{"id":"https://openalex.org/W4304091737","doi":"https://doi.org/10.1145/3503161.3548383","title":"MAVT-FG","display_name":"MAVT-FG","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304091737","doi":"https://doi.org/10.1145/3503161.3548383"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548383","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548383","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","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/A5101467238","display_name":"Xiaoyu Zhou","orcid":"https://orcid.org/0009-0000-4131-6093"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaoyu Zhou","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017316982","display_name":"Xiaotong Song","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaotong Song","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100448260","display_name":"Hao Wu","orcid":"https://orcid.org/0000-0003-2427-6004"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Wu","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059349096","display_name":"Jingran Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingran Zhang","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009074046","display_name":"Xing Xu","orcid":"https://orcid.org/0000-0001-5685-3123"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Xu","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101467238"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.1798,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.5092685,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3811","last_page":"3819"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9437000155448914,"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":0.9437000155448914,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9257000088691711,"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":0.5031883120536804}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5031883120536804}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3548383","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548383","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6728120685","display_name":null,"funder_award_id":"61976049, 62072080 and U20B2063","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1954152232","https://openalex.org/W2106414111","https://openalex.org/W2137917285","https://openalex.org/W2899607431","https://openalex.org/W2956335072","https://openalex.org/W2962850006","https://openalex.org/W2964227577","https://openalex.org/W2997426000","https://openalex.org/W2997700007","https://openalex.org/W2998619563","https://openalex.org/W3005971801","https://openalex.org/W3008809756","https://openalex.org/W3034865111","https://openalex.org/W3035333188","https://openalex.org/W3048939150","https://openalex.org/W3049148844","https://openalex.org/W3092721023","https://openalex.org/W3092837619","https://openalex.org/W3093038900","https://openalex.org/W3093174808","https://openalex.org/W3095721108","https://openalex.org/W3099638501","https://openalex.org/W3103717910","https://openalex.org/W3108870912","https://openalex.org/W3111984153","https://openalex.org/W3162322471","https://openalex.org/W3170972077","https://openalex.org/W3173388686","https://openalex.org/W3175300676","https://openalex.org/W3193137605","https://openalex.org/W3195146806","https://openalex.org/W3206008172","https://openalex.org/W3206019042","https://openalex.org/W3206734547","https://openalex.org/W3207395111","https://openalex.org/W3209058072","https://openalex.org/W3209279902","https://openalex.org/W4220733195"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2093578348","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W2096946506","https://openalex.org/W2766271392","https://openalex.org/W2350741829"],"abstract_inverted_index":{"Weakly-supervised":[0,55],"fine-grained":[1,28,36,112],"recognition":[2,29,37,113],"aims":[3],"to":[4,78,92],"detect":[5],"potential":[6],"differences":[7],"between":[8,84],"subcategories":[9,32],"at":[10,33,114],"a":[11,50,101],"more":[12,40],"detailed":[13],"scale":[14],"without":[15],"using":[16],"any":[17],"manual":[18],"annotations.":[19],"While":[20],"most":[21,95],"recent":[22],"works":[23],"focus":[24],"on":[25],"classical":[26],"image-based":[27],"that":[30,119],"recognizes":[31],"image-level,":[34],"video-based":[35],"is":[38],"much":[39],"challenging":[41],"and":[42,82,87,125],"specifically":[43],"needed.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48,99],"propose":[49],"Multimodal":[51],"Audio-Visual":[52,68,75,107],"Transformer":[53],"for":[54,70,74,109],"Fine-Grained":[56],"Recognition":[57],"(MAVT-FG)":[58],"model":[59],"which":[60],"incorporates":[61],"audio-visual":[62,110],"modalities.":[63],"Specifically,":[64],"MAVT-FG":[65],"consists":[66],"of":[67,106],"Dual-Encoder":[69],"feature":[71],"extraction,":[72],"Cross-Decoder":[73],"Fusion":[76],"(DAVF)":[77],"exploit":[79],"inherent":[80],"cues":[81],"correspondences":[83],"two":[85],"modalities,":[86],"Search-and-Select":[88],"Fine-grained":[89,104],"Branch":[90],"(SSFG)":[91],"capture":[93],"the":[94],"discriminative":[96],"regions.":[97],"Furthermore,":[98],"construct":[100],"new":[102],"benchmark:":[103],"Birds":[105],"(FGB-AV)":[108],"weakly-supervised":[111],"video-level.":[115],"Experimental":[116],"results":[117],"show":[118],"our":[120],"method":[121],"achieves":[122],"superior":[123],"performance":[124],"outperforms":[126],"other":[127],"state-of-the-art":[128],"methods.":[129]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2022-10-10T00:00:00"}