{"id":"https://openalex.org/W4415538295","doi":"https://doi.org/10.1145/3746027.3755706","title":"DiffuSeg: Diffusion-Enhanced Cross-Modal Semantic Segmentation for RGB-D","display_name":"DiffuSeg: Diffusion-Enhanced Cross-Modal Semantic Segmentation for RGB-D","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538295","doi":"https://doi.org/10.1145/3746027.3755706"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755706","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755706","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":"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/A5103205273","display_name":"Jun Yang","orcid":"https://orcid.org/0000-0002-2124-0869"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jun Yang","raw_affiliation_strings":["Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085971847","display_name":"Maoyu Mao","orcid":"https://orcid.org/0000-0002-4316-4385"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Maoyu Mao","raw_affiliation_strings":["Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103205273"],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.45623539,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2141","last_page":"2149"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9984999895095825,"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"}},"topics":[{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9984999895095825,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9951000213623047,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9926999807357788,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6585999727249146},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5896999835968018},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5830000042915344},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5134000182151794},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4740999937057495},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.454800009727478},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.4530999958515167},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.45239999890327454},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44769999384880066}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8007000088691711},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6675000190734863},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6585999727249146},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5896999835968018},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5830000042915344},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5134000182151794},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4740999937057495},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.454800009727478},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.4530999958515167},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.45239999890327454},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44769999384880066},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.4284000098705292},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.41839998960494995},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.38659998774528503},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3546999990940094},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.3521000146865845},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.3142000138759613},{"id":"https://openalex.org/C2778045648","wikidata":"https://www.wikidata.org/wiki/Q176827","display_name":"Markov random field","level":4,"score":0.30160000920295715},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2985000014305115},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2957000136375427},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755706","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755706","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W125693051","https://openalex.org/W1923184257","https://openalex.org/W2557465155","https://openalex.org/W2609822318","https://openalex.org/W2963896186","https://openalex.org/W3015871565","https://openalex.org/W3194841206","https://openalex.org/W3207537403","https://openalex.org/W4221152259","https://openalex.org/W4226014430","https://openalex.org/W4292829030","https://openalex.org/W4313142416","https://openalex.org/W4386057777","https://openalex.org/W4392931179","https://openalex.org/W4393154023","https://openalex.org/W4406572793"],"related_works":[],"abstract_inverted_index":{"Diffusion":[0],"models":[1],"have":[2],"recently":[3],"shown":[4],"strong":[5,178],"capabilities":[6],"in":[7,182],"image":[8],"generation.":[9],"This":[10,68],"paper":[11,69],"investigates":[12],"their":[13],"potential":[14],"for":[15,64],"semantic":[16,54,95,185],"segmentation,":[17],"with":[18,80],"a":[19,131,146],"focus":[20],"on":[21,172],"RGB-D":[22],"tasks":[23],"that":[24,47,137],"demand":[25],"precise":[26],"pixel-level":[27,161],"predictions.":[28],"In":[29],"particular,":[30],"we":[31,98],"delve":[32],"into":[33],"the":[34,39,53,89,100,150,165,177],"intermediate":[35],"activations":[36,49],"generated":[37,82],"during":[38],"reverse":[40],"Markov":[41],"step":[42],"of":[43,56,91,148,180],"diffusion":[44,86],"process,":[45],"discovering":[46],"these":[48],"can":[50],"effectively":[51],"capture":[52],"information":[55,158],"an":[57,84],"input":[58],"image,":[59],"making":[60],"them":[61],"outstanding":[62],"representations":[63],"addressing":[65],"segmentation":[66,186],"challenges.":[67],"proposes":[70],"Diffusion-Enhanced":[71],"Multi-Modal":[72],"Segmenter":[73],"(DiffuSeg),":[74],"which":[75,105],"innovatively":[76],"combines":[77],"RGB":[78,112],"features":[79,115],"those":[81],"by":[83,159],"additional":[85],"model,":[87],"facilitating":[88],"extraction":[90],"comprehensive":[92],"and":[93,113,140],"nuanced":[94],"features.":[96],"Furthermore,":[97],"propose":[99],"Cross":[101],"Attention-and-Aggregation":[102],"Module":[103,153],"(CAAM),":[104],"not":[106],"only":[107],"fosters":[108],"long-range":[109],"interactions":[110],"between":[111],"diffusion-derived":[114],"but":[116],"also":[117],"recalibrates":[118],"both":[119],"feature":[120,167],"sets":[121],"before":[122],"integration,":[123],"enhancing":[124,164],"multi-modal":[125],"synergy.":[126],"Additionally,":[127],"our":[128],"model":[129],"incorporates":[130],"Dynamic":[132],"Cascade":[133],"Kernel":[134],"(DCK)":[135],"architecture":[136],"exploits":[138],"local":[139],"intricate":[141],"multi-scale":[142],"geometric":[143],"details.":[144],"As":[145],"part":[147],"DCK,":[149],"Spatial":[151],"Interaction":[152],"(SIM)":[154],"dynamically":[155],"encodes":[156],"spatial":[157,166],"establishing":[160],"correlations,":[162],"thereby":[163],"representation":[168],"capacity.":[169],"Extensive":[170],"experiments":[171],"two":[173],"benchmark":[174],"datasets":[175],"demonstrate":[176],"capability":[179],"DiffuSeg":[181],"handling":[183],"challenging":[184],"tasks.":[187]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-25T00:00:00"}