{"id":"https://openalex.org/W2765836634","doi":"https://doi.org/10.1145/3123266.3127901","title":"Knowing Yourself: Improving Video Caption via In-depth Recap","display_name":"Knowing Yourself: Improving Video Caption via In-depth Recap","publication_year":2017,"publication_date":"2017-10-20","ids":{"openalex":"https://openalex.org/W2765836634","doi":"https://doi.org/10.1145/3123266.3127901","mag":"2765836634"},"language":"en","primary_location":{"id":"doi:10.1145/3123266.3127901","doi":"https://doi.org/10.1145/3123266.3127901","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3123266.3127901","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Proceedings of the 25th ACM international conference on Multimedia","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5009985839","display_name":"Qin Jin","orcid":"https://orcid.org/0000-0001-6486-6020","observed_orcids":["https://orcid.org/0000-0001-6486-6020"]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qin Jin","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101776086","display_name":"Shizhe Chen","orcid":"https://orcid.org/0000-0002-7313-9703","observed_orcids":["https://orcid.org/0000-0002-7313-9703"]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shizhe Chen","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100743860","display_name":"Jia Chen","orcid":"https://orcid.org/0000-0003-2628-8471","observed_orcids":["https://orcid.org/0000-0003-2628-8471"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jia Chen","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103099928","display_name":"Alexander G. Hauptmann","orcid":"https://orcid.org/0000-0003-2123-0684","observed_orcids":["https://orcid.org/0000-0003-2123-0684"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander Hauptmann","raw_affiliation_strings":["Carnegie Mellen University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellen University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4628,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.75401735,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1906","last_page":"1911"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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":0.9994999766349792,"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":9.999999747378752e-05,"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":9.999999747378752e-05,"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/video-captioning","display_name":"video captioning","score":1.0},{"id":"https://openalex.org/keywords/model-ensembling","display_name":"model ensembling","score":0.5529999732971191},{"id":"https://openalex.org/keywords/re-ranking","display_name":"re-ranking","score":0.9959999918937683},{"id":"https://openalex.org/keywords/wisdom-of-crowds","display_name":"wisdom of crowds","score":0.878000020980835},{"id":"https://openalex.org/keywords/model-generalization","display_name":"model generalization","score":0.5799999833106995},{"id":"https://openalex.org/keywords/feature-representation","display_name":"feature representation","score":0.4440000057220459}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9917682409286499},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.864694356918335},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7002202272415161},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6597049236297607},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5966333150863647},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5185880661010742},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.49497121572494507},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4496038556098938},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4469625949859619},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4463639259338379},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4299573302268982},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4166853725910187},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32950443029403687},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.16240108013153076},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3123266.3127901","doi":"https://doi.org/10.1145/3123266.3127901","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3123266.3127901","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Proceedings of the 25th ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1573040851","https://openalex.org/W1586939924","https://openalex.org/W1931639407","https://openalex.org/W1956340063","https://openalex.org/W2064675550","https://openalex.org/W2110933980","https://openalex.org/W2120190345","https://openalex.org/W2133564696","https://openalex.org/W2136036867","https://openalex.org/W2139501017","https://openalex.org/W2142900973","https://openalex.org/W2194775991","https://openalex.org/W2274287116","https://openalex.org/W2302086703","https://openalex.org/W2411037331","https://openalex.org/W2425121537","https://openalex.org/W2523993696","https://openalex.org/W2524766041","https://openalex.org/W2527349934","https://openalex.org/W2558834163","https://openalex.org/W2575629043","https://openalex.org/W2618127004","https://openalex.org/W2752191396","https://openalex.org/W2963843052"],"related_works":["https://openalex.org/W4399423097","https://openalex.org/W2507365558","https://openalex.org/W4400207764","https://openalex.org/W4308234208","https://openalex.org/W4206910575","https://openalex.org/W4402467034","https://openalex.org/W2783312365","https://openalex.org/W7133295703","https://openalex.org/W4385832667","https://openalex.org/W3205021045"],"abstract_inverted_index":{"Generating":[0],"natural":[1],"language":[2],"descriptions":[3],"for":[4,79],"videos":[5],"(a.k.a":[6],"video":[7,84,100,110],"captioning)":[8],"has":[9],"attracted":[10],"much":[11],"research":[12],"attention":[13],"in":[14,36,65,99,153],"recent":[15],"years,":[16],"and":[17,39,103,134,176],"a":[18,72,139,156,198],"lot":[19],"of":[20,83,129,158,210],"models":[21,45,119,166],"have":[22,46,197],"been":[23,47],"proposed":[24,43],"to":[25,32,70,92,142,201],"improve":[26],"the":[27,33,57,80,94,130,143,150,168,172,181,207],"caption":[28,44,111,165,187,212],"performance.":[29],"However,":[30,189],"due":[31],"rapid":[34],"progress":[35],"dataset":[37],"expansion":[38],"feature":[40],"representation,":[41],"newly":[42],"evaluated":[48],"on":[49,171,185],"different":[50,97],"settings,":[51],"which":[52],"makes":[53],"it":[54,177],"unclear":[55],"about":[56,75],"contributions":[58],"from":[59,96,127,149],"either":[60],"features":[61],"or":[62],"models.":[63,112,213],"Therefore,":[64],"this":[66],"work":[67],"we":[68,87,114,124,137,148,195],"aim":[69],"gain":[71],"deep":[73],"understanding":[74],"\"where":[76],"are":[77,120,147],"we\"":[78],"current":[81,186,211],"development":[82],"captioning.":[85],"First,":[86],"carry":[88],"out":[89],"extensive":[90],"experiments":[91],"identify":[93],"contribution":[95],"components":[98],"captioning":[101],"task":[102],"make":[104],"fair":[105],"comparison":[106],"among":[107],"several":[108],"state-of-the-art":[109,118,169],"Second,":[113],"discover":[115],"that":[116,123,194],"these":[117],"complementary":[121],"so":[122],"could":[125],"benefit":[126],"\"wisdom":[128],"crowd\"":[131],"through":[132],"ensembling":[133],"reranking.":[135],"Finally,":[136],"give":[138],"preliminary":[140],"answer":[141],"question":[144],"\"how":[145],"far":[146],"human-level":[151,183],"performance":[152,170,184],"general''":[154],"via":[155],"series":[157],"carefully":[159],"designed":[160],"experiments.":[161],"In":[162],"summary,":[163],"our":[164,190],"achieve":[167],"MSR-VTT":[173],"2017":[174],"challenge,":[175],"is":[178],"comparable":[179],"with":[180],"average":[182],"metrics.":[188],"analysis":[191],"also":[192],"shows":[193],"still":[196],"long":[199],"way":[200],"go,":[202],"such":[203],"as":[204],"further":[205],"improving":[206],"generalization":[208],"ability":[209]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2017-11-10T00:00:00"}