{"id":"https://openalex.org/W2607816824","doi":"https://doi.org/10.1109/icpr.2016.7900131","title":"DLSTM approach to video modeling with hashing for large-scale video retrieval","display_name":"DLSTM approach to video modeling with hashing for large-scale video retrieval","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2607816824","doi":"https://doi.org/10.1109/icpr.2016.7900131","mag":"2607816824"},"language":"en","primary_location":{"id":"doi:10.1109/icpr.2016.7900131","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2016.7900131","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://stars.library.ucf.edu/scopus2015/4387","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022382399","display_name":"Naifan Zhuang","orcid":"https://orcid.org/0000-0002-4699-9329"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Naifan Zhuang","raw_affiliation_strings":["Department of Computer Science, University of Central Florida, Orlando, Florida"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Central Florida, Orlando, Florida","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100382930","display_name":"Jun Ye","orcid":"https://orcid.org/0000-0003-2841-6529"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jun Ye","raw_affiliation_strings":["Department of Computer Science, University of Central Florida, Orlando, Florida"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Central Florida, Orlando, Florida","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110083332","display_name":"Kien A. Hua","orcid":null},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kien A. Hua","raw_affiliation_strings":["Department of Computer Science, University of Central Florida, Orlando, Florida"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Central Florida, Orlando, Florida","institution_ids":["https://openalex.org/I106165777"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I106165777"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3222","last_page":"3227"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/T11439","display_name":"Video Analysis and Summarization","score":0.9997000098228455,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9993000030517578,"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":0.7448818683624268},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6302233934402466},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5461025834083557},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.5456193685531616},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.5285882949829102},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.5161281824111938},{"id":"https://openalex.org/keywords/hamming-space","display_name":"Hamming space","score":0.5076099634170532},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.4889315664768219},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.48216718435287476},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4638606905937195},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.4385179579257965},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.424185574054718},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.4226214587688446},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.4210614562034607},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4062752425670624},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.2829863727092743},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16693904995918274},{"id":"https://openalex.org/keywords/hamming-code","display_name":"Hamming code","score":0.10979035496711731},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09632205963134766}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7448818683624268},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6302233934402466},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5461025834083557},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.5456193685531616},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.5285882949829102},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.5161281824111938},{"id":"https://openalex.org/C2779494224","wikidata":"https://www.wikidata.org/wiki/Q5645799","display_name":"Hamming space","level":5,"score":0.5076099634170532},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.4889315664768219},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.48216718435287476},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4638606905937195},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.4385179579257965},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.424185574054718},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4226214587688446},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.4210614562034607},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4062752425670624},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.2829863727092743},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16693904995918274},{"id":"https://openalex.org/C73150493","wikidata":"https://www.wikidata.org/wiki/Q853922","display_name":"Hamming code","level":4,"score":0.10979035496711731},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09632205963134766},{"id":"https://openalex.org/C157125643","wikidata":"https://www.wikidata.org/wiki/Q884707","display_name":"Block