{"id":"https://openalex.org/W4412725365","doi":"https://doi.org/10.1109/tpami.2025.3593283","title":"Parameter-Inverted Image Pyramid Networks for Visual Perception and Multimodal Understanding","display_name":"Parameter-Inverted Image Pyramid Networks for Visual Perception and Multimodal Understanding","publication_year":2025,"publication_date":"2025-07-28","ids":{"openalex":"https://openalex.org/W4412725365","doi":"https://doi.org/10.1109/tpami.2025.3593283","pmid":"https://pubmed.ncbi.nlm.nih.gov/40720274"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3593283","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3593283","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zhaokai Wang","orcid":"https://orcid.org/0009-0003-3331-4022"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaokai Wang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China","Shanghai Jiao Tong University, China"],"raw_orcid":"https://orcid.org/0009-0003-3331-4022","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112877229","display_name":"Xizhou Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xizhou Zhu","raw_affiliation_strings":["Tsinghua University, Beijing, China","Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xue Yang","orcid":"https://orcid.org/0000-0002-7084-9101"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xue Yang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China","Shanghai Jiao Tong University, China"],"raw_orcid":"https://orcid.org/0000-0002-7084-9101","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102997988","display_name":"Gen Luo","orcid":"https://orcid.org/0000-0001-5334-1843"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gen Luo","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory, Shanghai, China","Shanghai Artificial Intelligence Laboratory, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]},{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100348559","display_name":"Hao Li","orcid":"https://orcid.org/0000-0002-1758-5936"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hao Li","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong","Chinese University of Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087792832","display_name":"Changyao Tian","orcid":"https://orcid.org/0000-0002-3285-4671"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Changyao Tian","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong","Chinese University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-3285-4671","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wenhan Dou","orcid":"https://orcid.org/0009-0002-6398-0512"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhan Dou","raw_affiliation_strings":["Tsinghua University, Beijing, China","Tsinghua University, China"],"raw_orcid":"https://orcid.org/0009-0002-6398-0512","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113244353","display_name":"Junqi Ge","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junqi Ge","raw_affiliation_strings":["Tsinghua University, Beijing, China","Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101377851","display_name":"Lewei Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210092218","display_name":"Sensimetrics Corporation","ror":"https://ror.org/00h7y2d26","country_code":"US","type":"company","lineage":["https://openalex.org/I4210092218"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lewei Lu","raw_affiliation_strings":["Sensetime, Hong Kong"],"raw_orcid":"https://orcid.org/0009-0009-9809-3818","affiliations":[{"raw_affiliation_string":"Sensetime, Hong Kong","institution_ids":["https://openalex.org/I4210092218"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100748135","display_name":"Yu Qiao","orcid":"https://orcid.org/0000-0002-1889-2567"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Qiao","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory, Shanghai, China","Shanghai Artificial Intelligence Laboratory, China"],"raw_orcid":"https://orcid.org/0000-0002-1889-2567","affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]},{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026944066","display_name":"Jifeng Dai","orcid":"https://orcid.org/0000-0002-6785-0785"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jifeng Dai","raw_affiliation_strings":["Tsinghua University, Beijing, China","Tsinghua University, China"],"raw_orcid":"https://orcid.org/0000-0002-6785-0785","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7802,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.73088422,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"47","issue":"11","first_page":"10142","last_page":"10159"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9994000196456909,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9994000196456909,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9983999729156494,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9975000023841858,"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":0.8077158331871033},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7251102328300476},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.6361573338508606},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5608683824539185},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5348794460296631},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5312380790710449},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47332462668418884},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4724567234516144},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4714150130748749},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4652123749256134},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4547017514705658},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42251163721084595},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4216316044330597},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3736644387245178},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.08480438590049744}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8077158331871033},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7251102328300476},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.6361573338508606},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5608683824539185},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5348794460296631},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5312380790710449},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47332462668418884},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