{"id":"https://openalex.org/W7203839299","doi":"https://doi.org/10.4018/979-8-2600-0965-9.ch013","title":"Transformer-Based Models for Video Recognition and Scene Understanding","display_name":"Transformer-Based Models for Video Recognition and Scene Understanding","publication_year":2026,"publication_date":"2026-08-20","ids":{"openalex":"https://openalex.org/W7203839299","doi":"https://doi.org/10.4018/979-8-2600-0965-9.ch013"},"language":"en","primary_location":{"id":"doi:10.4018/979-8-2600-0965-9.ch013","doi":"https://doi.org/10.4018/979-8-2600-0965-9.ch013","is_oa":false,"landing_page_url":"https://doi.org/10.4018/979-8-2600-0965-9.ch013","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/A5138946218","display_name":"Mavlanov Normumin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I55383850","display_name":"Tashkent State University of Economics","ror":"https://ror.org/029t9db68","country_code":"UZ","type":"education","lineage":["https://openalex.org/I55383850"]}],"countries":["UZ"],"is_corresponding":false,"raw_author_name":"Mavlanov Normumin","raw_affiliation_strings":["Department of Scientific Research and Innovation, Tashkent State University of Economics, Tashkent, Uzbekistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Scientific Research and Innovation, Tashkent State University of Economics, Tashkent, Uzbekistan","institution_ids":["https://openalex.org/I55383850"]}]},{"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":5,"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":"319","last_page":"342"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9794999957084656,"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":0.9794999957084656,"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":0.008299999870359898,"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":0.008299999870359898,"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-recognition","display_name":"video recognition","score":0.9670000076293945},{"id":"https://openalex.org/keywords/scene-understanding","display_name":"scene understanding","score":0.9980000257492065},{"id":"https://openalex.org/keywords/self-attention","display_name":"self-attention","score":0.968999981880188},{"id":"https://openalex.org/keywords/long-range-temporal-dependencies","display_name":"long-range temporal dependencies","score":0.7720000147819519},{"id":"https://openalex.org/keywords/human-action-recognition","display_name":"human action recognition","score":0.8899999856948853},{"id":"https://openalex.org/keywords/event-detection","display_name":"event detection","score":0.9860000014305115},{"id":"https://openalex.org/keywords/video-classification","display_name":"video classification","score":0.9810000061988831}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7512000203132629},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.603600025177002},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5666000247001648},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.5242000222206116},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.3871000111103058},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38420000672340393},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.3391999900341034},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.33000001311302185},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.3098999857902527},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C2778598663","wikidata":"https://www.wikidata.org/wiki/Q1407599","display_name":"Video content analysis","level":4,"score":0.26989999413490295},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.2635999917984009},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.4018/979-8-2600-0965-9.ch013","doi":"https://doi.org/10.4018/979-8-2600-0965-9.ch013","is_oa":false,"landing_page_url":"https://doi.org/10.4018/979-8-2600-0965-9.ch013","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W3147387781","https://openalex.org/W3190334976","https://openalex.org/W4210352519","https://openalex.org/W4221141684","https://openalex.org/W4293680532","https://openalex.org/W4296211656","https://openalex.org/W4297821406","https://openalex.org/W4312263092","https://openalex.org/W4382138923","https://openalex.org/W4385800770","https://openalex.org/W4386071559","https://openalex.org/W4389666826","https://openalex.org/W4402705238","https://openalex.org/W4402727022","https://openalex.org/W4402753403","https://openalex.org/W4404562731","https://openalex.org/W4406610856","https://openalex.org/W4407203437","https://openalex.org/W7118246782"],"related_works":["https://openalex.org/W4410951336","https://openalex.org/W7202132364","https://openalex.org/W4319777935","https://openalex.org/W4400094413","https://openalex.org/W4312658081","https://openalex.org/W4409152578","https://openalex.org/W7219962338","https://openalex.org/W4391456595","https://openalex.org/W4386452909","https://openalex.org/W7203834840"],"abstract_inverted_index":{"Transformer-based":[0,58],"models":[1],"have":[2],"significantly":[3],"advanced":[4],"video":[5,19,46,59],"recognition":[6],"and":[7,15,45,55,64],"scene":[8],"understanding":[9],"by":[10],"effectively":[11],"capturing":[12],"long-range":[13],"spatial":[14],"temporal":[16],"dependencies":[17],"in":[18,37],"data.":[20],"Unlike":[21],"traditional":[22],"convolutional":[23],"approaches,":[24],"Transformers":[25],"leverage":[26],"self-attention":[27],"mechanisms":[28],"to":[29],"model":[30],"complex":[31],"relationships":[32],"across":[33],"frames,":[34],"improving":[35],"performance":[36],"tasks":[38],"such":[39],"as":[40],"action":[41],"recognition,":[42],"event":[43],"detection,":[44],"classification.":[47],"This":[48],"work":[49],"reviews":[50],"the":[51],"principles,":[52],"architectures,":[53],"applications,":[54],"challenges":[56],"of":[57],"models,":[60],"highlighting":[61],"recent":[62],"developments":[63],"future":[65],"research":[66],"directions.":[67]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-08-21T00:00:00"}
