{"id":"https://openalex.org/W2951098185","doi":"https://doi.org/10.18653/v1/p19-1641","title":"Dense Procedure Captioning in Narrated Instructional Videos","display_name":"Dense Procedure Captioning in Narrated Instructional Videos","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2951098185","doi":"https://doi.org/10.18653/v1/p19-1641","mag":"2951098185"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1641","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1641","pdf_url":"https://www.aclweb.org/anthology/P19-1641.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P19-1641.pdf","any_repository_has_fulltext":null},"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":true,"raw_author_name":"Botian Shi","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"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/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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Ji","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Science, Beijing, China","Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100678419","display_name":"Yaobo Liang","orcid":"https://orcid.org/0000-0002-6595-5145"},"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":"Yaobo Liang","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"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"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100338429","display_name":"Peng Chen","orcid":"https://orcid.org/0000-0001-5221-3655"},"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":"Peng Chen","raw_affiliation_strings":["Microsoft Research and AI Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research and AI Group, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"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"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","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"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5058342038"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":3.3715,"has_fulltext":true,"cited_by_count":71,"citation_normalized_percentile":{"value":0.94076386,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6382","last_page":"6391"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9988999962806702,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9988999962806702,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9987999796867371,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9710999727249146,"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/closed-captioning","display_name":"Closed captioning","score":0.9851207733154297},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8591979742050171},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48291608691215515},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4787273108959198},{"id":"https://openalex.org/keywords/snippet","display_name":"Snippet","score":0.4484177827835083},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.42316025495529175},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4181765913963318},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3889407515525818},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38634803891181946},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.18567726016044617}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9851207733154297},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8591979742050171},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48291608691215515},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4787273108959198},{"id":"https://openalex.org/C2777822670","wikidata":"https://www.wikidata.org/wiki/Q1120538","display_name":"Snippet","level":2,"score":0.4484177827835083},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.42316025495529175},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4181765913963318},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3889407515525818},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38634803891181946},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.18567726016044617},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p19-1641","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1641","pdf_url":"https://www.aclweb.org/anthology/P19-1641.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1641","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1641","pdf_url":"https://www.aclweb.org/anthology/P19-1641.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8700000047683716}],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4020255992","display_name":null,"funder_award_id":"Project","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4122877081","display_name":null,"funder_award_id":"No.2012CB7207002","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G467322759","display_name":null,"funder_award_id":"2012CB7207002","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G4803633324","display_name":null,"funder_award_id":"No. 61370137","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G635447344","display_name":null,"funder_award_id":"61370137","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7286328465","display_name":null,"funder_award_id":"2016/2-7","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/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2951098185.pdf","grobid_xml":"https://content.openalex.org/works/W2951098185.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W410625161","https://openalex.org/W639708223","https://openalex.org/W805710393","https://openalex.org/W1522301498","https://openalex.org/W1586939924","https://openalex.org/W1992681465","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2108710284","https://openalex.org/W2123301721","https://openalex.org/W2130942839","https://openalex.org/W2139019684","https://openalex.org/W2139594308","https://openalex.org/W2139857301","https://openalex.org/W2194775991","https://openalex.org/W2296613712","https://openalex.org/W2398250566","https://openalex.org/W2425121537","https://openalex.org/W2519328139","https://openalex.org/W2523993696","https://openalex.org/W2613718673","https://openalex.org/W2755876276","https://openalex.org/W2766375149","https://openalex.org/W2784025607","https://openalex.org/W2798793675","https://openalex.org/W2883910824","https://openalex.org/W2891955747","https://openalex.org/W2896457183","https://openalex.org/W2949789546","https://openalex.org/W2952132648","https://openalex.org/W2962795934","https://openalex.org/W2962799512","https://openalex.org/W2962994439","https://openalex.org/W2963341956","https://openalex.org/W2963351113","https://openalex.org/W2963403868","https://openalex.org/W2963753226","https://openalex.org/W2963916161","https://openalex.org/W2963919999","https://openalex.org/W2964040984","https://openalex.org/W2964121744","https://openalex.org/W2964214371","https://openalex.org/W2964241990","https://openalex.org/W3123077146","https://openalex.org/W4298000964","https://openalex.org/W4299341000","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W1607713096","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"],"abstract_inverted_index":{"Understanding":[0],"narrated":[1,27,59],"instructional":[2,28,60],"videos":[3,29,61],"is":[4],"important":[5,144],"for":[6,145],"both":[7,136],"research":[8],"and":[9,48,70,97,128,130,140],"real-world":[10],"web":[11],"applications.":[12],"Motivated":[13],"by":[14,66,85,101],"video":[15,42,46,64,91,103,138],"dense":[16,43],"captioning,":[17,129],"we":[18,77],"propose":[19],"a":[20,32,79,86,108],"model":[21,120],"to":[22,81],"generate":[23,49,99],"procedure":[24,126],"captions":[25,50,100],"from":[26],"which":[30,89],"are":[31,143],"sequence":[33],"of":[34,110],"stepwise":[35],"clips":[36],"with":[37,93],"description.":[38],"Previous":[39],"works":[40],"on":[41],"captioning":[44],"learn":[45],"segments":[47],"without":[51],"considering":[52],"transcripts.":[53],"We":[54],"argue":[55],"that":[56,118,135],"transcripts":[57,111,142],"in":[58,125],"can":[62,121],"enhance":[63],"representation":[65],"providing":[67],"fine-grained":[68],"complimentary":[69],"semantic":[71],"textual":[72],"information.":[73],"In":[74],"this":[75],"paper,":[76],"introduce":[78],"framework":[80],"(1)":[82],"extract":[83],"procedures":[84],"cross-modality":[87],"module,":[88],"fuses":[90],"content":[92],"the":[94,131,137,141,146],"entire":[95],"transcript;":[96],"(2)":[98],"encoding":[102],"frames":[104,139],"as":[105,107],"well":[106],"snippet":[109],"within":[112],"each":[113],"extracted":[114],"procedure.":[115],"Experiments":[116],"show":[117],"our":[119],"achieve":[122],"state-of-the-art":[123],"performance":[124],"extraction":[127],"ablation":[132],"studies":[133],"demonstrate":[134],"task.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}