{"id":"https://openalex.org/W4394898123","doi":"https://doi.org/10.1145/3650400.3650477","title":"Research on Video Retrieval Technology based on Multimodal Fusion and Attention Mechanism","display_name":"Research on Video Retrieval Technology based on Multimodal Fusion and Attention Mechanism","publication_year":2023,"publication_date":"2023-10-20","ids":{"openalex":"https://openalex.org/W4394898123","doi":"https://doi.org/10.1145/3650400.3650477"},"language":"en","primary_location":{"id":"doi:10.1145/3650400.3650477","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3650400.3650477","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 7th International Conference on Electronic Information Technology and Computer Engineering","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/A5113180900","display_name":"T. Tai","orcid":"https://orcid.org/0009-0002-8856-2229"},"institutions":[{"id":"https://openalex.org/I1456306","display_name":"North China University of Technology","ror":"https://ror.org/01nky7652","country_code":"CN","type":"education","lineage":["https://openalex.org/I1456306"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tianyang Tai","raw_affiliation_strings":["College of Information, North China University of Technology, China"],"raw_orcid":"https://orcid.org/0009-0002-8856-2229","affiliations":[{"raw_affiliation_string":"College of Information, North China University of Technology, China","institution_ids":["https://openalex.org/I1456306"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033204139","display_name":"Zeng Fanfeng","orcid":null},"institutions":[{"id":"https://openalex.org/I1456306","display_name":"North China University of Technology","ror":"https://ror.org/01nky7652","country_code":"CN","type":"education","lineage":["https://openalex.org/I1456306"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fanfeng Zeng","raw_affiliation_strings":["College of Information, North China University of Technology, China"],"raw_orcid":"https://orcid.org/0009-0005-7923-6378","affiliations":[{"raw_affiliation_string":"College of Information, North China University of Technology, China","institution_ids":["https://openalex.org/I1456306"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5113180900"],"corresponding_institution_ids":["https://openalex.org/I1456306"],"apc_list":null,"apc_paid":null,"fwci":0.1177,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.46831197,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"470","last_page":"474"},"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":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"}},"topics":[{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/T11439","display_name":"Video Analysis and Summarization","score":0.9995999932289124,"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":0.9994000196456909,"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":0.8689114451408386},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6511109471321106},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.6208227872848511},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5443503260612488},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.4973774254322052},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4924510419368744},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.48362982273101807},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47551968693733215},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4509503245353699},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.44702979922294617},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.44678911566734314},{"id":"https://openalex.org/keywords/histogram","display_name":"Histogram","score":0.42882779240608215},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4233786463737488},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1938958764076233}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8689114451408386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6511109471321106},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6208227872848511},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5443503260612488},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4973774254322052},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4924510419368744},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.48362982273101807},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47551968693733215},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4509503245353699},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.44702979922294617},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.44678911566734314},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.42882779240608215},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4233786463737488},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1938958764076233},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3650400.3650477","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3650400.3650477","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 7th International Conference on Electronic Information Technology and Computer Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1974647172","https://openalex.org/W2563615176","https://openalex.org/W2963297060","https://openalex.org/W2963563276","https://openalex.org/W2996754048","https://openalex.org/W3014605045","https://openalex.org/W3159735885","https://openalex.org/W6756911974"],"related_works":["https://openalex.org/W2107628111","https://openalex.org/W2394004323","https://openalex.org/W2398764543","https://openalex.org/W2789802309","https://openalex.org/W2027335291","https://openalex.org/W4210328553","https://openalex.org/W1980417906","https://openalex.org/W2171903035","https://openalex.org/W2106598802","https://openalex.org/W2159024673"],"abstract_inverted_index":{"Feature":[0],"extraction":[1],"and":[2,20,32,53,71,85,95,118,138],"matching":[3],"are":[4],"crucial":[5],"in":[6,17,49,56],"video":[7,57,64,90,152],"retrieval":[8,65,133,153],"tasks.":[9],"However,":[10],"existing":[11],"algorithms":[12],"often":[13],"overlook":[14],"motion":[15,83],"features":[16,31,34,52,84,88,128],"action-related":[18],"videos":[19],"focus":[21],"only":[22],"on":[23,136],"global":[24,40],"static":[25,86],"features.":[26],"Distinguishing":[27],"between":[28,110],"key":[29],"action":[30],"background":[33],"is":[35],"challenging,":[36],"which":[37],"hinders":[38],"capturing":[39],"dependency":[41],"relationships":[42],"during":[43],"the":[44,77,93,111,142],"convolutional":[45],"process.":[46],"This":[47],"results":[48,135],"less":[50],"expressive":[51],"reduced":[54],"accuracy":[55],"retrieval.In":[58],"this":[59],"paper,":[60],"we":[61,103,121],"propose":[62],"a":[63,105,123],"model":[66,75],"that":[67],"combines":[68],"multimodal":[69],"fusion":[70],"attention":[72,108],"mechanism.":[73],"Our":[74],"employs":[76],"SlowFast":[78],"backbone":[79],"network,":[80],"extracting":[81],"skeleton":[82],"image":[87],"from":[89],"sequences":[91],"using":[92],"Slow":[94],"Fast":[96],"networks":[97],"respectively.":[98],"To":[99],"address":[100],"feature":[101],"fusion,":[102],"introduce":[104],"3D":[106],"residual":[107],"structure":[109],"two":[112],"branches.":[113],"By":[114],"incorporating":[115],"bilateral":[116],"connections":[117],"hash":[119,124],"encoding,":[120],"construct":[122],"layer":[125],"to":[126],"map":[127],"into":[129],"binary":[130],"codes,":[131],"improving":[132],"efficiency.Experimental":[134],"UCF101":[137],"HMDB51":[139],"datasets":[140],"validate":[141],"effectiveness":[143],"of":[144],"our":[145],"approach,":[146],"demonstrating":[147],"its":[148],"advantages":[149],"over":[150],"state-of-the-art":[151],"methods.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}