4724567234516144},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4714150130748749},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4652123749256134},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4547017514705658},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42251163721084595},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4216316044330597},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3736644387245178},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.08480438590049744},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3593283","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3593283","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:40720274","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40720274","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1193382289","display_name":null,"funder_award_id":"2022ZD0161300","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G2438210826","display_name":null,"funder_award_id":"62321005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4092911450","display_name":null,"funder_award_id":"62376134","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6226388984","display_name":null,"funder_award_id":"25ZR1402268","funder_id":"https://openalex.org/F4320309612","funder_display_name":"Natural Science Foundation of Shanghai"},{"id":"https://openalex.org/G8442236830","display_name":null,"funder_award_id":"U24A20325","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320309612","display_name":"Natural Science Foundation of Shanghai","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2108598243","https://openalex.org/W2307512708","https://openalex.org/W2560730294","https://openalex.org/W2565639579","https://openalex.org/W2737258237","https://openalex.org/W2768489488","https://openalex.org/W2884822772","https://openalex.org/W2963150697","https://openalex.org/W2963420691","https://openalex.org/W2963518342","https://openalex.org/W2964241181","https://openalex.org/W2964444661","https://openalex.org/W2966317026","https://openalex.org/W2979382951","https://openalex.org/W2988326850","https://openalex.org/W2990631821","https://openalex.org/W2991359031","https://openalex.org/W3014641072","https://openalex.org/W3034971973","https://openalex.org/W3081168214","https://openalex.org/W3129831491","https://openalex.org/W3131500599","https://openalex.org/W3138516171","https://openalex.org/W3151130473","https://openalex.org/W3176371077","https://openalex.org/W3188427387","https://openalex.org/W4213213306","https://openalex.org/W4226334005","https://openalex.org/W4250482878","https://openalex.org/W4285255856","https://openalex.org/W4312290555","https://openalex.org/W4312443924","https://openalex.org/W4312446817","https://openalex.org/W4312453657","https://openalex.org/W4312746376","https://openalex.org/W4313156423","https://openalex.org/W4385245566","https://openalex.org/W4386076222","https://openalex.org/W4386076522","https://openalex.org/W4389523832","https://openalex.org/W4390873750","https://openalex.org/W4390874070","https://openalex.org/W4402713111","https://openalex.org/W4402727669","https://openalex.org/W4402727764","https://openalex.org/W4402753874","https://openalex.org/W4402753969","https://openalex.org/W4402952458","https://openalex.org/W4403081466","https://openalex.org/W4404002404","https://openalex.org/W4404199570","https://openalex.org/W4404575065","https://openalex.org/W4404781880","https://openalex.org/W4405595839","https://openalex.org/W4413156626"],"related_works":["https://openalex.org/W4249847449","https://openalex.org/W44395729","https://openalex.org/W2765338038","https://openalex.org/W1496225612","https://openalex.org/W1523500768","https://openalex.org/W1566843515","https://openalex.org/W4292850564","https://openalex.org/W2181660907","https://openalex.org/W4386191828","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Image":[0,50],"pyramids":[1,21],"are":[2,73],"widely":[3],"adopted":[4],"in":[5],"top-performing":[6],"methods":[7],"to":[8,27,34,64,79,107,142,154],"obtain":[9],"multi-scale":[10,66],"features":[11],"for":[12],"precise":[13],"visual":[14],"perception":[15,109],"and":[16,83,111,120,134,144,170,187,203],"understanding.":[17,136],"However,":[18],"current":[19],"image":[20,132],"use":[22],"the":[23,176],"same":[24],"large-scale":[25,157],"model":[26,117],"process":[28,65],"multiple":[29],"resolutions":[30,72],"of":[31,70,175],"images,":[32,67],"leading":[33],"significant":[35],"computational":[36,81,150],"cost.":[37,151],"To":[38,85,101],"address":[39],"this":[40],"challenge,":[41],"we":[42,92,104],"propose":[43,94],"a":[44,95,112,156],"novel":[45,96],"network":[46,77],"architecture,":[47],"called":[48,118],"Parameter-Inverted":[49],"Pyramid":[51],"Networks":[52],"(PIIP).":[53],"Specifically,":[54],"PIIP":[55,137,161],"uses":[56],"pretrained":[57],"models":[58,110],"(ViTs":[59],"or":[60],"CNNs)":[61],"as":[62,128],"branches":[63,78],"where":[68],"images":[69],"higher":[71],"processed":[74],"by":[75,166],"smaller":[76],"balance":[80],"cost":[82],"performance.":[84],"integrate":[86],"information":[87],"from":[88],"different":[89],"spatial":[90],"scales,":[91],"further":[93],"cross-branch":[97],"feature":[98],"interaction":[99],"mechanism.":[100],"validate":[102],"PIIP,":[103],"apply":[105],"it":[106],"various":[108,125],"representative":[113],"multimodal":[114,135,194],"large":[115],"language":[116],"LLaVA,":[119],"conduct":[121],"extensive":[122],"experiments":[123],"on":[124,168,184,190,201,205],"tasks":[126],"such":[127],"object":[129],"detection,":[130],"segmentation,":[131],"classification":[133],"achieves":[138,198],"superior":[139],"performance":[140,165],"compared":[141],"single-branch":[143],"existing":[145],"multi-resolution":[146],"approaches":[147],"with":[148,172,207],"lower":[149],"When":[152],"applied":[153],"InternViT-6B,":[155],"vision":[158],"foundation":[159],"model,":[160],"can":[162],"improve":[163],"its":[164],"1%-2%":[167],"detection":[169],"segmentation":[171],"only":[173,208],"40%-60%":[174],"original":[177],"computation,":[178],"finally":[179],"achieving":[180],"60.0":[181],"box":[182],"AP":[183],"MS":[185],"COCO":[186],"59.7":[188],"mIoU":[189],"ADE20":[191],"K.":[192],"For":[193],"understanding,":[195],"our":[196],"PIIP-LLaVA":[197],"73.0%":[199],"accuracy":[200],"TextVQA":[202],"74.5%":[204],"MMBench":[206],"2.8":[209],"M":[210],"training":[211],"data.":[212]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-08T08:33:18.762332","created_date":"2025-10-10T00:00:00"}