{"id":"https://openalex.org/W2523937091","doi":"https://doi.org/10.1145/2964284.2984064","title":"Early Embedding and Late Reranking for Video Captioning","display_name":"Early Embedding and Late Reranking for Video Captioning","publication_year":2016,"publication_date":"2016-09-29","ids":{"openalex":"https://openalex.org/W2523937091","doi":"https://doi.org/10.1145/2964284.2984064","mag":"2523937091"},"language":"en","primary_location":{"id":"doi:10.1145/2964284.2984064","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2964284.2984064","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM international conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://dare.uva.nl/personal/pure/en/publications/early-embedding-and-late-reranking-for-video-captioning(b807e00c-a919-4678-aa7c-28ab644430a3).html","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008417257","display_name":"Jianfeng Dong","orcid":"https://orcid.org/0000-0001-5244-3274"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianfeng Dong","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060270456","display_name":"Xirong Li","orcid":"https://orcid.org/0000-0002-0220-8310"},"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":"Xirong Li","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":null,"display_name":"Weiyu Lan","orcid":null},"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":"Weiyu Lan","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/A5101582804","display_name":"Yujia Huo","orcid":"https://orcid.org/0000-0002-4484-7700"},"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":"Yujia Huo","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":"last","author":{"id":"https://openalex.org/A5024508073","display_name":"Cees G. M. Snoek","orcid":"https://orcid.org/0000-0001-9092-1556"},"institutions":[{"id":"https://openalex.org/I4210135670","display_name":"Amsterdam University of the Arts","ror":"https://ror.org/04dde1554","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210135670"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Cees G.M. Snoek","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.2792,"has_fulltext":false,"cited_by_count":81,"citation_normalized_percentile":{"value":0.98709656,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1082","last_page":"1086"},"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":0.9979000091552734,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9914000034332275,"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":0.9764039516448975},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8471153974533081},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7117687463760376},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.7021023631095886},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6757198572158813},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.6568652987480164},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.527214765548706},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5062379240989685},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5033790469169617},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4659128487110138},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.42617931962013245},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4161868691444397},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34574270248413086},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.29663515090942383},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07245895266532898}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9764039516448975},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8471153974533081},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7117687463760376},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.7021023631095886},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6757198572158813},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.6568652987480164},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.527214765548706},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5062379240989685},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5033790469169617},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4659128487110138},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.42617931962013245},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4161868691444397},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34574270248413086},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.29663515090942383},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07245895266532898},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/2964284.2984064","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2964284.2984064","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM international conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:dare.uva.nl:openaire_cris_publications/b807e00c-a919-4678-aa7c-28ab644430a3","is_oa":true,"landing_page_url":"https://dare.uva.nl/personal/pure/en/publications/early-embedding-and-late-reranking-for-video-captioning(b807e00c-a919-4678-aa7c-28ab644430a3).