{"id":"https://openalex.org/W4403791547","doi":"https://doi.org/10.1145/3664647.3681253","title":"PrimKD: Primary Modality Guided Multimodal Fusion for RGB-D Semantic Segmentation","display_name":"PrimKD: Primary Modality Guided Multimodal Fusion for RGB-D Semantic Segmentation","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791547","doi":"https://doi.org/10.1145/3664647.3681253"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681253","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681253","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3664647.3681253","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057198274","display_name":"Zhiwei Hao","orcid":"https://orcid.org/0000-0002-6237-7028"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwei Hao","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6237-7028","affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhongyu Xiao","orcid":"https://orcid.org/0009-0002-1313-4297"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongyu Xiao","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-1313-4297","affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039158745","display_name":"Yong Luo","orcid":"https://orcid.org/0000-0002-2296-6370"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Luo","raw_affiliation_strings":["Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-2296-6370","affiliations":[{"raw_affiliation_string":"Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016185815","display_name":"Jianyuan Guo","orcid":"https://orcid.org/0000-0002-2981-1953"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jianyuan Guo","raw_affiliation_strings":["The University of Sydney, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0002-2981-1953","affiliations":[{"raw_affiliation_string":"The University of Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100378697","display_name":"Jing Wang","orcid":"https://orcid.org/0000-0003-3653-7013"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Wang","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3653-7013","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042802004","display_name":"Li Shen","orcid":"https://orcid.org/0000-0001-5659-3464"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Shen","raw_affiliation_strings":["Sun Yat-Sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-5659-3464","affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020194895","display_name":"Han Hu","orcid":"https://orcid.org/0000-0001-7532-0496"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Hu","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7532-0496","affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1943","last_page":"1951"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"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":0.9962999820709229,"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/modality","display_name":"Modality (human\u2013computer interaction)","score":0.7267704010009766},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7178134322166443},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6040892004966736},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5240476131439209},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5190637707710266},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.4550841450691223},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4441390633583069},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3546314835548401},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.05023738741874695}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7267704010009766},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7178134322166443},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6040892004966736},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5240476131439209},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5190637707710266},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.4550841450691223},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4441390633583069},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3546314835548401},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.05023738741874695},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681253","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681253","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3664647.3681253","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681253","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1923184257","https://openalex.org/W2117539524","https://openalex.org/W2963140444","https://openalex.org/W2971014764","https://openalex.org/W3015871565","https://openalex.org/W3035333188","https://openalex.org/W3108601100","https://openalex.org/W3124434019","https://openalex.org/W3174008611","https://openalex.org/W3176459575","https://openalex.org/W3194841206","https://openalex.org/W4212774754","https://openalex.org/W4220849367","https://openalex.org/W4226426325","https://openalex.org/W4281483168","https://openalex.org/W4281571140","https://openalex.org/W4285205872","https://openalex.org/W4287101401","https://openalex.org/W4312372834","https://openalex.org/W4312610896","https://openalex.org/W4312685069","https://openalex.org/W4312950730","https://openalex.org/W4312980183","https://openalex.org/W4313142416","https://openalex.org/W4362496243","https://openalex.org/W4386179772","https://openalex.org/W6839053282"],"related_works":["https://openalex.org/W2385859805","https://openalex.org/W2530972254","https://openalex.org/W2374013449","https://openalex.org/W73545470","https://openalex.org/W2364381299","https://openalex.org/W2374430585","https://openalex.org/W3144423903","https://openalex.org/W2377397762","https://openalex.org/W2793967660","https://openalex.org/W2361654993"],"abstract_inverted_index":{"The":[0,209],"recent":[1],"advancements":[2],"in":[3,11,37,160],"cross-modal":[4],"transformers":[5],"have":[6],"demonstrated":[7],"their":[8],"superior":[9],"performance":[10],"RGB-D":[12],"segmentation":[13,55,162],"tasks":[14],"by":[15,204],"effectively":[16],"integrating":[17],"information":[18,66,130],"from":[19,131],"both":[20,123],"RGB":[21,60,95,108,124,134],"and":[22,43,125,147,174,177,194,206],"depth":[23,68,126,139],"modalities.":[24,127],"However,":[25],"existing":[26,202],"methods":[27],"often":[28],"overlook":[29],"the":[30,47,93,107,111,114,132,138,155,170,178,182],"varying":[31],"levels":[32],"of":[33,46,117,184,192],"informative":[34],"content":[35],"present":[36],"each":[38],"modality,":[39,140],"treating":[40],"them":[41],"equally":[42],"using":[44],"models":[45],"same":[48],"architecture.":[49],"This":[50,152],"oversight":[51],"can":[52],"potentially":[53],"hinder":[54],"performance,":[56],"especially":[57],"considering":[58],"that":[59,82,121],"images":[61],"typically":[62],"contain":[63],"significantly":[64],"more":[65],"than":[67],"images.":[69],"To":[70,128],"address":[71],"this":[72],"issue,":[73],"we":[74,100,141],"propose":[75],"PrimKD,":[76],"a":[77,102,118,148],"knowledge":[78],"distillation":[79],"based":[80],"approach":[81,188],"focuses":[83],"on":[84,91,106,169,196],"guided":[85],"multimodal":[86],"fusion,":[87,158],"with":[88],"an":[89],"emphasis":[90],"leveraging":[92,137],"primary":[94,133,143],"modality.":[96],"In":[97],"our":[98,166,187],"approach,":[99],"utilize":[101],"model":[103,120],"trained":[104],"exclusively":[105],"modality":[109,135],"as":[110],"teacher,":[112],"guiding":[113],"learning":[115],"process":[116],"student":[119],"fuses":[122],"prioritize":[129],"while":[136],"incorporate":[142],"focused":[144],"feature":[145],"reconstruction":[146],"selective":[149],"alignment":[150],"scheme.":[151],"integration":[153],"enhances":[154],"overall":[156],"freature":[157],"resulting":[159],"improved":[161],"results.":[163],"We":[164],"evaluate":[165],"proposed":[167],"method":[168],"NYU":[171],"Depth":[172],"V2":[173],"SUN-RGBD":[175],"datasets,":[176,199],"experimental":[179],"results":[180],"demonstrate":[181],"effectiveness":[183],"PrimKD.":[185],"Specifically,":[186],"achieves":[189],"mIoU":[190],"scores":[191],"57.8":[193],"52.5":[195],"these":[197],"two":[198],"respectively,":[200],"surpassing":[201],"counterparts":[203],"1.5":[205],"0.4":[207],"mIoU.":[208],"code":[210],"is":[211],"available":[212],"at":[213],"https://github.com/xiaoshideta/PrimKD.":[214]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}