{"id":"https://openalex.org/W7160044699","doi":"https://doi.org/10.1109/iccv51701.2025.02238","title":"Token-Efficient VLM: High-Resolution Image Understanding Via Dynamic Region Proposal","display_name":"Token-Efficient VLM: High-Resolution Image Understanding Via Dynamic Region Proposal","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W7160044699","doi":"https://doi.org/10.1109/iccv51701.2025.02238"},"language":null,"primary_location":{"id":"doi:10.1109/iccv51701.2025.02238","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02238","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","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/A5101093961","display_name":"Yitong Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yitong Jiang","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100370029","display_name":"Jinwei Gu","orcid":"https://orcid.org/0000-0001-8705-8237"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinwei Gu","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100552155","display_name":"Tianfan Xue","orcid":"https://orcid.org/0000-0001-5031-6618"},"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":"Tianfan Xue","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135211470","display_name":"Ka Shing M. Cheung","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ka Chun Cheung","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135128715","display_name":"Pavlo Molchanov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pavlo Molchanov","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135134297","display_name":"Hongxu Yin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongxu Yin","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049815485","display_name":"Sifei Liu","orcid":"https://orcid.org/0000-0002-6011-3686"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sifei Liu","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"24147","last_page":"24158"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.12359999865293503,"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"}},"topics":[{"id":"https://openalex.org/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.12359999865293503,"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"}},{"id":"https://openalex.org/T12549","display_name":"Image and Object Detection Techniques","score":0.07090000063180923,"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":0.06390000134706497,"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/image","display_name":"Image (mathematics)","score":0.5},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.3578000068664551},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3043000102043152},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.2955000102519989},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.28999999165534973},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.28540000319480896}],"concepts":[{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5608999729156494},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5602999925613403},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5228000283241272},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3578000068664551},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2955000102519989},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.28999999165534973},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.25940001010894775},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccv51701.2025.02238","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02238","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2307512708","https://openalex.org/W2549599535","https://openalex.org/W2560730294","https://openalex.org/W2947312908","https://openalex.org/W2963420691","https://openalex.org/W2963518342","https://openalex.org/W2979382951","https://openalex.org/W3004268082","https://openalex.org/W3106859150","https://openalex.org/W3120043490","https://openalex.org/W3156892778","https://openalex.org/W4213213306","https://openalex.org/W4214713996","https://openalex.org/W4224919571","https://openalex.org/W4285255856","https://openalex.org/W4300655590","https://openalex.org/W4312233877","https://openalex.org/W4312299632","https://openalex.org/W4312960790","https://openalex.org/W4389523832","https://openalex.org/W4390873312","https://openalex.org/W4402716330","https://openalex.org/W4402716477","https://openalex.org/W4402727516","https://openalex.org/W4402727764","https://openalex.org/W4402727815","https://openalex.org/W4402727885","https://openalex.org/W4402753807","https://openalex.org/W4402754023","https://openalex.org/W4403081466","https://openalex.org/W4403842540","https://openalex.org/W4413147769","https://openalex.org/W4415796658","https://openalex.org/W4415800665","https://openalex.org/W7125812135","https://openalex.org/W7133196460","https://openalex.org/W7133220561","https://openalex.org/W7133223072","https://openalex.org/W7133250524"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-05-05T00:00:00"}