{"id":"https://openalex.org/W4413147804","doi":"https://doi.org/10.1109/cvpr52734.2025.01877","title":"DVHGNN: Multi-Scale Dilated Vision HGNN for Efficient Vision Recognition","display_name":"DVHGNN: Multi-Scale Dilated Vision HGNN for Efficient Vision Recognition","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413147804","doi":"https://doi.org/10.1109/cvpr52734.2025.01877"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.01877","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01877","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5083280519","display_name":"Caoshuo Li","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Caoshuo Li","raw_affiliation_strings":["Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China,China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111099939","display_name":"Tanzhe Li","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tanzhe Li","raw_affiliation_strings":["Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China,China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101735199","display_name":"Xiaobin Hu","orcid":"https://orcid.org/0000-0002-5764-3096"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaobin Hu","raw_affiliation_strings":["Tencent Youtu Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027893969","display_name":"Donghao Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Donghao Luo","raw_affiliation_strings":["Tencent Youtu Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036950222","display_name":"Taisong Jin","orcid":"https://orcid.org/0000-0002-8873-1814"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Taisong Jin","raw_affiliation_strings":["Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China,China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20158","last_page":"20168"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9222999811172485,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9222999811172485,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9016000032424927,"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":0.7126178741455078},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.646418571472168},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6394909620285034},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5512925386428833},{"id":"https://openalex.org/keywords/machine-vision","display_name":"Machine vision","score":0.46689853072166443},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07662057876586914},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.0717628002166748}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7126178741455078},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.646418571472168},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6394909620285034},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5512925386428833},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.46689853072166443},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07662057876586914},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0717628002166748}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.01877","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01877","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320307904","display_name":"Oracle","ror":"https://ror.org/006c77m33"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336125","display_name":"National Science Fund for Distinguished Young Scholars","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Recently,":[0],"Vision":[1,17,59],"Graph":[2,18],"Neural":[3,19,61],"Network":[4,20,62],"(ViG)":[5],"has":[6],"gained":[7],"considerable":[8],"attention":[9],"in":[10],"computer":[11],"vision.":[12],"Despite":[13],"its":[14,31],"groundbreaking":[15],"innovation,":[16],"encounters":[21],"key":[22],"issues":[23],"including":[24],"the":[25,38,48,79,95,114,123,129,134],"quadratic":[26],"computational":[27],"complexity":[28],"caused":[29],"by":[30,153,157],"K-Nearest":[32],"Neighbor":[33],"(KNN)":[34],"graph":[35],"construction":[36],"and":[37,84,111,119,155],"limitation":[39],"of":[40,43,122,147],"pairwise":[41],"relations":[42],"normal":[44],"graphs.":[45],"To":[46],"address":[47],"aforementioned":[49],"challenges,":[50],"we":[51],"propose":[52],"a":[53,99],"novel":[54],"vision":[55,136],"architecture,":[56],"termed":[57],"Dilated":[58,85],"HyperGraph":[60,86],"(DVHGNN),":[63],"which":[64],"is":[65,104],"designed":[66],"to":[67,71,89,106],"leverage":[68],"multi-scale":[69,92],"hypergraph":[70,101,115],"efficiently":[72],"capture":[73,91],"high-order":[74],"correlations":[75],"among":[76,94],"objects.":[77],"Specifically,":[78],"proposed":[80,105,130],"method":[81],"tailors":[82],"Clustering":[83],"Construction":[87],"(DHGC)":[88],"adaptively":[90],"dependencies":[93],"data":[96],"samples.":[97],"Furthermore,":[98],"dynamic":[100],"convolution":[102],"mechanism":[103],"facilitate":[107],"adaptive":[108],"feature":[109],"exchange":[110],"fusion":[112],"at":[113],"level.":[116],"Extensive":[117],"qualitative":[118],"quantitative":[120],"evaluations":[121],"benchmark":[124],"image":[125],"datasets":[126],"demonstrate":[127],"that":[128],"DVHGNN":[131],"significantly":[132],"outperforms":[133],"state-of-the-art":[135],"backbones.":[137],"For":[138],"instance,":[139],"our":[140],"DVHGNN-S":[141],"achieves":[142],"an":[143],"impressive":[144],"top-1":[145],"accuracy":[146],"83.1%":[148],"on":[149],"ImageNet-1K,":[150],"surpassing":[151],"ViG-S":[152],"+1.0\u2191":[154],"ViHGNN-S":[156],"+0.6\u2191.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}