{"id":"https://openalex.org/W4412030744","doi":"https://doi.org/10.1109/cbms65348.2025.00018","title":"Automatic Prompt Generation for Zero-Shot Single Object Frame Segmentation in Videos Using Classification Models: A Polyp Case Study","display_name":"Automatic Prompt Generation for Zero-Shot Single Object Frame Segmentation in Videos Using Classification Models: A Polyp Case Study","publication_year":2025,"publication_date":"2025-06-18","ids":{"openalex":"https://openalex.org/W4412030744","doi":"https://doi.org/10.1109/cbms65348.2025.00018"},"language":"en","primary_location":{"id":"doi:10.1109/cbms65348.2025.00018","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbms65348.2025.00018","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 38th International Symposium on Computer-Based Medical Systems (CBMS)","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/A5055184717","display_name":"Hanna Borgli","orcid":"https://orcid.org/0000-0001-9925-6134"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]},{"id":"https://openalex.org/I2799829267","display_name":"Simula Research Laboratory","ror":"https://ror.org/00vn06n10","country_code":"NO","type":"facility","lineage":["https://openalex.org/I2799829267"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Hanna Borgli","raw_affiliation_strings":["Simula & University of Oslo,Oslo,Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Simula & University of Oslo,Oslo,Norway","institution_ids":["https://openalex.org/I184942183","https://openalex.org/I2799829267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102968267","display_name":"Michael A. Riegler","orcid":"https://orcid.org/0000-0002-3153-2064"},"institutions":[{"id":"https://openalex.org/I2799829267","display_name":"Simula Research Laboratory","ror":"https://ror.org/00vn06n10","country_code":"NO","type":"facility","lineage":["https://openalex.org/I2799829267"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Michael Riegler","raw_affiliation_strings":["Simula,Oslo,Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Simula,Oslo,Norway","institution_ids":["https://openalex.org/I2799829267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113578303","display_name":"H\u00e5kon Kvale Stensland","orcid":"https://orcid.org/0000-0002-1085-8540"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]},{"id":"https://openalex.org/I2799829267","display_name":"Simula Research Laboratory","ror":"https://ror.org/00vn06n10","country_code":"NO","type":"facility","lineage":["https://openalex.org/I2799829267"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"H\u00e5kon Kvale Stensland","raw_affiliation_strings":["Simula & University of Oslo,Oslo,Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Simula & University of Oslo,Oslo,Norway","institution_ids":["https://openalex.org/I184942183","https://openalex.org/I2799829267"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088962741","display_name":"P\u00e5l Halvorsen","orcid":"https://orcid.org/0000-0003-2073-7029"},"institutions":[{"id":"https://openalex.org/I4210153474","display_name":"Simula Metropolitan Center for Digital Engineering","ror":"https://ror.org/04xtarr15","country_code":"NO","type":"nonprofit","lineage":["https://openalex.org/I184531372","https://openalex.org/I2799829267","https://openalex.org/I4210153474"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"P\u00e5l Halvorsen","raw_affiliation_strings":["SimulaMet & OsloMet,Oslo,Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SimulaMet & OsloMet,Oslo,Norway","institution_ids":["https://openalex.org/I4210153474"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14288702,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"41","last_page":"48"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9264000058174133,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9264000058174133,"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":0.9007999897003174,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.6651718616485596},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6649746894836426},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.654524564743042},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5831859707832336},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5558583736419678},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5437227487564087},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5396826863288879},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4907265901565552},{"id":"https://openalex.org/keywords/single-shot","display_name":"Single shot","score":0.48904117941856384},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.4696578085422516},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4658316969871521},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.4323046803474426},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.30443331599235535},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0700782835483551}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6651718616485596},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6649746894836426},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.654524564743042},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5831859707832336},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5558583736419678},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5437227487564087},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5396826863288879},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4907265901565552},{"id":"https://openalex.org/C3019835501","wikidata":"https://www.wikidata.org/wiki/Q1310130","display_name":"Single