{"id":"https://openalex.org/W4327950607","doi":"https://doi.org/10.1145/3588572","title":"Semantic Enhanced Video Captioning with Multi-feature Fusion","display_name":"Semantic Enhanced Video Captioning with Multi-feature Fusion","publication_year":2023,"publication_date":"2023-03-20","ids":{"openalex":"https://openalex.org/W4327950607","doi":"https://doi.org/10.1145/3588572"},"language":"en","primary_location":{"id":"doi:10.1145/3588572","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1145/3588572","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"type":"article","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/A5049500421","display_name":"Tian-Zi Niu","orcid":"https://orcid.org/0000-0002-7389-5883"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tian-Zi Niu","raw_affiliation_strings":["School of Software, Shandong University, China"],"raw_orcid":"https://orcid.org/0000-0002-7389-5883","affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004858240","display_name":"Shan-Shan Dong","orcid":"https://orcid.org/0000-0002-2500-9488"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shan-Shan Dong","raw_affiliation_strings":["School of Software, Shandong University, China"],"raw_orcid":"https://orcid.org/0000-0002-2500-9488","affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021275163","display_name":"Zhen-Duo Chen","orcid":"https://orcid.org/0000-0002-3481-4892"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen-Duo Chen","raw_affiliation_strings":["School of Software, Shandong University, China"],"raw_orcid":"https://orcid.org/0000-0002-3481-4892","affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052168662","display_name":"Xin Luo","orcid":"https://orcid.org/0000-0002-6901-5476"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Luo","raw_affiliation_strings":["School of Software, Shandong University, China"],"raw_orcid":"https://orcid.org/0000-0002-6901-5476","affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084460856","display_name":"Shanqing Guo","orcid":"https://orcid.org/0000-0003-3367-0951"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shanqing Guo","raw_affiliation_strings":["School of Cyber Science and Technology, Shandong University, China"],"raw_orcid":"https://orcid.org/0000-0003-3367-0951","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Technology, Shandong University, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078170935","display_name":"Zi Huang","orcid":"https://orcid.org/0000-0002-9738-4949"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]},{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zi Huang","raw_affiliation_strings":["School of Information Technology and Electrical Engineering, The University of Queensland, Australia"],"raw_orcid":"https://orcid.org/0000-0002-9738-4949","affiliations":[{"raw_affiliation_string":"School of Information Technology and Electrical Engineering, The University of Queensland, Australia","institution_ids":["https://openalex.org/I160993911","https://openalex.org/I165143802"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086235570","display_name":"Xin-Shun Xu","orcid":"https://orcid.org/0000-0001-9972-7370"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin-Shun Xu","raw_affiliation_strings":["School of Software, Shandong University, China"],"raw_orcid":"https://orcid.org/0000-0001-9972-7370","affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, China","institution_ids":["https://openalex.org/I154099455"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4254,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.60201623,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"19","issue":"6","first_page":"1","last_page":"21"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9973999857902527,"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":0.9965999722480774,"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/closed-captioning","display_name":"Closed captioning","score":0.9460774660110474},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9135761260986328},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5965249538421631},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5781181454658508},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.557133138179779},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5139588713645935},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.49129217863082886},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4664062559604645},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.4639192819595337},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.41093289852142334},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.39931631088256836},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.16358813643455505},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.08034244179725647}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9460774660110474},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9135761260986328},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5965249538421631},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5781181454658508},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.557133138179779},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5139588713645935},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.49129217863082886},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4664062559604645},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.4639192819595337},