{"id":"https://openalex.org/W7129067285","doi":"https://doi.org/10.3103/s0146411625701354","title":"A Scene-Based Multimodal Video Similarity Detection Algorithm","display_name":"A Scene-Based Multimodal Video Similarity Detection Algorithm","publication_year":2025,"publication_date":"2025-12-01","ids":{"openalex":"https://openalex.org/W7129067285","doi":"https://doi.org/10.3103/s0146411625701354"},"language":"en","primary_location":{"id":"doi:10.3103/s0146411625701354","is_oa":false,"landing_page_url":"https://doi.org/10.3103/s0146411625701354","pdf_url":null,"source":{"id":"https://openalex.org/S17203304","display_name":"Automatic Control and Computer Sciences","issn_l":"0146-4116","issn":["0146-4116","1558-108X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320267","host_organization_name":"Pleiades Publishing","host_organization_lineage":["https://openalex.org/P4310320267","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Pleiades Publishing","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Automatic Control and Computer Sciences","raw_type":"journal-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/A5000882722","display_name":"X. Z. Li","orcid":"https://orcid.org/0009-0009-1594-6361"},"institutions":[{"id":"https://openalex.org/I2801618472","display_name":"PLA Rocket Force University of Engineering","ror":"https://ror.org/00gg5zj35","country_code":"CN","type":"education","lineage":["https://openalex.org/I2801618472"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xue\u00a0Li","raw_affiliation_strings":["Rocket Force University of Engineering, Xi\u2019an, China"],"affiliations":[{"raw_affiliation_string":"Rocket Force University of Engineering, Xi\u2019an, China","institution_ids":["https://openalex.org/I2801618472"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5000882722"],"corresponding_institution_ids":["https://openalex.org/I2801618472"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.73841886,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"59","issue":"6","first_page":"832","last_page":"845"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.5667999982833862,"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/T11439","display_name":"Video Analysis and Summarization","score":0.5667999982833862,"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":0.18320000171661377,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.03929999843239784,"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/similarity","display_name":"Similarity (geometry)","score":0.680899977684021},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5342000126838684},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5235000252723694},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.4830000102519989},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.47269999980926514},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4237000048160553},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.4154999852180481},{"id":"https://openalex.org/keywords/mode","display_name":"Mode (computer interface)","score":0.4115000069141388},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.37779998779296875}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8748000264167786},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.680899977684021},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6743000149726868},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5342000126838684},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5235000252723694},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.4830000102519989},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.47269999980926514},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4237000048160553},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.4154999852180481},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.4115000069141388},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3781000077724457},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.37779998779296875},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.36320000886917114},{"id":"https://openalex.org/C143271835","wikidata":"https://www.wikidata.org/wiki/Q254515","display_name":"Similitude","level":2,"score":0.32429999113082886},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32019999623298645},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C2779769447","wikidata":"https://www.wikidata.org/wiki/Q3813641","display_name":"Foreground detection","level":4,"score":0.28859999775886536},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2831000089645386},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2578999996185303},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.2563999891281128}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3103/s0146411625701354","is_oa":false,"landing_page_url":"https://doi.org/10.3103/s0146411625701354","pdf_url":null,"source":{"id":"https://openalex.org/S17203304","display_name":"Automatic Control and Computer Sciences","issn_l":"0146-4116","issn":["0146-4116","1558-108X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320267","host_organization_name":"Pleiades Publishing","host_organization_lineage":["https://openalex.org/P4310320267","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Pleiades Publishing","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Automatic Control and Computer Sciences","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5981130003929138,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1981485102","https://openalex.org/W1983364832","https://openalex.org/W2035364148","https://openalex.org/W2097117768","https://openalex.org/W2129795158","https://openalex.org/W2162659160","https://openalex.org/W2618530766","https://openalex.org/W2799050036","https://openalex.org/W2887928923","https://openalex.org/W2921310091","https://openalex.org/W2962835968","https://openalex.org/W2963524571","https://openalex.org/W2990730805","https://openalex.org/W3096832794","https://openalex.org/W3172613897","https://openalex.org/W3180463990","https://openalex.org/W3207015681","https://openalex.org/W3208223014","https://openalex.org/W4200162459","https://openalex.org/W4225567241","https://openalex.org/W4312442470","https://openalex.org/W4313396824","https://openalex.org/W4320495784","https://openalex.org/W4386057769","https://openalex.org/W4386596970","https://openalex.org/W4387766053","https://openalex.org/W4391594693","https://openalex.org/W4392946626"],"related_works":[],"abstract_inverted_index":{"Storing":[0],"similar":[1],"videos":[2],"will":[3],"seriously":[4],"waste":[5],"the":[6,23,33,51,76,82,97,100,105,115,139,147,158,170,175,184,194],"storage":[7],"resources.":[8],"However,":[9],"many":[10],"methods":[11],"have":[12],"low":[13],"detection":[14,40],"accuracy":[15,190],"and":[16,21,63,107,129,165,180],"efficiency,":[17],"which":[18,48],"cannot":[19],"extract":[20,75],"analyze":[22],"dynamic":[24,116],"features":[25,53,79,92,110],"of":[26,54,119,189],"specific":[27,121],"local":[28,120],"targets":[29],"effectively.":[30,145],"To":[31],"solve":[32],"above":[34],"problems,":[35],"a":[36,67,85,124,130],"multimodal":[37],"long":[38],"video":[39,154],"algorithm":[41,177],"based":[42,80],"on":[43,81,163],"multiscenario":[44],"learning":[45],"is":[46,72,89,135,150],"proposed,":[47],"effectively":[49],"integrates":[50],"multimode":[52],"four":[55,77],"modes,":[56],"i.e.,":[57],"text":[58],"flow,":[59,62],"keyframes,":[60],"optical":[61,108],"audio":[64],"flow.":[65],"Firstly,":[66],"coevolutionary":[68],"neural":[69],"network":[70],"model":[71,134],"constructed":[73],"to":[74,103,137,152,156,193],"pattern":[78],"scene":[83],"as":[84],"unit.":[86],"Our":[87],"innovation":[88],"that":[90,169],"keyframe":[91],"are":[93,111,178],"obtained":[94,112,173],"by":[95,113,174],"selecting":[96],"frames":[98],"with":[99],"lowest":[101],"similarity":[102,149,159],"aggregate":[104],"features,":[106],"flow":[109],"extracting":[114],"running":[117],"mode":[118],"targets.":[122],"Then,":[123],"position":[125],"cross":[126,131],"attention":[127],"module":[128],"modal":[132,143],"fusion":[133],"designed":[136],"capture":[138],"correlation":[140],"between":[141],"different":[142],"data":[144],"Finally,":[146],"chamfer":[148],"applied":[151],"various":[153],"scenes":[155],"calculate":[157],"matrix.":[160],"Experiments":[161],"conducted":[162],"CC_WEB_VIDEO":[164],"VCDB":[166],"datasets":[167],"reveal":[168],"mAP":[171],"values":[172],"present":[176],"98.5":[179],"94.9%":[181],"respectively,":[182],"demonstrating":[183],"best":[185],"performance":[186],"in":[187,191],"terms":[188],"comparison":[192],"baseline":[195],"methods.":[196]},"counts_by_year":[],"updated_date":"2026-02-18T06:20:13.636215","created_date":"2026-02-17T00:00:00"}