{"id":"https://openalex.org/W2608022654","doi":"https://doi.org/10.1109/icpr.2016.7900081","title":"Automatic video description generation via LSTM with joint two-stream encoding","display_name":"Automatic video description generation via LSTM with joint two-stream encoding","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2608022654","doi":"https://doi.org/10.1109/icpr.2016.7900081","mag":"2608022654"},"language":"en","primary_location":{"id":"doi:10.1109/icpr.2016.7900081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2016.7900081","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 23rd International Conference on Pattern Recognition (ICPR)","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/A5100337316","display_name":"Chenyang Zhang","orcid":"https://orcid.org/0000-0001-5282-3410"},"institutions":[{"id":"https://openalex.org/I125687163","display_name":"City College of New York","ror":"https://ror.org/00wmhkr98","country_code":"US","type":"education","lineage":["https://openalex.org/I125687163"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chenyang Zhang","raw_affiliation_strings":["Department of Electrical Engineering, The City College of New York, New York, New York"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, The City College of New York, New York, New York","institution_ids":["https://openalex.org/I125687163"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074244244","display_name":"Yingli Tian","orcid":"https://orcid.org/0000-0003-4458-360X"},"institutions":[{"id":"https://openalex.org/I125687163","display_name":"City College of New York","ror":"https://ror.org/00wmhkr98","country_code":"US","type":"education","lineage":["https://openalex.org/I125687163"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yingli Tian","raw_affiliation_strings":["Department of Electrical Engineering, The City College of New York, New York, New York"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, The City College of New York, New York, New York","institution_ids":["https://openalex.org/I125687163"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100337316"],"corresponding_institution_ids":["https://openalex.org/I125687163"],"apc_list":null,"apc_paid":null,"fwci":1.7332,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.90017271,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2924","last_page":"2929"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9983000159263611,"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":0.9922999739646912,"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":0.8871185779571533},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.7247428297996521},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.65128493309021},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6192511320114136},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.5780937075614929},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5727659463882446},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.5356568694114685},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.48745083808898926},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.45988476276397705},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.440030038356781},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42298218607902527},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3798556625843048},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.35604730248451233},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.20781159400939941},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08250963687896729}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8871185779571533},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.7247428297996521},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.65128493309021},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6192511320114136},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.5780937075614929},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5727659463882446},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.5356568694114685},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.48745083808898926},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.45988476276397705},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.440030038356781},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42298218607902527},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3798556625843048},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.35604730248451233},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.20781159400939941},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08250963687896729},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr.2016.7900081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2016.7900081","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 23rd International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1522734439","https://openalex.org/W1586939924","https://openalex.org/W1889081078","https://openalex.org/W1893116441","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1931795219","https://openalex.org/W1985944917","https://openalex.org/W1987835821","https://openalex.org/W2016053056","https://openalex.org/W2078238240","https://openalex.org/W2101105183","https://openalex.org/W2107878631","https://openalex.org/W2133459682","https://openalex.org/W2139501017","https://openalex.org/W2153579005","https://openalex.org/W2159243025","https://openalex.org/W2181691731","https://openalex.org/W2251353663","https://openalex.org/W2308045930","https://openalex.org/W2964241990","https://openalex.org/W4285719527","https://openalex.org/W4294170691","https://openalex.org/W4297813007","https://openalex.org/W6640257717","https://openalex.org/W6682691769","https://openalex.org/W6691419566","https://openalex.org/W6898505805","https://openalex.org/W7011438494"],"related_works":["https://openalex.org/W2368824897","https://openalex.org/W1508050556","https://openalex.org/W1910862367","https://openalex.org/W2379365082","https://openalex.org/W2370747590","https://openalex.org/W2030109976","https://openalex.org/W3031223029","https://openalex.org/W3167704465","https://openalex.org/W2369260257","https://openalex.org/W2389120450"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,25,46],"novel":[6],"two-stream":[7,27],"framework":[8,16],"based":[9],"on":[10,85,127],"combinational":[11,114],"deep":[12],"neural":[13,40],"networks.":[14],"The":[15,62],"is":[17,24,45,109,125],"mainly":[18],"composed":[19],"of":[20,64,81,102,116],"two":[21,142],"components:":[22],"one":[23,133],"parallel":[26],"encoding":[28,33,115],"component":[29],"which":[30,52],"learns":[31],"video":[32,57,130,165],"from":[34,112],"multiple":[35,117],"sources":[36],"using":[37],"3D":[38,82],"convolutional":[39,83],"networks":[41,84],"and":[42,74,90,141,149,154],"the":[43,54,79,100,107,161],"other":[44],"long-short-term-memory":[47],"(LSTM)-based":[48],"decoding":[49],"language":[50,121],"model":[51,67,96,124],"transfers":[53],"input":[55],"encoded":[56],"representations":[58],"to":[59,119],"text":[60],"descriptions.":[61],"merits":[63],"our":[65],"proposed":[66],"are:":[68],"1)":[69],"It":[70],"extracts":[71],"both":[72,86],"temporal":[73],"spatial":[75],"features":[76,118],"by":[77],"exploring":[78],"usage":[80],"raw":[87],"RGB":[88],"frames":[89],"motion":[91],"history":[92],"images.":[93],"2)":[94],"Our":[95,123],"can":[97],"dynamically":[98],"tune":[99],"weights":[101],"different":[103],"feature":[104],"channels":[105],"since":[106],"network":[108],"trained":[110],"end-to-end":[111],"learning":[113],"LSTM-based":[120],"model.":[122],"evaluated":[126],"three":[128],"public":[129],"description":[131,145],"datasets:":[132],"YouTube":[134],"clips":[135],"dataset":[136],"(Microsoft":[137],"Video":[138,151],"Description":[139],"Corpus)":[140],"large":[143],"movie":[144],"datasets":[146],"(MPII":[147],"Corpus":[148],"Montreal":[150],"Annotation":[152],"Dataset)":[153],"achieves":[155],"comparable":[156],"or":[157],"better":[158],"performance":[159],"than":[160],"state-of-the-art":[162],"approaches":[163],"in":[164],"caption":[166],"generation.":[167]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}