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.41093289852142334},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39931631088256836},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.16358813643455505},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.08034244179725647},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3588572","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1145/3588572","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1435273207","display_name":null,"funder_award_id":"61991411","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"},{"id":"https://openalex.org/G513007275","display_name":null,"funder_award_id":"62202278","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5593383844","display_name":null,"funder_award_id":"61991411","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5877029504","display_name":null,"funder_award_id":"ZR2019ZD06","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"},{"id":"https://openalex.org/G6703053633","display_name":null,"funder_award_id":"62172256, 62202278, and 62202272","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7923371280","display_name":null,"funder_award_id":"62202272","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G98586731","display_name":null,"funder_award_id":"62172256","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation 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/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1601567445","https://openalex.org/W1931639407","https://openalex.org/W1956340063","https://openalex.org/W2117539524","https://openalex.org/W2157331557","https://openalex.org/W2186222003","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2602753196","https://openalex.org/W2892181857","https://openalex.org/W2956959730","https://openalex.org/W2972281329","https://openalex.org/W2996817764","https://openalex.org/W3009192917","https://openalex.org/W3034464851","https://openalex.org/W3111947517","https://openalex.org/W3134875898","https://openalex.org/W3211865849","https://openalex.org/W4213031069","https://openalex.org/W4214931354","https://openalex.org/W4234552385","https://openalex.org/W4286488082","https://openalex.org/W4301409532"],"related_works":["https://openalex.org/W2473933584","https://openalex.org/W2932687906","https://openalex.org/W2384506582","https://openalex.org/W1999004178","https://openalex.org/W2280723418","https://openalex.org/W2350165951","https://openalex.org/W2389537640","https://openalex.org/W1898182388","https://openalex.org/W2082085186","https://openalex.org/W2369105423"],"abstract_inverted_index":{"Video":[0,220],"captioning":[1,113],"aims":[2],"to":[3,39,138,147,157,167,182,192,226,237],"automatically":[4],"describe":[5],"a":[6,57,87,106,133,144,151,172,177],"video":[7,88,112],"clip":[8],"with":[9,89,114],"informative":[10],"sentences.":[11],"At":[12],"present,":[13],"deep":[14],"learning-based":[15],"models":[16],"have":[17],"become":[18],"the":[19,71,122,184,199,203],"mainstream":[20],"for":[21,118,198],"this":[22],"task":[23],"and":[24,62,160,186,224],"achieved":[25],"competitive":[26],"results":[27,231],"on":[28,217],"public":[29],"datasets.":[30,229],"Usually,":[31],"these":[32,102],"methods":[33,51],"leverage":[34],"different":[35,74,125,162,165,190],"types":[36,75,126],"of":[37,59,68,76,81,86,124,127,189],"features":[38,128,142,159,191,197],"generate":[40],"sentences,":[41],"e.g.,":[42],"semantic":[43,54,134,141,145],"information,":[44],"2D":[45],"or":[46],"3D":[47],"features.":[48,77],"However,":[49],"some":[50,67],"only":[52],"treat":[53],"information":[55],"as":[56],"complement":[58],"visual":[60,196],"representations":[61],"cannot":[63],"fully":[64],"exploit":[65],"it;":[66],"them":[69,82],"ignore":[70],"relationship":[72],"between":[73],"In":[78],"addition,":[79],"most":[80],"select":[83],"multiple":[84],"frames":[85],"an":[90,210],"equally":[91],"spaced":[92],"sampling":[93],"scheme,":[94],"resulting":[95],"in":[96,209],"much":[97],"redundant":[98],"information.":[99],"To":[100],"address":[101],"issues,":[103],"we":[104],"present":[105],"novel":[107,178],"video-captioning":[108],"framework,":[109],"Semantic":[110],"Enhanced":[111],"Multi-feature":[115],"Fusion,":[116],"SEMF":[117,234],"short.":[119],"It":[120],"optimizes":[121],"use":[123],"from":[129],"three":[130],"aspects.":[131],"First,":[132],"encoder":[135],"is":[136,235],"designed":[137],"enhance":[139],"meaningful":[140],"through":[143],"dictionary":[146],"boost":[148],"performance.":[149],"Second,":[150],"discrete":[152],"selection":[153],"module":[154,175],"pays":[155],"attention":[156,180],"important":[158],"obtains":[161],"contexts":[163],"at":[164],"steps":[166],"reduce":[168],"feature":[169],"redundancy.":[170],"Finally,":[171],"multi-feature":[173],"fusion":[174],"uses":[176],"relation-aware":[179],"mechanism":[181],"separate":[183],"common":[185],"complementary":[187],"components":[188],"provide":[193],"more":[194],"effective":[195],"next":[200],"step.":[201],"Moreover,":[202],"entire":[204],"framework":[205],"can":[206],"be":[207],"trained":[208],"end-to-end":[211],"manner.":[212],"Extensive":[213],"experiments":[214],"are":[215],"conducted":[216],"Microsoft":[218],"Research":[219],"Description":[221],"Corpus":[222],"(MSVD)":[223],"MSR-Video":[225],"Text":[227],"(MSR-VTT)":[228],"The":[230],"demonstrate":[232],"that":[233],"able":[236],"achieve":[238],"state-of-the-art":[239],"results.":[240]},"counts_by_year":[{"year":2024,"cited_by_count":4}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
