{"id":"https://openalex.org/W2895845501","doi":"https://doi.org/10.1145/3240508.3240667","title":"SibNet","display_name":"SibNet","publication_year":2018,"publication_date":"2018-10-15","ids":{"openalex":"https://openalex.org/W2895845501","doi":"https://doi.org/10.1145/3240508.3240667","mag":"2895845501"},"language":"en","primary_location":{"id":"doi:10.1145/3240508.3240667","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3240508.3240667","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM international conference on Multimedia","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/A5100319993","display_name":"Sheng Liu","orcid":"https://orcid.org/0000-0001-9608-0524"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sheng Liu","raw_affiliation_strings":["State University of New York at Buffalo, Buffalo, NY, USA"],"affiliations":[{"raw_affiliation_string":"State University of New York at Buffalo, Buffalo, NY, USA","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083293468","display_name":"Zhou Ren","orcid":"https://orcid.org/0000-0002-1402-966X"},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhou Ren","raw_affiliation_strings":["Snap Research, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"Snap Research, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I4210142583"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085245110","display_name":"Junsong Yuan","orcid":"https://orcid.org/0000-0002-7901-8793"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junsong Yuan","raw_affiliation_strings":["State University of New York at Buffalo, Buffalo, NY, USA"],"affiliations":[{"raw_affiliation_string":"State University of New York at Buffalo, Buffalo, NY, USA","institution_ids":["https://openalex.org/I63190737"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100319993"],"corresponding_institution_ids":["https://openalex.org/I63190737"],"apc_list":null,"apc_paid":null,"fwci":4.5961,"has_fulltext":false,"cited_by_count":74,"citation_normalized_percentile":{"value":0.96296161,"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":"1425","last_page":"1434"},"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":0.9991999864578247,"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":0.9976999759674072,"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/computer-science","display_name":"Computer science","score":0.8883708715438843},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7562984824180603},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.6301449537277222},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5903191566467285},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5532841682434082},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.532995343208313},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5255778431892395},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48166024684906006},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4566052258014679},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4559441804885864},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.44705408811569214},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.44340577721595764},{"id":"https://openalex.org/keywords/information-flow","display_name":"Information flow","score":0.4278199076652527},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.39696934819221497},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33698445558547974},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.2880536913871765},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.23845285177230835},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.19368195533752441}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8883708715438843},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7562984824180603},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6301449537277222},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5903191566467285},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5532841682434082},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.532995343208313},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5255778431892395},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48166024684906006},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4566052258014679},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4559441804885864},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.44705408811569214},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.44340577721595764},{"id":"https://openalex.org/C2779136372","wikidata":"https://www.wikidata.org/wiki/Q10283002","display_name":"Information flow","level":2,"score":0.4278199076652527},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39696934819221497},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33698445558547974},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2880536913871765},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.23845285177230835},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.19368195533752441},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/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},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","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},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3240508.3240667","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3240508.3240667","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332641","display_name":"University at Buffalo","ror":"https://ror.org/01y64my43"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W15066456","https://openalex.org/W398859631","https://openalex.org/W569478347","https://openalex.org/W1522301498","https://openalex.org/W1522734439","https://openalex.org/W1533861849","https://openalex.org/W1573040851","https://openalex.org/W1586939924","https://openalex.org/W1665214252","https://openalex.org/W1956340063","https://openalex.org/W1968240228","https://openalex.org/W2080672747","https://openalex.org/W2095705004","https://openalex.org/W2097117768","https://openalex.org/W2101105183","https://openalex.org/W2139501017","https://openalex.org/W2154652894","https://openalex.org/W2158139315","https://openalex.org/W2164290393","https://openalex.org/W2180092181","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2302086703","https://openalex.org/W2339652278","https://openalex.org/W2425121537","https://openalex.org/W2507009361","https://openalex.org/W2507365558","https://openalex.org/W2523937091","https://openalex.org/W2523993696","https://openalex.org/W2526544345","https://openalex.org/W2527145521","https://openalex.org/W2527238922","https://openalex.org/W2527349934","https://openalex.org/W2528777330","https://openalex.org/W2556388456","https://openalex.org/W2558834163","https://openalex.org/W2559542432","https://openalex.org/W2565656701","https://openalex.org/W2584992898","https://openalex.org/W2593390416","https://openalex.org/W2597655663","https://openalex.org/W2607119937","https://openalex.org/W2607151106","https://openalex.org/W2749708282","https://openalex.org/W2752191396","https://openalex.org/W2765658575","https://openalex.org/W2766375149","https://openalex.org/W2767057417","https://openalex.org/W2950178297","https://openalex.org/W2952296662","https://openalex.org/W2962681491","https://openalex.org/W2963410018","https://openalex.org/W2963446712","https://openalex.org/W2963465031","https://openalex.org/W2963576560","https://openalex.org/W2963843052","https://openalex.org/W2964065937","https://openalex.org/W2964241990","https://openalex.org/W2964308564","https://openalex.org/W2964350399","https://openalex.org/W3102566412"],"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/W4289422896"],"abstract_inverted_index":{"Video":[0],"captioning":[1],"is":[2],"a":[3,33,41,52,99,142],"challenging":[4],"task":[5],"owing":[6],"to":[7,55,102],"the":[8,12,64,69,74,79,115,121,135],"complexity":[9],"of":[10,68],"understanding":[11],"copious":[13],"visual":[14,65],"information":[15,31,67,81,123],"in":[16,36,124],"videos":[17],"and":[18,73,95,112,130],"describing":[19],"it":[20],"using":[21,32],"natural":[22],"language.":[23],"Different":[24],"from":[25],"previous":[26],"work":[27],"that":[28,134],"encodes":[29,63,78],"video":[30,48,70],"single":[34],"flow,":[35],"this":[37],"work,":[38],"we":[39],"introduce":[40],"novel":[42],"Sibling":[43],"Convolutional":[44],"Encoder":[45],"(SibNet)":[46],"for":[47],"captioning,":[49],"which":[50],"utilizes":[51],"two-branch":[53],"architecture":[54,137],"collaboratively":[56],"encode":[57],"videos.":[58,125],"The":[59],"first":[60],"content":[61,66,111],"branch":[62,77],"via":[71],"autoencoder,":[72],"second":[75],"semantic":[76,80,113],"by":[82,141],"visual-semantic":[83],"joint":[84],"embedding.":[85],"Then":[86],"both":[87,110],"branches":[88],"are":[89],"effectively":[90],"combined":[91],"with":[92],"soft-attention":[93],"mechanism":[94],"finally":[96],"fed":[97],"into":[98],"RNN":[100],"decoder":[101],"generate":[103],"captions.":[104],"With":[105],"our":[106],"SibNet":[107],"explicitly":[108],"capturing":[109],"information,":[114],"proposed":[116,136],"method":[117],"can":[118],"better":[119],"represent":[120],"rich":[122],"Extensive":[126],"experiments":[127],"on":[128],"YouTube2Text":[129],"MSR-VTT":[131],"datasets":[132],"validate":[133],"outperforms":[138],"existing":[139],"methods":[140],"large":[143],"margin":[144],"across":[145],"different":[146],"evaluation":[147],"metrics.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":24},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":11},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2018-10-26T00:00:00"}