shot","level":2,"score":0.48904117941856384},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.4696578085422516},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4658316969871521},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.4323046803474426},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.30443331599235535},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0700782835483551},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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/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},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cbms65348.2025.00018","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbms65348.2025.00018","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 38th International Symposium on Computer-Based Medical Systems (CBMS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1495267108","https://openalex.org/W2017814585","https://openalex.org/W2108598243","https://openalex.org/W2295107390","https://openalex.org/W2337429362","https://openalex.org/W2552414813","https://openalex.org/W2962758679","https://openalex.org/W2962867364","https://openalex.org/W2997286550","https://openalex.org/W2997851315","https://openalex.org/W2999580839","https://openalex.org/W3034930876","https://openalex.org/W3082604781","https://openalex.org/W3092344722","https://openalex.org/W3162386519","https://openalex.org/W3177958285","https://openalex.org/W4308456711","https://openalex.org/W4313153210","https://openalex.org/W4319298404","https://openalex.org/W4385481295","https://openalex.org/W4388998820","https://openalex.org/W4389430914","https://openalex.org/W4390874575","https://openalex.org/W4402716047","https://openalex.org/W4402727630","https://openalex.org/W4404612908","https://openalex.org/W4405925280","https://openalex.org/W4407874968","https://openalex.org/W4408345812","https://openalex.org/W4408977016","https://openalex.org/W6631190155","https://openalex.org/W6680096826","https://openalex.org/W6768817161","https://openalex.org/W6803376173","https://openalex.org/W6804750070","https://openalex.org/W6851800889","https://openalex.org/W6856857450","https://openalex.org/W6861232000","https://openalex.org/W6873574188","https://openalex.org/W6874673442"],"related_works":["https://openalex.org/W3142396426","https://openalex.org/W2471333042","https://openalex.org/W4396643691","https://openalex.org/W4409177797","https://openalex.org/W4404739899","https://openalex.org/W4402383816","https://openalex.org/W2955491601","https://openalex.org/W146529714","https://openalex.org/W4402559869","https://openalex.org/W4230158770"],"abstract_inverted_index":{"Video":[0],"object":[1],"segmentation":[2,30,135,137],"is":[3,37],"vital":[4],"for":[5,16,39,85],"applications":[6],"like":[7,19],"medical":[8],"diagnostics,":[9],"but":[10,31],"acquiring":[11],"dense":[12],"pixel-level":[13],"annotations,":[14],"especially":[15],"specialized":[17],"domains":[18],"polyp":[20],"segmentation,":[21],"remains":[22],"a":[23,45,63,89],"major":[24],"bottleneck.":[25],"Foundational":[26],"models":[27],"offer":[28],"zero-shot":[29],"typically":[32],"require":[33],"manual":[34],"prompting,":[35],"which":[36],"impractical":[38],"long":[40],"videos.":[41],"We":[42],"propose":[43],"Map2VidSeg,":[44],"novel":[46],"pipeline":[47],"that":[48],"automatically":[49],"generates":[50],"prompts":[51,110],"from":[52,62],"imagelevel":[53],"classification":[54],"labels.":[55],"It":[56],"leverages":[57],"localization":[58],"cues":[59],"(attention":[60],"maps/CAMs)":[61],"trained":[64],"image":[65],"classifier":[66],"(ViT/CNN)":[67],"to":[68],"create":[69],"bounding":[70],"box":[71],"prompts.":[72],"These":[73],"guide":[74],"an":[75],"efficient":[76],"model":[77,91],"(YOLOE)":[78],"with":[79],"tracking":[80],"(BOT-SORT)":[81],"and":[82,99,125],"bidirectional":[83],"propagation":[84],"initial":[86],"segmentation.":[87],"Optionally,":[88],"high-fidelity":[90],"(SAM-2)":[92],"refines":[93],"these":[94],"masks":[95],"using":[96],"temporal":[97],"memory":[98],"fusion.":[100],"Demonstrated":[101],"on":[102],"the":[103,130],"challenging":[104],"SUN-SEG":[105],"benchmark,":[106],"finetuned":[107],"DINOv2":[108],"(ViT)":[109],"significantly":[111],"outperform":[112],"DenseNet-121":[113],"(CNN).":[114],"Our":[115],"best":[116],"configuration":[117],"(DINOv2+YOLOE+SAM-2":[118],"Bidirectional)":[119],"achieves":[120],"Dice/mIoU":[121],"0.76/0.70":[122],"(Easy":[123],"Unseen)":[124],"0.66/0.60":[126],"(Hard":[127],"Unseen),":[128],"showcasing":[129],"viability":[131],"of":[132],"robust":[133],"video":[134],"without":[136],"training":[138],"data.":[139]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}