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Dong, J, Li, X, Lan, W, Huo, Y & Snoek, C G M 2016, Early Embedding and Late Reranking for Video Captioning. in MM\u201916 : proceedings of the 2016 ACM Multimedia Conference. Association for Computing Machinery, New York, pp. 1082-1086, ACM Multimedia Conference, Amsterdam, Netherlands, 15/10/16. https://doi.org/10.1145/2964284.2984064","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:dare.uva.nl:publications/b807e00c-a919-4678-aa7c-28ab644430a3","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/early-embedding-and-late-reranking-for-video-captioning(b807e00c-a919-4678-aa7c-28ab644430a3).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Dong, J, Li, X, Lan, W, Huo, Y & Snoek, C G M 2016, Early Embedding and Late Reranking for Video Captioning. in MM\u201916 : proceedings of the 2016 ACM Multimedia Conference. Association for Computing Machinery, New York, pp. 1082-1086, ACM Multimedia Conference, Amsterdam, Netherlands, 15/10/16. https://doi.org/10.1145/2964284.2984064","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:dare.uva.nl:publications/b807e00c-a919-4678-aa7c-28ab644430a3","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:dare.uva.nl:openaire_cris_publications/b807e00c-a919-4678-aa7c-28ab644430a3","is_oa":true,"landing_page_url":"https://dare.uva.nl/personal/pure/en/publications/early-embedding-and-late-reranking-for-video-captioning(b807e00c-a919-4678-aa7c-28ab644430a3).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Dong, J, Li, X, Lan, W, Huo, Y & Snoek, C G M 2016, Early Embedding and Late Reranking for Video Captioning. in MM\u201916 : proceedings of the 2016 ACM Multimedia Conference. Association for Computing Machinery, New York, pp. 1082-1086, ACM Multimedia Conference, Amsterdam, Netherlands, 15/10/16. https://doi.org/10.1145/2964284.2984064","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.49000000953674316,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G4027869084","display_name":null,"funder_award_id":"14XNLQ01","funder_id":"https://openalex.org/F4320322499","funder_display_name":"Renmin University of China"},{"id":"https://openalex.org/G6545374415","display_name":null,"funder_award_id":"61303184","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/F4320322499","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1510632636","https://openalex.org/W1522734439","https://openalex.org/W1573040851","https://openalex.org/W1614298861","https://openalex.org/W1777628566","https://openalex.org/W1895577753","https://openalex.org/W1931639407","https://openalex.org/W1956340063","https://openalex.org/W2097117768","https://openalex.org/W2139501017","https://openalex.org/W2161258050","https://openalex.org/W2280837843","https://openalex.org/W2425121537","https://openalex.org/W2465870074","https://openalex.org/W2950577311","https://openalex.org/W2962980738","https://openalex.org/W2963576560","https://openalex.org/W4298212933","https://openalex.org/W4300560153"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"our":[3],"solution":[4,111],"for":[5,48,74],"the":[6,15,34,79,84,109,116,120,127,137,142],"MSR":[7],"Video":[8],"to":[9,38,57],"Language":[10],"Challenge.":[11],"We":[12],"start":[13],"from":[14],"popular":[16],"ConvNet":[17,98],"+":[18,99],"LSTM":[19,39,100],"model,":[20],"which":[21,32,140],"we":[22],"extend":[23],"with":[24],"two":[25,89],"novel":[26],"modules.":[27],"One":[28],"is":[29,45,112,124],"early":[30],"embedding,":[31],"enriches":[33],"current":[35],"low-level":[36],"input":[37],"by":[40,65,115,119],"tag":[41],"embeddings.":[42],"The":[43,61,106],"other":[44],"late":[46],"reranking,":[47],"re-scoring":[49],"generated":[50,145],"sentences":[51],"in":[52,130],"terms":[53,131],"of":[54,87,108,132,144],"their":[55],"relevance":[56],"a":[58,92,96],"specific":[59],"video.":[60,75],"modules":[62,90],"are":[63],"inspired":[64],"recent":[66],"works":[67],"on":[68,78],"image":[69],"captioning,":[70],"repurposed":[71],"and":[72],"redesigned":[73],"As":[76],"experiments":[77],"MSR-VTT":[80],"validation":[81],"set":[82],"show,":[83],"joint":[85],"use":[86],"these":[88],"add":[91],"clear":[93],"improvement":[94],"over":[95],"non-trivial":[97],"baseline":[101],"under":[102],"four":[103],"performance":[104],"metrics.":[105],"viability":[107],"proposed":[110],"further":[113],"confirmed":[114],"blind":[117],"test":[118],"organizers.":[121],"Our":[122],"system":[123],"ranked":[125],"at":[126],"4th":[128],"place":[129],"overall":[133],"performance,":[134],"while":[135],"scoring":[136],"best":[138],"CIDEr-D,":[139],"measures":[141],"human-likeness":[143],"captions.":[146]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":20},{"year":2018,"cited_by_count":15},{"year":2017,"cited_by_count":19},{"year":2016,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}