],"train":[11,36],"the":[12,37,71,80,83,101],"VQA":[13,38,58,77],"model":[14,40,44],"using":[15,79],"segmented":[16],"objects":[17],"data":[18],"as":[19,55],"inputs":[20],"is":[21],"proved":[22],"be":[24],"effective":[25],"for":[26],"various":[27],"downstream":[28],"tasks.":[29],"In":[30],"this":[31],"work,":[32],"we":[33,87],"tried":[34],"task":[39,105],"and":[41,73,90,98],"object":[42,67],"segmentation":[43,68],"in":[45,95],"end-to-end":[46,96],"fashion":[47],"instead":[48],"of":[49,82,103],"training":[50],"independently.":[51],"We":[52,60],"employed":[53],"CLEVRER":[54],"a":[56,76],"target":[57],"task.":[59],"first":[61],"trained":[62,74,84],"MONet(Multiple":[63],"Object":[64],"Network),":[65],"an":[66],"network,":[69],"with":[70],"dataset,":[72],"Aloe,":[75],"model,":[78],"output":[81],"MONet.":[85],"Finally":[86],"connect":[88],"MONet":[89],"Aloe":[91],"fine-tune":[93],"them":[94],"setting":[97],"confirmed":[99],"performance":[102],"VOA":[104],"has":[106],"been":[107],"greatly":[108],"improved.":[109]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
