{"id":"https://openalex.org/W4415537329","doi":"https://doi.org/10.1145/3746027.3762093","title":"Multi-Level CLS Token Fusion for Contrastive Learning in Endoscopy Image Classification","display_name":"Multi-Level CLS Token Fusion for Contrastive Learning in Endoscopy Image Classification","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415537329","doi":"https://doi.org/10.1145/3746027.3762093"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3762093","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3762093","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":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.00752","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Y Hop Nguyen","orcid":"https://orcid.org/0009-0001-0021-5429"},"institutions":[{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]}],"countries":["VN"],"is_corresponding":true,"raw_author_name":"Y Hop Nguyen","raw_affiliation_strings":["University of Science, VNU-HCM, Ho Chi Minh, Vietnam and South Telecom JSC, Ho Chi Minh, Vietnam"],"raw_orcid":"https://orcid.org/0009-0001-0021-5429","affiliations":[{"raw_affiliation_string":"University of Science, VNU-HCM, Ho Chi Minh, Vietnam and South Telecom JSC, Ho Chi Minh, Vietnam","institution_ids":["https://openalex.org/I23582244"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120131503","display_name":"Doan Anh Phan Huu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095603","display_name":"Vietnam Posts and Telecommunications Group (Vietnam)","ror":"https://ror.org/00q0e7f94","country_code":"VN","type":"company","lineage":["https://openalex.org/I4210095603"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Doan Anh Phan Huu","raw_affiliation_strings":["South Telecom JSC, Ho Chi Minh, Vietnam"],"raw_orcid":"https://orcid.org/0009-0008-4512-0053","affiliations":[{"raw_affiliation_string":"South Telecom JSC, Ho Chi Minh, Vietnam","institution_ids":["https://openalex.org/I4210095603"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058001152","display_name":"Trung Thai Tran","orcid":"https://orcid.org/0000-0001-5073-4481"},"institutions":[{"id":"https://openalex.org/I4210095603","display_name":"Vietnam Posts and Telecommunications Group (Vietnam)","ror":"https://ror.org/00q0e7f94","country_code":"VN","type":"company","lineage":["https://openalex.org/I4210095603"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Trung Thai Tran","raw_affiliation_strings":["South Telecom JSC, Ho Chi Minh, Vietnam"],"raw_orcid":"https://orcid.org/0009-0002-1422-9685","affiliations":[{"raw_affiliation_string":"South Telecom JSC, Ho Chi Minh, Vietnam","institution_ids":["https://openalex.org/I4210095603"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047437481","display_name":"Nhat Nam","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095603","display_name":"Vietnam Posts and Telecommunications Group (Vietnam)","ror":"https://ror.org/00q0e7f94","country_code":"VN","type":"company","lineage":["https://openalex.org/I4210095603"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Nhat Nam Mai","raw_affiliation_strings":["South Telecom JSC, Ho Chi Minh, Vietnam"],"raw_orcid":"https://orcid.org/0009-0005-3310-7562","affiliations":[{"raw_affiliation_string":"South Telecom JSC, Ho Chi Minh, Vietnam","institution_ids":["https://openalex.org/I4210095603"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120131504","display_name":"Van Toi Giap","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095603","display_name":"Vietnam Posts and Telecommunications Group (Vietnam)","ror":"https://ror.org/00q0e7f94","country_code":"VN","type":"company","lineage":["https://openalex.org/I4210095603"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Van Toi Giap","raw_affiliation_strings":["South Telecom JSC, Ho Chi Minh, Vietnam"],"raw_orcid":"https://orcid.org/0009-0007-0219-1735","affiliations":[{"raw_affiliation_string":"South Telecom JSC, Ho Chi Minh, Vietnam","institution_ids":["https://openalex.org/I4210095603"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002706405","display_name":"Thao Thi Phuong Dao","orcid":"https://orcid.org/0000-0002-0109-1114"},"institutions":[{"id":"https://openalex.org/I4210145414","display_name":"Hung Vuong Hospital","ror":"https://ror.org/04qrwnv94","country_code":"VN","type":"healthcare","lineage":["https://openalex.org/I4210145414"]},{"id":"https://openalex.org/I47265099","display_name":"Ho Chi Minh City University of Technology","ror":"https://ror.org/04qva2324","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I47265099"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Thao Thi Phuong Dao","raw_affiliation_strings":["University of Science, VNU-HCM, Ho Chi Minh, Vietnam and Thong Nhat Hospital, Ho Chi Minh, Vietnam"],"raw_orcid":"https://orcid.org/0000-0002-0109-1114","affiliations":[{"raw_affiliation_string":"University of Science, VNU-HCM, Ho Chi Minh, Vietnam and Thong Nhat Hospital, Ho Chi Minh, Vietnam","institution_ids":["https://openalex.org/I47265099","https://openalex.org/I4210145414"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062359795","display_name":"Trung-Nghia Le","orcid":"https://orcid.org/0000-0002-7363-2610"},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]},{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Trung-Nghia Le","raw_affiliation_strings":["University of Science, VNU-HCM, Ho Chi Minh, Vietnam"],"raw_orcid":"https://orcid.org/0000-0002-7363-2610","affiliations":[{"raw_affiliation_string":"University of Science, VNU-HCM, Ho Chi Minh, Vietnam","institution_ids":["https://openalex.org/I23582244","https://openalex.org/I123565023"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I23582244"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3965037,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"14197","last_page":"14203"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10552","display_name":"Colorectal Cancer Screening and