{"id":"https://openalex.org/W4398196974","doi":"https://doi.org/10.1145/3638682.3638691","title":"A Video Classification Algorithm Based on Visual-Audio Cross-Attention","display_name":"A Video Classification Algorithm Based on Visual-Audio Cross-Attention","publication_year":2023,"publication_date":"2023-11-24","ids":{"openalex":"https://openalex.org/W4398196974","doi":"https://doi.org/10.1145/3638682.3638691"},"language":"en","primary_location":{"id":"doi:10.1145/3638682.3638691","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3638682.3638691","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 5th International Conference on Video, Signal and Image Processing","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/A5066574717","display_name":"Xuchao Gong","orcid":"https://orcid.org/0000-0002-9783-8410"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuchao Gong","raw_affiliation_strings":["Information Technology Service Center of Shengli Petroleum Management Bureau, China"],"raw_orcid":"https://orcid.org/0000-0002-9783-8410","affiliations":[{"raw_affiliation_string":"Information Technology Service Center of Shengli Petroleum Management Bureau, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114166561","display_name":"Yahui Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yahui Wu","raw_affiliation_strings":["Sense Time group Inc., China"],"raw_orcid":"https://orcid.org/0009-0005-2555-3458","affiliations":[{"raw_affiliation_string":"Sense Time group Inc., China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhen Wang","orcid":"https://orcid.org/0009-0005-5376-8325"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhen Wang","raw_affiliation_strings":["Information Technology Service Center of Shengli Petroleum Management Bureau, China"],"raw_orcid":"https://orcid.org/0009-0005-5376-8325","affiliations":[{"raw_affiliation_string":"Information Technology Service Center of Shengli Petroleum Management Bureau, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058880760","display_name":"Hongjie Duan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongjie Duan","raw_affiliation_strings":["Information Technology Service Center of Shengli Petroleum Management Bureau, China"],"raw_orcid":"https://orcid.org/0009-0003-2220-5808","affiliations":[{"raw_affiliation_string":"Information Technology Service Center of Shengli Petroleum Management Bureau, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1123,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.4629246,"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":"57","last_page":"63"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9972000122070312,"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/T11309","display_name":"Music and Audio Processing","score":0.9944000244140625,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8490206003189087},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6068736910820007},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5757338404655457},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.562046468257904},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47901052236557007},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45533695816993713},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45419979095458984},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4500664472579956},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.20776471495628357}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8490206003189087},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6068736910820007},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5757338404655457},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.562046468257904},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47901052236557007},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45533695816993713},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45419979095458984},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4500664472579956},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.20776471495628357},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3638682.3638691","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3638682.3638691","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 5th International Conference on Video, Signal and Image Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1981276685","https://openalex.org/W2526468814","https://openalex.org/W4212807739","https://openalex.org/W4214612132","https://openalex.org/W4234552385","https://openalex.org/W4236965008","https://openalex.org/W4301409532","https://openalex.org/W6600279560","https://openalex.org/W6600351811","https://openalex.org/W6702248584"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731","https://openalex.org/W2393726419"],"abstract_inverted_index":{"Given":[0],"that":[1],"video":[2,22,115],"content":[3],"expression":[4],"involves":[5],"the":[6,45,52,61,70,86,96,102,109],"combination":[7],"of":[8],"auditory":[9],"and":[10,17,69,112],"visual.":[11],"How":[12],"to":[13,20,65,75],"effectively":[14],"combine":[15],"visual":[16],"audio":[18],"features":[19],"guide":[21],"classification":[23,67,116],"is":[24,55,73,93],"still":[25],"an":[26],"exploratory":[27],"problem.":[28],"In":[29,95],"this":[30],"paper,":[31],"we":[32],"propose":[33],"a":[34,89],"Visual-Audio":[35,90],"Cross-Attention":[36,91],"Video":[37],"Classification":[38],"Algorithm":[39],"(VACA-VCA).":[40],"The":[41],"method":[42,104],"mainly":[43],"includes":[44],"following":[46],"aspects.":[47],"1)":[48],"Tnspired":[49],"by":[50],"ViLT,":[51],"model":[53],"calculation":[54],"focused":[56],"on":[57,99],"modality":[58],"interaction":[59],"at":[60],"feature":[62],"fusion":[63],"level":[64],"improve":[66,85],"performance,":[68,88],"dual-stream":[71],"modeling":[72,78],"changed":[74],"concatenated":[76],"single-stream":[77],"without":[79],"introducing":[80],"additional":[81],"parameters.":[82],"2)":[83],"To":[84],"generalization":[87],"mechanism":[92],"proposed.":[94],"experimental":[97],"results":[98],"public":[100],"datasets,":[101],"proposed":[103],"achieved":[105],"significant":[106],"improvements":[107],"in":[108],"Kinetics":[110,113],"400":[111],"600":[114],"datasets.":[117]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}