{"id":"https://openalex.org/W3165961049","doi":"https://doi.org/10.1109/icme51207.2021.9428461","title":"Hierarchical Representation Network With Auxiliary Tasks For Video Captioning","display_name":"Hierarchical Representation Network With Auxiliary Tasks For Video Captioning","publication_year":2021,"publication_date":"2021-06-09","ids":{"openalex":"https://openalex.org/W3165961049","doi":"https://doi.org/10.1109/icme51207.2021.9428461","mag":"3165961049"},"language":"en","primary_location":{"id":"doi:10.1109/icme51207.2021.9428461","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme51207.2021.9428461","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-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/A5100445935","display_name":"Lei Yu","orcid":"https://orcid.org/0000-0002-9188-6112"},"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":true,"raw_author_name":"Yu Lei","raw_affiliation_strings":["University of Electronic Science and Technology of China,China","University of Electronic Science and Technology of China, China"],"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/A5100934920","display_name":"Zhonghai He","orcid":null},"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":"Zhonghai He","raw_affiliation_strings":["University of Electronic Science and Technology of China,China","University of Electronic Science and Technology of China, China"],"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"],"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"],"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/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"],"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":5,"corresponding_author_ids":["https://openalex.org/A5100445935"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.0961,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.36593137,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"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":0.9993000030517578,"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":0.996999979019165,"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":0.9037070274353027},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8498313426971436},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.6649320125579834},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6194813847541809},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5779539346694946},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5726889371871948},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5623332858085632},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5245083570480347},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5103065371513367},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.484971284866333},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4745030105113983},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.45739778876304626},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.42310744524002075},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.11383917927742004},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07728749513626099}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9037070274353027},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8498313426971436},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.6649320125579834},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6194813847541809},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5779539346694946},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5726889371871948},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5623332858085632},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5245083570480347},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5103065371513367},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.484971284866333},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4745030105113983},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.45739778876304626},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.42310744524002075},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11383917927742004},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07728749513626099},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme51207.2021.9428461","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme51207.2021.9428461","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"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":20,"referenced_works":["https://openalex.org/W1586939924","https://openalex.org/W2139501017","https://openalex.org/W2425121537","https://openalex.org/W2739107216","https://openalex.org/W2948358897","https://openalex.org/W2951390634","https://openalex.org/W2962681491","https://openalex.org/W2962990649","https://openalex.org/W2963971014","https://openalex.org/W2984862483","https://openalex.org/W2988753485","https://openalex.org/W2989322838","https://openalex.org/W2996984511","https://openalex.org/W3035356601","https://openalex.org/W3035365026","https://openalex.org/W3035372819","https://openalex.org/W6749578958","https://openalex.org/W6762586985","https://openalex.org/W6766991472","https://openalex.org/W6773982136"],"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/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4399485860"],"abstract_inverted_index":{"Video":[0],"captioning":[1],"is":[2,21],"to":[3,15,23,107,110,116,122],"understand":[4],"a":[5,25,60],"video":[6,26,53,78],"in":[7,51],"depth":[8],"and":[9,39,44,75,103,135],"generate":[10],"high-quality":[11,52],"descriptions.":[12],"However,":[13],"due":[14],"the":[16,81,86,95,117,123,133],"complexity":[17],"of":[18,34,88,91,98,137],"videos,":[19,92],"it":[20],"challenging":[22],"extract":[24],"feature":[27],"that":[28],"can":[29],"well":[30],"represent":[31],"multiple":[32],"levels":[33],"concepts":[35],"i.e.,":[36],"events,":[37],"objects":[38],"actions.":[40],"Meanwhile,":[41],"content":[42],"completeness":[43],"syntactic":[45],"consistency":[46],"play":[47],"an":[48],"important":[49],"role":[50],"captioning.":[54,79],"Motivated":[55],"by":[56,94],"these,":[57],"we":[58],"propose":[59],"novel":[61],"framework,":[62],"named":[63],"Hierarchical":[64],"Representation":[65],"Network":[66],"with":[67,141],"Auxiliary":[68],"Tasks":[69],"(HRNAT),":[70],"for":[71],"learning":[72,87],"multi-level":[73],"representations,":[74],"generating":[76,108],"syntax-aware":[77],"Specifically,":[80],"Cross-modality":[82],"Matching":[83],"Task":[84,102,105],"enables":[85],"hierarchical":[89],"representation":[90,97],"guided":[93],"three-level":[96],"languages.":[99],"The":[100],"Syntax-guiding":[101],"Vision-assist":[104],"contribute":[106],"descriptions":[109],"be":[111],"not":[112],"only":[113],"globally":[114],"similar":[115],"video,":[118],"but":[119],"also":[120],"syntax-consistent":[121],"ground-truth":[124],"description.":[125],"Finally,":[126],"performances":[127],"on":[128],"several":[129],"benchmark":[130],"datasets":[131],"validate":[132],"effectiveness":[134],"superiority":[136],"our":[138],"method":[139],"compared":[140],"state-of-the-art":[142],"methods.":[143]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
