{"id":"https://openalex.org/W7203833945","doi":"https://doi.org/10.4018/979-8-2600-0965-9.ch003","title":"Deep Learning Architectures for Advanced Video Understanding","display_name":"Deep Learning Architectures for Advanced Video Understanding","publication_year":2026,"publication_date":"2026-08-20","ids":{"openalex":"https://openalex.org/W7203833945","doi":"https://doi.org/10.4018/979-8-2600-0965-9.ch003"},"language":"en","primary_location":{"id":"doi:10.4018/979-8-2600-0965-9.ch003","doi":"https://doi.org/10.4018/979-8-2600-0965-9.ch003","is_oa":false,"landing_page_url":"https://doi.org/10.4018/979-8-2600-0965-9.ch003","pdf_url":null,"source":{"id":"https://openalex.org/S4210180746","display_name":"Advances in computational intelligence and robotics book series","issn_l":"2327-042X","issn":["2327-042X","2327-0411"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":"https://openalex.org/P4310320424","host_organization_name":"IGI Global","host_organization_lineage":["https://openalex.org/P4310320424"],"host_organization_lineage_names":["IGI Global"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Computational Intelligence and Robotics","raw_type":"book-chapter"},"volume":{"id":"https://openalex.org/W7203828271","display_name":"Next-Generation Computer Vision Techniques for Video Analysis"},"type":"book-chapter","is_traditional":true,"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/A5130787960","display_name":"Ergashev Nuriddin Gayratovich","orcid":"https://orcid.org/0000-0002-8274-6193","observed_orcids":["https://orcid.org/0000-0002-8274-6193","https://orcid.org/0009-0003-8851-5374"]},"institutions":[{"id":"https://openalex.org/I4396570483","display_name":"Karshi State Technical University","ror":"https://ror.org/04xs15c78","country_code":"UZ","type":"education","lineage":["https://openalex.org/I4396570483"]}],"countries":["UZ"],"is_corresponding":false,"raw_author_name":"Ergashev Nuriddin","raw_affiliation_strings":["Department of Information Systems and Technologies, Karshi State Technical University, Uzbekistan"],"raw_orcid":"https://orcid.org/0009-0003-8851-5374","affiliations":[{"raw_affiliation_string":"Department of Information Systems and Technologies, Karshi State Technical University, Uzbekistan","institution_ids":["https://openalex.org/I4396570483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147505306","display_name":"Xurramov Ruslan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405254457","display_name":"Termez University of Economics and Service","ror":"https://ror.org/01tts0094","country_code":"UZ","type":"education","lineage":["https://openalex.org/I4405254457"]}],"countries":["UZ"],"is_corresponding":false,"raw_author_name":"Xurramov Ruslan","raw_affiliation_strings":["Department of Information Technology and Exact Sciences, Termez University of Economics and Service, Termez, Uzbekistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Technology and Exact Sciences, Termez University of Economics and Service, Termez, Uzbekistan","institution_ids":["https://openalex.org/I4405254457"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109493020","display_name":"Anorgul I. Ashirova","orcid":"https://orcid.org/0009-0006-7271-3634","observed_orcids":["https://orcid.org/0009-0006-7271-3634"]},"institutions":[{"id":"https://openalex.org/I4405255828","display_name":"Mamun University","ror":"https://ror.org/03fatne33","country_code":"UZ","type":"education","lineage":["https://openalex.org/I4405255828"]}],"countries":["UZ"],"is_corresponding":false,"raw_author_name":"Anorgul Ashirova","raw_affiliation_strings":["Department of General Professional Sciences, Mamun University, Khiva, Uzbekistan"],"raw_orcid":"https://orcid.org/0009-0006-7271-3634","affiliations":[{"raw_affiliation_string":"Department of General Professional Sciences, Mamun University, Khiva, Uzbekistan","institution_ids":["https://openalex.org/I4405255828"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130802596","display_name":"Khayrulla Urozboev","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405254406","display_name":"Alfraganus University","ror":"https://ror.org/01s7pfd33","country_code":"UZ","type":"education","lineage":["https://openalex.org/I4405254406"]}],"countries":["UZ"],"is_corresponding":false,"raw_author_name":"Khayrulla Urozboev","raw_affiliation_strings":["Department of International Scientific Journals and Ratings, Alfraganus University, Tashkent, Uzbekistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of International Scientific Journals and Ratings, Alfraganus University, Tashkent, Uzbekistan","institution_ids":["https://openalex.org/I4405254406"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"51","last_page":"76"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9750999808311462,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9750999808311462,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.011099999770522118,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.00930000003427267,"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/video-understanding","display_name":"video understanding","score":0.9549999833106995},{"id":"https://openalex.org/keywords/deep-learning-architectures","display_name":"deep learning