{"id":"https://openalex.org/W7204454134","doi":"https://doi.org/10.48550/arxiv.2608.25520","title":"Asymmetric Cross-Modal Fine-Grained Visual Categorization: ACF-Net and the BirdPro Benchmark","display_name":"Asymmetric Cross-Modal Fine-Grained Visual Categorization: ACF-Net and the BirdPro Benchmark","publication_year":2026,"publication_date":"2026-08-26","ids":{"openalex":"https://openalex.org/W7204454134","doi":"https://doi.org/10.48550/arxiv.2608.25520"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.25520","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.25520","pdf_url":"https://arxiv.org/pdf/2608.25520","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.25520","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5153405313","display_name":"Bohan Deng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4396570619","display_name":"Great Bay University","ror":"https://ror.org/01hdgge16","country_code":"CN","type":"education","lineage":["https://openalex.org/I4396570619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deng, Bohan","raw_affiliation_strings":["Great Bay University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Great Bay University","institution_ids":["https://openalex.org/I4396570619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140910909","display_name":"Shuo Ye","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4396570619","display_name":"Great Bay University","ror":"https://ror.org/01hdgge16","country_code":"CN","type":"education","lineage":["https://openalex.org/I4396570619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye, Shuo","raw_affiliation_strings":["Great Bay University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Great Bay University","institution_ids":["https://openalex.org/I4396570619"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5136548688","display_name":"Zitong Yu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4396570619","display_name":"Great Bay University","ror":"https://ror.org/01hdgge16","country_code":"CN","type":"education","lineage":["https://openalex.org/I4396570619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu, Zitong","raw_affiliation_strings":["Great Bay University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Great Bay University","institution_ids":["https://openalex.org/I4396570619"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4396570619"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9057999849319458,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9057999849319458,"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/T12032","display_name":"Multisensory perception and integration","score":0.032099999487400055,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0210999995470047,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/fine-grained-image-classification","display_name":"fine-grained image classification","score":0.9070000052452087},{"id":"https://openalex.org/keywords/optical-flow","display_name":"optical flow","score":0.6850000023841858},{"id":"https://openalex.org/keywords/uncertainty-aware-fusion","display_name":"uncertainty-aware fusion","score":0.878000020980835},{"id":"https://openalex.org/keywords/modality-reliability","display_name":"modality reliability","score":0.652999997138977},{"id":"https://openalex.org/keywords/bird-identification","display_name":"bird identification","score":0.8309999704360962}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7426000237464905},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7265999913215637},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6323999762535095},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.5990999937057495},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5521000027656555},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5318999886512756},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5121999979019165},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.43059998750686646},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42480000853538513},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41119998693466187},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3977000117301941},{"id":"https://openalex.org/C60115397","wikidata":"https://www.wikidata.org/wiki/Q5188732","display_name":"Crossmodal","level":4,"score":0.3874000012874603},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.3750999867916107},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3747999966144562},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.3596000075340271},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.3357999920845032},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3082999885082245},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2906999886035919},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.27959999442100525},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.25520","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.25520","pdf_url":"https://arxiv.org/pdf/2608.25520","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.25520","doi":"https://doi.org/10.48550/arxiv.2608.25520","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.25520","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.25520","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.25520","pdf_url":"https://arxiv.org/pdf/2608.25520","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204454134.pdf","grobid_xml":"https://content.openalex.org/works/W7204454134.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W2587372848","https://openalex.org/W3094502228","https://openalex.org/W4295901483","https://openalex.org/W4406457466","https://openalex.org/W6948418764","https://openalex.org/W7138251217","https://openalex.org/W7154342958"],"related_works":["https://openalex.org/W4304091737","https://openalex.org/W2789209438","https://openalex.org/W7155160852","https://openalex.org/W4415540663","https://openalex.org/W4312242460","https://openalex.org/W3020933450","https://openalex.org/W4388139335","https://openalex.org/W4410325927","https://openalex.org/W4312763854","https://openalex.org/W4390685975"],"abstract_inverted_index":{"Audio-visual":[0],"cross-modal":[1,22,52,138],"Fine-Grained":[2],"Visual":[3],"Categorization":[4],"(FGVC)":[5],"aims":[6],"to":[7,42,57,128],"identify":[8],"fine-grained":[9,79],"categories":[10],"by":[11,194],"jointly":[12],"leveraging":[13],"visual":[14,100],"and":[15,31,37,50,61,91,102,123,161,169,196,201],"auditory":[16],"information.":[17],"However,":[18],"FGVC":[19],"under":[20,118,158],"asymmetric":[21,77,137],"scenarios":[23],"has":[24],"received":[25],"limited":[26],"attention,":[27],"where":[28],"paired":[29],"video":[30],"audio":[32,167],"are":[33],"not":[34,39],"strictly":[35],"synchronized":[36],"may":[38],"even":[40],"correspond":[41],"the":[43,182,191,199],"same":[44],"individual":[45],"or":[46],"moment.":[47],"Such":[48],"weak":[49],"ambiguous":[51],"correspondence":[53],"poses":[54],"substantial":[55],"challenges":[56],"effective":[58],"representation":[59],"learning":[60],"modality":[62,116],"alignment.":[63],"To":[64,133],"address":[65],"these":[66],"issues,":[67],"we":[68,140],"propose":[69],"ACF-Net,":[70],"a":[71,144],"novel":[72],"optical":[73],"flow-guided":[74],"framework":[75],"for":[76],"audio-visual":[78,147],"learning.":[80],"ACF-Net":[81,180],"consists":[82],"of":[83],"two":[84],"key":[85],"modules:":[86],"Optical":[87],"Flow-Guided":[88],"Motion":[89],"(OFGM)":[90],"Asymmetric":[92],"CrossModal":[93],"Adaptive":[94],"Fusion":[95],"(ACAF).":[96],"OFGM":[97],"captures":[98],"motion-sensitive":[99],"cues":[101],"suppresses":[103],"irrelevant":[104],"background":[105],"interference,":[106],"thereby":[107],"enhancing":[108],"discriminative":[109],"dynamic":[110],"representations":[111],"in":[112,198],"videos.":[113],"ACAF":[114],"estimates":[115],"reliability":[117],"weakly":[119],"matched":[120],"audio-video":[121,156],"pairs":[122],"performs":[124],"uncertainty-aware":[125],"adaptive":[126],"fusion":[127],"improve":[129],"category-level":[130,155],"recognition":[131],"robustness.":[132],"support":[134],"research":[135],"on":[136],"FGVC,":[139],"further":[141],"construct":[142],"BirdPro,":[143],"new":[145],"bird-oriented":[146],"benchmark,":[148],"since":[149],"existing":[150],"datasets":[151],"often":[152],"lack":[153],"large-scale":[154],"associations":[157],"non-strict":[159],"temporal":[160],"instance":[162],"correspondence.":[163],"BirdPro":[164],"contains":[165],"1,919":[166],"recordings":[168],"11,965":[170],"videos":[171],"covering":[172],"194":[173],"bird":[174],"species.":[175],"Extensive":[176],"experiments":[177],"show":[178],"that":[179],"achieves":[181],"best":[183],"results":[184],"compared":[185],"with":[186],"representative":[187],"baseline":[188],"methods,":[189],"outperforming":[190],"strongest":[192],"baselines":[193],"2.97%":[195],"1.92%":[197],"fused":[200],"mismatched":[202],"settings,":[203],"respectively.":[204]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-28T00:00:00"}