code","level":3,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icpr.2016.7900131","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2016.7900131","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"},{"id":"pmh:oai:stars.library.ucf.edu:scopus2015-5386","is_oa":true,"landing_page_url":"https://stars.library.ucf.edu/scopus2015/4387","pdf_url":null,"source":{"id":"https://openalex.org/S4210172555","display_name":"Journal of International Crisis and Risk Communication Research","issn_l":"2576-0017","issn":["2576-0017","2576-0025"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scopus Export 2015-2019","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:stars.library.ucf.edu:scopus2015-5386","is_oa":true,"landing_page_url":"https://stars.library.ucf.edu/scopus2015/4387","pdf_url":null,"source":{"id":"https://openalex.org/S4210172555","display_name":"Journal of International Crisis and Risk Communication Research","issn_l":"2576-0017","issn":["2576-0017","2576-0025"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scopus Export 2015-2019","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306101","display_name":"National Aeronautics and Space Administration","ror":"https://ror.org/027ka1x80"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W846669277","https://openalex.org/W1910300841","https://openalex.org/W1992371516","https://openalex.org/W2014550941","https://openalex.org/W2043774165","https://openalex.org/W2064675550","https://openalex.org/W2074668987","https://openalex.org/W2084363474","https://openalex.org/W2085735683","https://openalex.org/W2108523493","https://openalex.org/W2110990863","https://openalex.org/W2117539524","https://openalex.org/W2130942839","https://openalex.org/W2143267104","https://openalex.org/W2143612262","https://openalex.org/W2144530948","https://openalex.org/W2147717514","https://openalex.org/W2150111138","https://openalex.org/W2155893237","https://openalex.org/W6679436768"],"related_works":["https://openalex.org/W2036753599","https://openalex.org/W2104807620","https://openalex.org/W2772529866","https://openalex.org/W4212842756","https://openalex.org/W1993530675","https://openalex.org/W1862594650","https://openalex.org/W2979980909","https://openalex.org/W2949049896","https://openalex.org/W2089632823","https://openalex.org/W2977099505"],"abstract_inverted_index":{"Although":[0],"Query-by-Example":[1],"techniques":[2],"based":[3,240],"on":[4,111,241],"Euclidean":[5],"distance":[6],"in":[7,51,157],"a":[8,73,124,208,259],"multidimensional":[9],"feature":[10,75,82,126,165,212],"space":[11],"have":[12],"proved":[13],"to":[14,26,37,88,118,151,159],"be":[15,23,34],"effective":[16],"for":[17,77],"image":[18],"databases,":[19,147],"this":[20,100,112,173],"approach":[21,101],"cannot":[22],"effectively":[24],"applied":[25],"video":[27,43,67,107,116,121,131,146,178,182,196,253],"since":[28],"the":[29,38,66,103,136,140,153,161,164,215,221,251],"number":[30,154],"of":[31,42,99,106,139,155,163,217,220,224],"dimensions":[32],"would":[33],"massive":[35],"due":[36],"richness":[39],"and":[40,59,71,206,247],"complexity":[41],"data.":[44,108],"The":[45,80],"above":[46],"issue":[47],"has":[48],"been":[49],"addressed":[50],"two":[52,242],"recent":[53],"solutions,":[54],"namely":[55],"Deterministic":[56],"Quantization":[57,62],"(DQ)":[58],"Dynamic":[60],"Temporal":[61],"(DTQ).":[63],"DQ":[64],"divides":[65],"into":[68,233],"equal":[69],"segments":[70,132,156],"extracts":[72],"visual":[74],"vector":[76],"each":[78],"segment.":[79],"bag-of-word":[81],"is":[83,102,149,185],"then":[84],"encoded":[85],"by":[86,113,174,230,258],"hashing":[87,231],"facilitate":[89],"approximate":[90],"nearest":[91],"neighbor":[92],"search":[93],"using":[94,114,175,197],"Hamming":[95],"distance.":[96],"One":[97],"weakness":[98],"deterministic":[104],"segmentation":[105,117,184],"DTQ":[109,257],"improves":[110],"dynamic":[115],"obtain":[119],"varied-length":[120],"segments.":[122],"As":[123],"result,":[125],"vectors":[127],"extracted":[128],"from":[129],"these":[130,225],"can":[133],"better":[134,190],"capture":[135],"semantic":[137],"content":[138],"video.":[141],"To":[142],"support":[143],"very":[144],"large":[145],"it":[148],"desirable":[150],"minimize":[152],"order":[158],"keep":[160],"size":[162],"representation":[166,213],"as":[167,169],"small":[168],"possible.":[170],"We":[171],"achieve":[172],"only":[176],"one":[177],"segment":[179],"(i.e.,":[180],"no":[181],"data":[183,244],"even":[186,189],"necessary)":[187],"with":[188,214],"retrieval":[191],"performance.":[192],"Our":[193],"scheme":[194],"models":[195],"differential":[198],"long":[199],"short-term":[200],"memory":[201],"(DLSTM)":[202],"recurrent":[203],"neural":[204],"networks":[205],"obtains":[207],"highly":[209],"compact":[210],"fixed-size":[211],"output":[216],"hidden":[218],"states":[219],"DLSTM.":[222],"Each":[223],"features":[226],"are":[227],"further":[228],"compressed":[229],"them":[232],"binary":[234],"bits":[235],"via":[236],"quantization.":[237],"Experimental":[238],"results":[239],"public":[243],"sets,":[245],"UCF101":[246],"MSRActionPairs,":[248],"indicate":[249],"that":[250],"proposed":[252],"modeling":[254],"technique":[255],"outperforms":[256],"significant":[260],"margin.":[261]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}