architectures","score":0.9670000076293945},{"id":"https://openalex.org/keywords/convolutional-neural-networks","display_name":"convolutional neural networks","score":0.9789999723434448},{"id":"https://openalex.org/keywords/recurrent-neural-networks","display_name":"recurrent neural networks","score":1.0},{"id":"https://openalex.org/keywords/vision-transformer","display_name":"vision transformer","score":0.8330000042915344},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.9980000257492065},{"id":"https://openalex.org/keywords/human-action-recognition","display_name":"human action recognition","score":0.972000002861023},{"id":"https://openalex.org/keywords/object-tracking","display_name":"object tracking","score":0.9800000190734863},{"id":"https://openalex.org/keywords/event-detection","display_name":"event detection","score":0.9769999980926514},{"id":"https://openalex.org/keywords/video-captioning","display_name":"video captioning","score":1.0},{"id":"https://openalex.org/keywords/spatiotemporal-feature-extraction","display_name":"spatiotemporal feature extraction","score":0.9309999942779541}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8222000002861023},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.7605999708175659},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.660099983215332},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5957000255584717},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5447999835014343},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.44269999861717224},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.41370001435279846},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3978999853134155},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3840000033378601},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.38370001316070557},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.37540000677108765},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3698999881744385},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.35989999771118164},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.32010000944137573},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2971000075340271},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.28220000863075256},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2793999910354614},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2777999937534332},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.26019999384880066},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C22561748","wikidata":"https://www.wikidata.org/wiki/Q854954","display_name":"Videoconferencing","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.4018/979-8-2600-0965-9.ch003","doi":"https://doi.org/10.4018/979-8-2600-0965-9.ch003","is_oa":false,"landing_page_url":"https://doi.org/10.4018/979-8-2600-0965-9.ch003","pdf_url":null,"source":{"id":"https://openalex.org/S4210180746","display_name":"Advances in computational intelligence and robotics book series","issn_l":"2327-042X","issn":["2327-042X","2327-0411"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":"https://openalex.org/P4310320424","host_organization_name":"IGI Global","host_organization_lineage":["https://openalex.org/P4310320424"],"host_organization_lineage_names":["IGI Global"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Computational Intelligence and Robotics","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2526417872","https://openalex.org/W2773325192","https://openalex.org/W2792220137","https://openalex.org/W2990685265","https://openalex.org/W3001186970","https://openalex.org/W3113370935","https://openalex.org/W3203313189","https://openalex.org/W3206471682","https://openalex.org/W3207662977","https://openalex.org/W4211011341","https://openalex.org/W4319319086","https://openalex.org/W4364376005","https://openalex.org/W4401906098"],"related_works":["https://openalex.org/W4401226286","https://openalex.org/W6893305655","https://openalex.org/W4407424292","https://openalex.org/W4401226202","https://openalex.org/W7203834840","https://openalex.org/W7203826430","https://openalex.org/W4401226082","https://openalex.org/W7222201485","https://openalex.org/W7203825070","https://openalex.org/W4401226283"],"abstract_inverted_index":{"Advanced":[0],"video":[1,42,54,74],"understanding":[2],"has":[3],"become":[4],"a":[5],"key":[6],"research":[7],"area":[8],"in":[9,68],"computer":[10],"vision,":[11],"driven":[12],"by":[13],"the":[14,39],"rapid":[15],"growth":[16],"of":[17,41,61],"multimedia":[18],"data.":[19],"Deep":[20],"learning":[21],"architectures,":[22],"including":[23],"convolutional":[24],"neural":[25,29],"networks":[26,30],"(CNNs),":[27],"recurrent":[28],"(RNNs),":[31],"transformers,":[32],"and":[33,53,64],"vision-language":[34],"models,":[35],"have":[36],"significantly":[37],"improved":[38],"accuracy":[40],"analysis":[43],"tasks":[44],"such":[45],"as":[46],"action":[47],"recognition,":[48],"object":[49],"tracking,":[50],"event":[51],"detection,":[52],"captioning.":[55],"This":[56],"study":[57],"provides":[58],"an":[59],"overview":[60],"these":[62],"architectures":[63],"highlights":[65],"their":[66],"effectiveness":[67],"extracting":[69],"spatial-temporal":[70],"features":[71],"for":[72],"intelligent":[73],"understanding.":[75]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-08-21T00:00:00"}