{"id":"https://openalex.org/W4385960790","doi":"https://doi.org/10.1145/3581783.3612122","title":"PVG: Progressive Vision Graph for Vision Recognition","display_name":"PVG: Progressive Vision Graph for Vision Recognition","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4385960790","doi":"https://doi.org/10.1145/3581783.3612122"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612122","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612122","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2308.00574","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025002931","display_name":"Jiafu Wu","orcid":"https://orcid.org/0000-0002-1036-5076"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"JiaFu Wu","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1036-5076","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100402508","display_name":"Jian Li","orcid":"https://orcid.org/0000-0002-0242-6481"},"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":"Jian Li","raw_affiliation_strings":["Tencent Youtu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-0242-6481","affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021861529","display_name":"Jiangning Zhang","orcid":"https://orcid.org/0000-0001-8891-6766"},"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":"Jiangning Zhang","raw_affiliation_strings":["Tencent Youtu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8891-6766","affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004670511","display_name":"Boshen Zhang","orcid":"https://orcid.org/0000-0001-9204-5676"},"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":"Boshen Zhang","raw_affiliation_strings":["Tencent Youtu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9204-5676","affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057267422","display_name":"Mingmin Chi","orcid":"https://orcid.org/0000-0003-2650-4146"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingmin Chi","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-2650-4146","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028731909","display_name":"Yabiao Wang","orcid":"https://orcid.org/0000-0002-6592-8411"},"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":"Yabiao Wang","raw_affiliation_strings":["Tencent Youtu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-6592-8411","affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023834700","display_name":"Chengjie Wang","orcid":"https://orcid.org/0000-0003-4216-8090"},"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":"Chengjie Wang","raw_affiliation_strings":["Tencent Youtu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-4216-8090","affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"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":true,"cited_by_count":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2477","last_page":"2486"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","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/T10036","display_name":"Advanced Neural Network Applications","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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9991000294685364,"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":0.998199999332428,"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":0.7006785869598389},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.6818581819534302},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5601003766059875},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.5015463829040527},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4802113473415375},{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.4271640479564667},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3881445825099945},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.33958375453948975},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.30947577953338623}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7006785869598389},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6818581819534302},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5601003766059875},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.5015463829040527},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4802113473415375},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.4271640479564667},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3881445825099945},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33958375453948975},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.30947577953338623}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3581783.3612122","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612122","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2308.00574","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.00574","pdf_url":"https://arxiv.org/pdf/2308.00574","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2308.00574","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.00574","pdf_url":"https://arxiv.org/pdf/2308.00574","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":[{"display_name":"Industry, innovation and infrastructure","score":0.44999998807907104,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G2728175297","display_name":null,"funder_award_id":"62171139","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385960790.pdf","grobid_xml":"https://content.openalex.org/works/W4385960790.