{"id":"https://openalex.org/W7147006960","doi":"https://doi.org/10.1109/cnml68938.2026.11452259","title":"CLIP-DyCAM: Dynamic Category Feature Fusion and CAMs Optimization for Weakly Supervised Semantic Segmentation","display_name":"CLIP-DyCAM: Dynamic Category Feature Fusion and CAMs Optimization for Weakly Supervised Semantic Segmentation","publication_year":2026,"publication_date":"2026-01-30","ids":{"openalex":"https://openalex.org/W7147006960","doi":"https://doi.org/10.1109/cnml68938.2026.11452259"},"language":null,"primary_location":{"id":"doi:10.1109/cnml68938.2026.11452259","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cnml68938.2026.11452259","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on Communication Networks and Machine Learning (CNML)","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/A5132575401","display_name":"Yuqiang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuqiang Li","raw_affiliation_strings":["Wuhan University of Technology,Wuhan,China,430070"],"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology,Wuhan,China,430070","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132671229","display_name":"Han Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Cao","raw_affiliation_strings":["Wuhan University of Technology,Wuhan,China,430070"],"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology,Wuhan,China,430070","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011466881","display_name":"Zongjin Li","orcid":"https://orcid.org/0000-0002-8477-6863"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Li","raw_affiliation_strings":["Wuhan University of Technology,Wuhan,China,430070"],"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology,Wuhan,China,430070","institution_ids":["https://openalex.org/I196699116"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5132575401"],"corresponding_institution_ids":["https://openalex.org/I196699116"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.89916034,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"784","last_page":"788"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8511000275611877,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8511000275611877,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.09480000287294388,"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":0.012500000186264515,"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/pascal","display_name":"Pascal (unit)","score":0.6244000196456909},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6147000193595886},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5957000255584717},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5239999890327454},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4571000039577484},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.4316999912261963},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37389999628067017},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.35530000925064087}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7520999908447266},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.690500020980835},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.6244000196456909},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6147000193595886},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5957000255584717},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5239999890327454},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4571000039577484},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.4316999912261963},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37389999628067017},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.35530000925064087},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.35370001196861267},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.35100001096725464},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33399999141693115},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3172999918460846},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2996000051498413},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.29510000348091125},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.28690001368522644},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.25609999895095825},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.25600001215934753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cnml68938.2026.11452259","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cnml68938.2026.11452259","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on Communication Networks and Machine Learning (CNML)","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":9,"referenced_works":["https://openalex.org/W2031489346","https://openalex.org/W2295107390","https://openalex.org/W2952122856","https://openalex.org/W2962758679","https://openalex.org/W2962858109","https://openalex.org/W4386071798","https://openalex.org/W4387968037","https://openalex.org/W4402727341","https://openalex.org/W4405104655"],"related_works":[],"abstract_inverted_index":{"Image-level":[0],"Weakly":[1],"Supervised":[2],"Semantic":[3],"Segmentation":[4],"(WSSS)":[5],"has":[6],"attracted":[7],"significant":[8],"interest":[9],"due":[10],"to":[11,14,144],"its":[12],"potential":[13],"reduce":[15],"annotation":[16],"efforts.":[17],"Recent":[18],"advancements":[19],"utilizing":[20],"CLIP-based":[21],"frameworks,":[22],"such":[23],"as":[24],"CLIP-ES,":[25,145],"have":[26],"demonstrated":[27],"notable":[28],"progress.":[29],"However,":[30],"persistent":[31],"challenges":[32],"remain":[33],"in":[34,54,149],"complex":[35,151],"scenes":[36],"characterized":[37],"by":[38,137],"multi-object":[39],"coexistence":[40],"and":[41,58,110,117,128,139],"fine-grained":[42,89],"details.":[43],"These":[44],"issues":[45],"largely":[46],"stem":[47],"from":[48,86,92],"the":[49,59,93],"lack":[50],"of":[51,61],"contextual":[52,90],"awareness":[53],"static":[55],"text":[56],"prompts":[57],"oversight":[60],"shallow":[62,116],"feature":[63,78],"attention.":[64],"To":[65],"address":[66],"these":[67],"limitations,":[68],"we":[69,99],"propose":[70],"CLIP-DyCAM.":[71],"This":[72],"framework":[73],"introduces":[74],"a":[75,101],"dynamic":[76,121],"category":[77],"fusion":[79,113],"mechanism":[80,105],"that":[81,133],"strategically":[82],"combines":[83],"global":[84],"semantics":[85],"CLIP":[87],"with":[88],"descriptions":[91],"BLIP":[94],"visual":[95],"question-answering":[96],"model.":[97],"Furthermore,":[98],"design":[100],"hierarchical":[102],"CAMs":[103],"optimization":[104],"incorporating":[106],"category-sensitive":[107],"temperature":[108],"scaling":[109],"multi-level":[111],"attention":[112],"(combining":[114],"ViT\u2019s":[115],"deep":[118],"features)":[119],"alongside":[120],"thresholding.":[122],"Experiments":[123],"on":[124],"PASCAL":[125],"VOC":[126],"2012":[127],"MS":[129],"COCO":[130],"2014":[131],"demonstrate":[132],"CLIP-DyCAM":[134],"improves":[135],"mIoU":[136],"1.1%":[138],"1":[140],".3%":[141],"respectively":[142],"compared":[143],"showing":[146],"clear":[147],"advantages":[148],"handling":[150],"backgrounds.":[152]},"counts_by_year":[],"updated_date":"2026-04-02T13:53:19.096889","created_date":"2026-04-02T00:00:00"}