{"id":"https://openalex.org/W4281251030","doi":"https://doi.org/10.1109/icme52920.2022.9859943","title":"Support-Set Based Multi-Modal Representation Enhancement for Video Captioning","display_name":"Support-Set Based Multi-Modal Representation Enhancement for Video Captioning","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4281251030","doi":"https://doi.org/10.1109/icme52920.2022.9859943"},"language":"en","primary_location":{"id":"doi:10.1109/icme52920.2022.9859943","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859943","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","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":"2022 IEEE International Conference on Multimedia and Expo (ICME)","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/A5062917884","display_name":"Xiao\u2010Ya Chen","orcid":"https://orcid.org/0000-0002-2909-8414"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoya Chen","raw_affiliation_strings":["University of Electronic Science and Technology of China,China","University of Electronic Science and Technology of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"University of Electronic Science and Technology of China, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036987388","display_name":"Jingkuan Song","orcid":"https://orcid.org/0000-0002-2549-8322"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingkuan Song","raw_affiliation_strings":["University of Electronic Science and Technology of China,China","University of Electronic Science and Technology of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"University of Electronic Science and Technology of China, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087623065","display_name":"Pengpeng Zeng","orcid":"https://orcid.org/0000-0002-0672-3790"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengpeng Zeng","raw_affiliation_strings":["University of Electronic Science and Technology of China,China","University of Electronic Science and Technology of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"University of Electronic Science and Technology of China, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066645546","display_name":"Lianli Gao","orcid":"https://orcid.org/0000-0002-2522-6394"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianli Gao","raw_affiliation_strings":["University of Electronic Science and Technology of China,China","University of Electronic Science and Technology of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"University of Electronic Science and Technology of China, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052993469","display_name":"Heng Tao Shen","orcid":"https://orcid.org/0000-0002-2999-2088"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Tao Shen","raw_affiliation_strings":["University of Electronic Science and Technology of China,China","University of Electronic Science and Technology of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"University of Electronic Science and Technology of China, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"1","last_page":"6"},"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":0.9977999925613403,"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":0.9929999709129333,"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":0.8115614652633667},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7251429557800293},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.681286096572876},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6394460797309875},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5827892422676086},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5693908929824829},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5115183591842651},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48718756437301636},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.48252245783805847},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.461361825466156},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.44622933864593506},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4350108504295349},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35049259662628174},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3264421224594116},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.23314476013183594},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08949175477027893}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8115614652633667},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7251429557800293},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.681286096572876},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6394460797309875},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5827892422676086},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5693908929824829},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5115183591842651},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48718756437301636},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48252245783805847},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.461361825466156},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.44622933864593506},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4350108504295349},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35049259662628174},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3264421224594116},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.23314476013183594},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08949175477027893},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme52920.2022.9859943","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859943","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","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":"2022 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1987917322","display_name":null,"funder_award_id":"62122018,61772116,61872064","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5133417063","display_name":null,"funder_award_id":"2018AAA0102200","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1995820507","https://openalex.org/W2164290393","https://openalex.org/W2194775991","https://openalex.org/W2425121537","https://openalex.org/W2554906389","https://openalex.org/W2619947201","https://openalex.org/W2774267535","https://openalex.org/W2905145027","https://openalex.org/W2951390634","https://openalex.org/W2962934715","https://openalex.org/W2962990649","https://openalex.org/W2964350391","https://openalex.org/W2984862483","https://openalex.org/W3034221024","https://openalex.org/W3035365026","https://openalex.org/W3035372819","https://openalex.org/W3035392611","https://openalex.org/W3122640483","https://openalex.org/W3176425931","https://openalex.org/W3176689360","https://openalex.org/W3207608362","https://openalex.org/W3209229003","https://openalex.org/W3212148916","https://openalex.org/W4214692497","https://openalex.org/W4214931087","https://openalex.org/W6684090549","https://openalex.org/W6747225742","https://openalex.org/W6762586985","https://openalex.org/W6784184991","https://openalex.org/W6789747622","https://openalex.org/W6799700609","https://openalex.org/W6803537622","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393"],"abstract_inverted_index":{"Video":[0],"captioning":[1],"is":[2,134],"a":[3,8,17,24,48,66,75,82,100,115],"challenging":[4],"task":[5],"that":[6,126],"necessitates":[7],"thorough":[9],"comprehension":[10],"of":[11],"visual":[12,93],"scenes.":[13],"Existing":[14],"methods":[15],"follow":[16],"typical":[18],"one-to-one":[19],"mapping,":[20],"which":[21],"concentrates":[22],"on":[23,120],"limited":[25],"sample":[26],"space":[27],"while":[28],"ignoring":[29],"the":[30],"intrinsic":[31],"semantic":[32,67],"associations":[33],"between":[34,70,88],"samples,":[35],"resulting":[36],"in":[37,65,114],"rigid":[38],"and":[39,50,90,110,122],"uninformative":[40],"expressions.":[41],"To":[42],"address":[43],"this":[44,96],"issue,":[45],"we":[46,73,98],"propose":[47,74],"novel":[49],"flexible":[51],"framework,":[52],"namely":[53],"Support-set":[54,76],"based":[55],"Multi-modal":[56],"Representation":[57],"Enhancement":[58],"(SMRE)":[59],"model,":[60],"to":[61,80,84,106],"mine":[62],"rich":[63],"information":[64],"subspace":[68],"shared":[69],"samples.":[71],"Specifically,":[72],"Construction":[77],"(SC)":[78],"module":[79,105],"construct":[81],"support-set":[83],"learn":[85],"underlying":[86],"connections":[87],"samples":[89],"obtain":[91],"semantic-related":[92],"elements.":[94],"During":[95],"process,":[97],"design":[99],"Semantic":[101],"Space":[102],"Transformation":[103],"(SST)":[104],"constrain":[107],"relative":[108],"distance":[109],"administrate":[111],"multi-modal":[112],"inter-actions":[113],"self-supervised":[116],"way.":[117],"Extensive":[118],"experiments":[119],"MSVD":[121],"MSR-VTT":[123],"datasets":[124],"demonstrate":[125],"our":[127],"SMRE":[128],"achieves":[129],"state-of-the-art":[130],"performance.":[131],"Our":[132],"code":[133],"released":[135],"at":[136],"https://github.com/SMRE-CV/SMRE.":[137]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}