{"id":"https://openalex.org/W4415541250","doi":"https://doi.org/10.1145/3746027.3754736","title":"MediSee: Reasoning-Based Pixel-Level Perception in Medical Images","display_name":"MediSee: Reasoning-Based Pixel-Level Perception in Medical Images","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415541250","doi":"https://doi.org/10.1145/3746027.3754736"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754736","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754736","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","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/A5120132634","display_name":"Qinyue Tong","orcid":"https://orcid.org/0009-0003-1007-9349"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qinyue Tong","raw_affiliation_strings":["Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0003-1007-9349","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103069321","display_name":"Ziqian Lu","orcid":"https://orcid.org/0009-0007-3579-9130"},"institutions":[{"id":"https://openalex.org/I1328775524","display_name":"Zhejiang Sci-Tech University","ror":"https://ror.org/03893we55","country_code":"CN","type":"education","lineage":["https://openalex.org/I1328775524"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziqian Lu","raw_affiliation_strings":["Zhejiang Sci-Tech University, Hangzhou, Zhejiang, China","Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0007-3579-9130","affiliations":[{"raw_affiliation_string":"Zhejiang Sci-Tech University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I1328775524"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jun Liu","orcid":"https://orcid.org/0009-0007-4759-2276"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Liu","raw_affiliation_strings":["Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0007-4759-2276","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025598497","display_name":"Yangming Zheng","orcid":"https://orcid.org/0000-0002-7577-4778"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangming Zheng","raw_affiliation_strings":["Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0002-7577-4778","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083531923","display_name":"Zhe\u2010Ming Lu","orcid":"https://orcid.org/0000-0003-1785-7847"},"institutions":[{"id":"https://openalex.org/I1328775524","display_name":"Zhejiang Sci-Tech University","ror":"https://ror.org/03893we55","country_code":"CN","type":"education","lineage":["https://openalex.org/I1328775524"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhe-Ming Lu","raw_affiliation_strings":["Zhejiang Sci-Tech University, Hangzhou, Zhejiang, China","Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0003-1785-7847","affiliations":[{"raw_affiliation_string":"Zhejiang Sci-Tech University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I1328775524"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5120132634"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":2.2665,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.90298862,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2742","last_page":"2751"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9987999796867371,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9987999796867371,"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9976999759674072,"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/bounding-overwatch","display_name":"Bounding overwatch","score":0.7610999941825867},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7289000153541565},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.5109000205993652},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.49889999628067017},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.46480000019073486},{"id":"https://openalex.org/keywords/medical-diagnosis","display_name":"Medical diagnosis","score":0.4368000030517578}],"concepts":[{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.7610999941825867},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7289000153541565},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6459000110626221},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6136000156402588},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.5109000205993652},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.49889999628067017},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.46480000019073486},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.4368000030517578},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4172999858856201},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4007999897003174},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.37950000166893005},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3440000116825104},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2833999991416931},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C2982822547","wikidata":"https://www.wikidata.org/wiki/Q179661","display_name":"Medical treatment","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754736","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754736","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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":22,"referenced_works":["https://openalex.org/W2021707668","https://openalex.org/W2517954747","https://openalex.org/W2883683269","https://openalex.org/W2978708129","https://openalex.org/W3004371585","https://openalex.org/W3081168214","https://openalex.org/W3109384313","https://openalex.org/W3156643720","https://openalex.org/W3172681723","https://openalex.org/W4206693420","https://openalex.org/W4294842893","https://openalex.org/W4312420092","https://openalex.org/W4387025475","https://openalex.org/W4390874575","https://openalex.org/W4391109864","https://openalex.org/W4399087878","https://openalex.org/W4402727018","https://openalex.org/W4402754134","https://openalex.org/W4402781286","https://openalex.org/W4402916449","https://openalex.org/W4403666775","https://openalex.org/W4413147717"],"related_works":[],"abstract_inverted_index":{"Despite":[0],"progress":[1],"in":[2],"pixel-level":[3],"medical":[4,25,53,69,107,145],"image":[5],"perception,":[6],"existing":[7],"methods":[8],"remain":[9],"task-specific":[10],"or":[11,19],"depend":[12],"on":[13],"precise":[14],"prompts":[15],"like":[16],"bounding":[17,78],"boxes":[18],"text.":[20],"However,":[21],"the":[22,30,73,81,131],"need":[23],"for":[24,29,80,124],"knowledge":[26],"limits":[27],"accessibility":[28],"general":[31],"public,":[32],"who":[33],"are":[34],"more":[35],"likely":[36],"to":[37,64],"use":[38],"logically":[39],"reasoned":[40],"oral":[41],"queries":[42,67,141],"than":[43],"domain-specific":[44],"inputs.":[45],"In":[46],"this":[47,86],"paper,":[48],"we":[49,88,116],"introduce":[50,90],"a":[51,91,103],"novel":[52],"vision":[54],"task:":[55],"Medical":[56,94],"Reasoning":[57,95],"Segmentation":[58,96],"and":[59,71,77,97,142],"Detection":[60,98],"(MedSD),":[61],"which":[62,101],"aims":[63],"comprehend":[65],"implicit":[66,139],"about":[68],"images":[70],"generate":[72],"corresponding":[74,113],"segmentation":[75,147],"mask":[76],"box":[79],"target":[82],"object.":[83],"To":[84],"accomplish":[85],"task,":[87],"first":[89],"Multi-perspective,":[92],"Logic-driven":[93],"(MLMR-SD)":[99],"dataset,":[100],"encompasses":[102],"substantial":[104],"collection":[105],"of":[106],"entity":[108],"targets":[109],"along":[110],"with":[111,138],"their":[112],"reasoning.":[114],"Furthermore,":[115],"propose":[117],"MediSee,":[118],"an":[119],"effective":[120],"baseline":[121],"model":[122],"designed":[123],"MedSD.":[125],"The":[126,149],"experimental":[127],"results":[128],"indicate":[129],"that":[130],"proposed":[132],"method":[133],"can":[134,152],"effectively":[135],"address":[136],"MedSD":[137],"colloquial":[140],"outperform":[143],"traditional":[144],"referring":[146],"methods.":[148],"MediSee":[150],"project":[151],"be":[153],"found":[154],"here.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-25T00:00:00"}