{"id":"https://openalex.org/W4407692451","doi":"https://doi.org/10.1109/iceic64972.2025.10879619","title":"Focusing on Representation of Multi-head Attention for Open-Vocabulary Semantic Segmentation","display_name":"Focusing on Representation of Multi-head Attention for Open-Vocabulary Semantic Segmentation","publication_year":2025,"publication_date":"2025-01-19","ids":{"openalex":"https://openalex.org/W4407692451","doi":"https://doi.org/10.1109/iceic64972.2025.10879619"},"language":"en","primary_location":{"id":"doi:10.1109/iceic64972.2025.10879619","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iceic64972.2025.10879619","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Electronics, Information, and Communication (ICEIC)","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/A5017996855","display_name":"Dong Un Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Dong Un Kang","raw_affiliation_strings":["Seoul National University,Department of Electrical and Computer Engineering,Seoul,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Electrical and Computer Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052523460","display_name":"Se Young Chun","orcid":"https://orcid.org/0000-0001-8739-8960"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Se Young Chun","raw_affiliation_strings":["Seoul National University,Department of Electrical and Computer Engineering,Seoul,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Electrical and Computer Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5017996855"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":2.8599,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89525765,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.7523000240325928,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10028","display_name":"Topic Modeling","score":0.7523000240325928,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.7117999792098999,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T13243","display_name":"Innovation in Digital Healthcare Systems","score":0.6863999962806702,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.800140380859375},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.632747232913971},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6078891158103943},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5803836584091187},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.5442278385162354},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5304158329963684},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5253058075904846},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15141984820365906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.800140380859375},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.632747232913971},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6078891158103943},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5803836584091187},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.5442278385162354},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5304158329963684},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5253058075904846},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15141984820365906},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"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/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iceic64972.2025.10879619","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iceic64972.2025.10879619","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Electronics, Information, and Communication (ICEIC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2031489346","https://openalex.org/W2125215748","https://openalex.org/W2952122856","https://openalex.org/W4312960937","https://openalex.org/W4386075766","https://openalex.org/W4403759200","https://openalex.org/W6857257623"],"related_works":["https://openalex.org/W2349784553","https://openalex.org/W3022596247","https://openalex.org/W3097502728","https://openalex.org/W2601444686","https://openalex.org/W4307058054","https://openalex.org/W4292238148","https://openalex.org/W4323660495","https://openalex.org/W2385319785","https://openalex.org/W2900827440","https://openalex.org/W3167549738"],"abstract_inverted_index":{"With":[0],"the":[1,27,69,93,100,145,156],"advancement":[2],"of":[3,30,71,95,102,129,159],"large":[4],"vision-language":[5],"models,":[6],"impressive":[7],"results":[8],"have":[9,51],"been":[10,52],"achieved":[11],"in":[12,21,39,89,155],"open-vocabulary":[13,103],"tasks":[14],"that":[15,125],"require":[16],"strong":[17],"generalization":[18],"ability.":[19],"However,":[20,66],"pixel-level":[22],"dense":[23,45,77,135],"prediction":[24,78,136],"tasks,":[25],"recognizing":[26],"local":[28],"information":[29],"objects":[31],"remains":[32,79],"challenging.":[33],"This":[34],"is":[35,41,109],"because":[36],"query-key":[37],"multiplication":[38],"self-attention":[40,90],"not":[42],"well-suited":[43],"for":[44,111,134],"prediction.":[46],"Instead,":[47],"significant":[48,141],"performance":[49,101,142],"improvements":[50,143],"made":[53],"by":[54,150],"using":[55],"self-self":[56],"attention":[57,74,87,97,107,127,153],"among":[58],"queries,":[59],"keys,":[60],"and":[61,91,118,169],"values":[62],"(q-q,":[63],"k-k,":[64],"v-v).":[65],"research":[67],"on":[68,76,99],"impact":[70],"each":[72,96],"multi-head":[73,86],"mechanism":[75],"scarce.":[80],"In":[81],"this":[82],"paper,":[83],"we":[84,123,139],"decompose":[85],"(MHA)":[88],"investigate":[92],"effectiveness":[94],"head":[98,108],"semantic":[104],"segmentation.":[105],"Each":[106],"responsible":[110],"different":[112],"representations,":[113],"such":[114],"as":[115],"number,":[116],"shape,":[117],"color.":[119],"Through":[120],"our":[121],"research,":[122],"found":[124],"certain":[126],"heads":[128,154],"CLIP":[130],"are":[131],"more":[132],"suited":[133],"tasks.":[137],"Finally,":[138],"achieve":[140],"over":[144],"current":[146],"state-of-the-art":[147],"model,":[148],"SCLIP,":[149],"selecting":[151],"specific":[152],"last":[157],"layer":[158],"CLIP's":[160],"visual":[161],"encoder":[162],"across":[163],"three":[164],"benchmark":[165],"datasets:":[166],"VOC21,":[167],"Context60,":[168],"COCO-Object.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}