{"id":"https://openalex.org/W3092714372","doi":"https://doi.org/10.1145/3394171.3413498","title":"Learning Semantic Concepts and Temporal Alignment for Narrated Video Procedural Captioning","display_name":"Learning Semantic Concepts and Temporal Alignment for Narrated Video Procedural Captioning","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3092714372","doi":"https://doi.org/10.1145/3394171.3413498","mag":"3092714372"},"language":"en","primary_location":{"id":"doi:10.1145/3394171.3413498","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413498","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","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/A5058342038","display_name":"Botian Shi","orcid":"https://orcid.org/0000-0003-3677-7252"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Botian Shi","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100754485","display_name":"Lei Ji","orcid":"https://orcid.org/0000-0002-7569-3265"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Ji","raw_affiliation_strings":["Microsoft Research Asia & University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210113369","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082774439","display_name":"Zhendong Niu","orcid":"https://orcid.org/0000-0002-0576-7572"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhendong Niu","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042018181","display_name":"Nan Duan","orcid":"https://orcid.org/0000-0002-3387-4674"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nan Duan","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100701572","display_name":"Ming Zhou","orcid":"https://orcid.org/0000-0002-2551-2964"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Zhou","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083420537","display_name":"Xilin Chen","orcid":"https://orcid.org/0000-0003-3024-4404"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xilin Chen","raw_affiliation_strings":["University of Chinese Academy of Sciences & Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences & Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4355","last_page":"4363"},"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":0.9948999881744385,"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":0.9907000064849854,"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":0.9685508012771606},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8696246147155762},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.706512451171875},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.622516930103302},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5465339422225952},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5100606083869934},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47857263684272766},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.451614648103714},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3383725881576538},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12303051352500916}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9685508012771606},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8696246147155762},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.706512451171875},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.622516930103302},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5465339422225952},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5100606083869934},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47857263684272766},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.451614648103714},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3383725881576538},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12303051352500916},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3394171.3413498","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413498","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1586939924","https://openalex.org/W1902237438","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2066134726","https://openalex.org/W2108325777","https://openalex.org/W2139501017","https://openalex.org/W2194775991","https://openalex.org/W2296613712","https://openalex.org/W2302086703","https://openalex.org/W2558834163","https://openalex.org/W2600463316","https://openalex.org/W2745461083","https://openalex.org/W2750779823","https://openalex.org/W2798793675","https://openalex.org/W2951098185","https://openalex.org/W2952132648","https://openalex.org/W2962795934","https://openalex.org/W2963290255","https://openalex.org/W2963351113","https://openalex.org/W2963403868","https://openalex.org/W2963916161","https://openalex.org/W2964040984","https://openalex.org/W2964241990","https://openalex.org/W2971274815","https://openalex.org/W2981851019","https://openalex.org/W2985185987"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W2963177403","https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W3209117276","https://openalex.org/W4388184981","https://openalex.org/W4323777661"],"abstract_inverted_index":{"Video":[0],"captioning":[1,65,124],"is":[2,79],"a":[3,111,141,147,154,179],"fundamental":[4],"task":[5],"for":[6,122],"visual":[7],"understanding.":[8],"Previous":[9],"works":[10],"employ":[11],"end-to-end":[12],"networks":[13],"to":[14,28,41,90,101,115,149,182,187],"learn":[15,103],"from":[16,191],"the":[17,34,49,53,64,71,91,104,118,123,151,169,184,200],"low-level":[18],"vision":[19,85],"feature":[20],"and":[21,32,60,84,88,96,108,120,173],"generate":[22],"descriptive":[23],"captions,":[24],"which":[25,78,205],"are":[26],"hard":[27],"recognize":[29],"fine-grained":[30],"objects":[31],"lacks":[33],"understanding":[35],"of":[36,52,58,73,81,202],"crucial":[37],"semantic":[38,105,142],"concepts.":[39],"According":[40],"DPC":[42,68],"[19],":[43],"these":[44],"concepts":[45,106,190],"generally":[46],"present":[47],"in":[48,153],"narrative":[50],"transcripts":[51],"instructional":[54],"videos.":[55],"The":[56,195],"incorporation":[57],"transcript":[59,74,95,121,174,193],"video":[61,76,119,171],"can":[62],"improve":[63],"performance.":[66],"However,":[67],"directly":[69],"concatenates":[70],"embedding":[72],"with":[75,131],"features,":[77],"incapable":[80],"fusing":[82],"language":[83],"features":[86],"effectively":[87],"leads":[89],"temporal":[92,112,164],"mis-alignment":[93],"between":[94],"video.":[97],"This":[98],"motivates":[99],"us":[100],"1)":[102],"explicitly":[107],"2)":[109],"design":[110,140],"alignment":[113,165],"mechanism":[114,181],"better":[116],"align":[117],"task.":[125],"In":[126],"this":[127],"paper,":[128],"we":[129,139,158,177],"start":[130],"an":[132,160],"encoder-decoder":[133],"backbone":[134],"using":[135],"transformer":[136],"models.":[137],"Firstly,":[138],"concept":[143],"prediction":[144],"module":[145,186],"as":[146],"multi-task":[148],"train":[150],"encoder":[152],"supervised":[155],"way.":[156],"Then,":[157],"develop":[159],"attention":[161],"based":[162],"cross-modality":[163],"method":[166],"that":[167],"combines":[168],"sequential":[170],"frames":[172],"sentences.":[175],"Finally,":[176],"adopt":[178],"copy":[180,188],"enable":[183],"decoder(generation)":[185],"important":[189],"source":[192],"directly.":[194],"extensive":[196],"experimental":[197],"results":[198,208],"demonstrate":[199],"effectiveness":[201],"our":[203],"model,":[204],"achieves":[206],"state-of-the-art":[207],"on":[209],"YouCookII":[210],"dataset.":[211]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}