Detection","score":0.9890000224113464,"subfield":{"id":"https://openalex.org/subfields/2730","display_name":"Oncology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10552","display_name":"Colorectal Cancer Screening and Detection","score":0.9890000224113464,"subfield":{"id":"https://openalex.org/subfields/2730","display_name":"Oncology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9824000000953674,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9776999950408936,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.554099977016449},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5529000163078308},{"id":"https://openalex.org/keywords/cls-upper-limits","display_name":"CLs upper limits","score":0.49459999799728394},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.453000009059906},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.43639999628067017},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.4230000078678131},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40950000286102295},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3871000111103058}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.76419997215271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6455000042915344},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.554099977016449},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5529000163078308},{"id":"https://openalex.org/C190729725","wikidata":"https://www.wikidata.org/wiki/Q5012817","display_name":"CLs upper limits","level":2,"score":0.49459999799728394},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.453000009059906},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.43639999628067017},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.4230000078678131},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40950000286102295},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3871000111103058},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3716000020503998},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.3582000136375427},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.35100001096725464},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3465000092983246},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.34220001101493835},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.335999995470047},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3353999853134155},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.33480000495910645},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33180001378059387},{"id":"https://openalex.org/C2776848632","wikidata":"https://www.wikidata.org/wiki/Q853463","display_name":"Clipping (morphology)","level":2,"score":0.32499998807907104},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.32199999690055847},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.3172000050544739},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.27320000529289246}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3762093","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3762093","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"},{"id":"pmh:oai:arXiv.org:2509.00752","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.00752","pdf_url":"https://arxiv.org/pdf/2509.00752","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.00752","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.00752","pdf_url":"https://arxiv.org/pdf/2509.00752","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2963163009","https://openalex.org/W3035253074","https://openalex.org/W3201906559","https://openalex.org/W4312310776","https://openalex.org/W4403228785"],"related_works":[],"abstract_inverted_index":{"We":[0,108],"present":[1],"a":[2,98],"unified":[3],"vision-language":[4],"framework":[5,111],"tailored":[6],"for":[7,133,162],"ENT":[8],"endoscopy":[9],"image":[10,18,95],"analysis":[11],"that":[12,29,92],"simultaneously":[13],"tackles":[14],"three":[15],"clinically-relevant":[16],"tasks:":[17],"classification,":[19,127],"image-to-image":[20,134],"retrieval,":[21],"and":[22,42,52,70,82,124,131,135,139,144],"text-to-image":[23,136],"retrieval.":[24],"Unlike":[25],"conventional":[26],"CNN-based":[27],"pipelines":[28],"struggle":[30],"to":[31],"capture":[32],"cross-modal":[33],"semantics,":[34],"our":[35,110,160],"approach":[36],"leverages":[37],"the":[38,77,94,115,149,157],"CLIP":[39],"ViT-B/16":[40],"backbone":[41],"enhances":[43],"it":[44],"through":[45,97,112],"Low-Rank":[46],"Adaptation,":[47],"multi-level":[48],"CLS":[49],"token":[50],"aggregation,":[51],"spherical":[53],"feature":[54],"interpolation.":[55],"These":[56],"components":[57],"collectively":[58],"enable":[59],"efficient":[60],"fine-tuning":[61],"on":[62],"limited":[63],"medical":[64,165],"data":[65],"while":[66],"improving":[67],"representation":[68],"diversity":[69],"semantic":[71],"alignment":[72],"across":[73],"modalities.":[74],"To":[75],"bridge":[76],"gap":[78],"between":[79],"visual":[80],"inputs":[81],"textual":[83],"diagnostic":[84],"context,":[85],"we":[86],"introduce":[87],"class-specific":[88],"natural":[89],"language":[90],"prompts":[91],"guide":[93],"encoder":[96],"joint":[99],"training":[100],"objective":[101],"combining":[102],"supervised":[103],"classification":[104],"with":[105],"contrastive":[106],"learning.":[107],"validated":[109],"participation":[113],"in":[114,126,167],"ACM":[116],"MM'25":[117],"ENTRep":[118],"Grand":[119],"Challenge,":[120],"achieving":[121],"95%":[122],"accuracy":[123],"F1-score":[125],"Recall@1":[128],"of":[129,142,152,159],"0.93":[130],"0.92":[132],"retrieval":[137],"respectively,":[138],"MRR":[140],"scores":[141],"0.97":[143],"0.96.":[145],"Ablation":[146],"studies":[147],"demonstrated":[148],"incremental":[150],"benefits":[151],"each":[153],"architectural":[154],"component,":[155],"validating":[156],"effectiveness":[158],"design":[161],"robust":[163],"multimodal":[164],"understanding":[166],"low-resource":[168],"clinical":[169],"settings.":[170]},"counts_by_year":[],"updated_date":"2026-04-30T09:15:22.047038","created_date":"2025-10-25T00:00:00"}