{"id":"https://openalex.org/W7160187380","doi":"https://doi.org/10.1109/iccv51701.2025.01939","title":"Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs","display_name":"Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W7160187380","doi":"https://doi.org/10.1109/iccv51701.2025.01939"},"language":null,"primary_location":{"id":"doi:10.1109/iccv51701.2025.01939","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01939","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/A5080378965","display_name":"Q. F. Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qizhe Zhang","raw_affiliation_strings":["School of Computer Science, Peking University,State Key Laboratory for Multimedia Information Processing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University,State Key Laboratory for Multimedia Information Processing","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109756790","display_name":"Aosong Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aosong Cheng","raw_affiliation_strings":["School of Computer Science, Peking University,State Key Laboratory for Multimedia Information Processing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University,State Key Laboratory for Multimedia Information Processing","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125048255","display_name":"M Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Lu","raw_affiliation_strings":["School of Computer Science, Peking University,State Key Laboratory for Multimedia Information Processing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University,State Key Laboratory for Multimedia Information Processing","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124925880","display_name":"Renrui Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Renrui Zhang","raw_affiliation_strings":["CUHK MMLab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CUHK MMLab","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025941787","display_name":"Zhiyong Zhuo","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Zhuo","raw_affiliation_strings":["School of Computer Science, Peking University,State Key Laboratory for Multimedia Information Processing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University,State Key Laboratory for Multimedia Information Processing","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135107633","display_name":"Jiajun Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiajun Cao","raw_affiliation_strings":["School of Computer Science, Peking University,State Key Laboratory for Multimedia Information Processing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University,State Key Laboratory for Multimedia Information Processing","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135102773","display_name":"Shaobo Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shaobo Guo","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018523545","display_name":"Qi She","orcid":"https://orcid.org/0000-0002-4490-2941"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi She","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040418528","display_name":"Shanghang Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shanghang Zhang","raw_affiliation_strings":["School of Computer Science, Peking University,State Key Laboratory for Multimedia Information Processing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University,State Key Laboratory for Multimedia Information Processing","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":"20857","last_page":"20867"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10789","display_name":"Interactive and Immersive Displays","score":0.47110000252723694,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T10789","display_name":"Interactive and Immersive Displays","score":0.47110000252723694,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T10799","display_name":"Data Visualization and Analytics","score":0.12189999967813492,"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/T10914","display_name":"Tactile and Sensory Interactions","score":0.09380000084638596,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.4018999934196472},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.31450000405311584},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.31209999322891235},{"id":"https://openalex.org/keywords/sensory-cue","display_name":"Sensory cue","score":0.2768000066280365},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.27399998903274536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6421999931335449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.579800009727478},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.4018999934196472},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3952000141143799},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.25999999046325684}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccv51701.2025.01939","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01939","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":37,"referenced_works":["https://openalex.org/W1994530392","https://openalex.org/W2560730294","https://openalex.org/W2606982687","https://openalex.org/W2765716052","https://openalex.org/W2963518342","https://openalex.org/W2963622213","https://openalex.org/W2964220823","https://openalex.org/W2979382951","https://openalex.org/W3159481202","https://openalex.org/W4221159599","https://openalex.org/W4385571769","https://openalex.org/W4388979610","https://openalex.org/W4389523832","https://openalex.org/W4390873312","https://openalex.org/W4402671548","https://openalex.org/W4402713111","https://openalex.org/W4402727764","https://openalex.org/W4402727851","https://openalex.org/W4402754023","https://openalex.org/W4403002096","https://openalex.org/W4403081466","https://openalex.org/W4403939369","https://openalex.org/W4404199570","https://openalex.org/W4404781554","https://openalex.org/W4404784276","https://openalex.org/W4409363282","https://openalex.org/W4411725552","https://openalex.org/W4413144738","https://openalex.org/W4413156814","https://openalex.org/W4413157503","https://openalex.org/W4415293928","https://openalex.org/W4415795395","https://openalex.org/W4415796867","https://openalex.org/W4415797729","https://openalex.org/W7133211372","https://openalex.org/W7133223072","https://openalex.org/W7133227460"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2026-05-05T00:00:00"}