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W2097117768","https://openalex.org/W2108598243","https://openalex.org/W2112796928","https://openalex.org/W2194775991","https://openalex.org/W2393319904","https://openalex.org/W2558460151","https://openalex.org/W2618530766","https://openalex.org/W2932399282","https://openalex.org/W2954628187","https://openalex.org/W2962766044","https://openalex.org/W2963017945","https://openalex.org/W2963084622","https://openalex.org/W2964051675","https://openalex.org/W2979300990","https://openalex.org/W2990045899","https://openalex.org/W2997136715","https://openalex.org/W3003446182","https://openalex.org/W3034345703","https://openalex.org/W3034637015","https://openalex.org/W3034749803","https://openalex.org/W3109196706","https://openalex.org/W3121523901","https://openalex.org/W3130602232","https://openalex.org/W3131500599","https://openalex.org/W3138516171","https://openalex.org/W3167292079","https://openalex.org/W3171087525","https://openalex.org/W3175227919","https://openalex.org/W3183605589","https://openalex.org/W3190624940","https://openalex.org/W3205953910","https://openalex.org/W3211555016","https://openalex.org/W4214493665","https://openalex.org/W4312349930","https://openalex.org/W4312443924","https://openalex.org/W4312575870","https://openalex.org/W4312775058","https://openalex.org/W4313007769","https://openalex.org/W6600175266","https://openalex.org/W6600755281"],"related_works":["https://openalex.org/W1670332068","https://openalex.org/W2095618524","https://openalex.org/W2735770592","https://openalex.org/W1971024059","https://openalex.org/W1502062143","https://openalex.org/W4224236531","https://openalex.org/W2953234277","https://openalex.org/W4291993329","https://openalex.org/W4226363941","https://openalex.org/W3015684221"],"abstract_inverted_index":{"Convolution-based":[0],"and":[1,47,99,115,122,210],"Transformer-based":[2],"vision":[3,67],"backbone":[4],"networks":[5],"process":[6],"images":[7],"into":[8],"the":[9,50,55,92,95,101,107,147,155,163,186,192],"grid":[10],"or":[11],"sequence":[12],"structures,":[13],"respectively,":[14],"which":[15],"are":[16],"inflexible":[17],"for":[18,29,66,153],"capturing":[19],"irregular":[20],"objects.":[21],"Though":[22],"Vision":[23,62],"GNN":[24],"(ViG)":[25],"adopts":[26],"graph-level":[27],"features":[28],"complex":[30],"images,":[31],"it":[32],"has":[33,198],"some":[34],"issues,":[35],"such":[36],"as":[37,106],"inaccurate":[38],"neighbor":[39,129],"node":[40,43],"selection,":[41],"expensive":[42],"information":[44,113,140,152],"aggregation":[45,114],"calculation,":[46],"over-smoothing":[48],"in":[49,141],"deep":[51],"layers.":[52],"To":[53],"address":[54],"above":[56],"problems,":[57],"we":[58],"propose":[59],"a":[60,142],"Progressive":[61],"Graph":[63,82,132],"(PVG)":[64],"architecture":[65],"recognition":[68],"task.":[69],"Compared":[70],"with":[71,185],"previous":[72],"works,":[73],"PVG":[74,166],"contains":[75],"three":[76],"main":[77],"components:":[78],"1)":[79],"Progressively":[80],"Separated":[81],"Construction":[83],"(PSGC)":[84],"to":[85,126,137,145],"introduce":[86],"second-order":[87],"similarity":[88],"by":[89,118,183,189],"gradually":[90],"increasing":[91],"channel":[93,102],"of":[94,103,149,165],"global":[96],"graph":[97],"branch":[98,105],"decreasing":[100],"local":[104],"layer":[108],"deepens;":[109],"2)":[110],"Neighbor":[111],"nodes":[112],"update":[116],"module":[117],"using":[119],"Max":[120],"pooling":[121],"mathematical":[123],"Expectation":[124],"(MaxE)":[125],"aggregate":[127],"rich":[128],"information;":[130],"3)":[131],"error":[133],"Linear":[134],"Unit":[135],"(GraphLU)":[136],"enhance":[138],"low-value":[139],"relaxed":[143],"form":[144],"reduce":[146],"compression":[148],"image":[150],"detail":[151],"alleviating":[154],"over-smoothing.":[156],"Extensive":[157],"experiments":[158],"on":[159,177,217],"mainstream":[160],"benchmarks":[161],"demonstrate":[162],"superiority":[164],"over":[167],"state-of-the-art":[168],"methods,":[169],"e.g.,":[170],"our":[171,204],"PVG-S":[172,205],"obtains":[173,195,206],"83.0%":[174],"Top-1":[175],"accuracy":[176],"ImageNet-1K":[178],"that":[179,197],"surpasses":[180],"GNN-based":[181],"ViG-S":[182,216],"+0.9\u2191":[184],"parameters":[187],"reduced":[188],"18.5%,":[190],"while":[191],"largest":[193],"PVG-B":[194],"84.2%":[196],"+0.5\u2191":[199],"improvement":[200],"than":[201,215],"ViG-B.":[202],"Furthermore,":[203],"+1.3\u2191":[207],"box":[208],"AP":[209,213],"+0.4\u2191":[211],"mask":[212],"gains":[214],"COCO":[218],"dataset.":[219]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}