{"id":"https://openalex.org/W3206198586","doi":"https://doi.org/10.1145/3474085.3475364","title":"Cross-modality Discrepant Interaction Network for RGB-D Salient Object Detection","display_name":"Cross-modality Discrepant Interaction Network for RGB-D Salient Object Detection","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3206198586","doi":"https://doi.org/10.1145/3474085.3475364","mag":"3206198586"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475364","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475364","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th 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/A5100374170","display_name":"Chen Zhang","orcid":"https://orcid.org/0000-0003-2068-7279"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chen Zhang","raw_affiliation_strings":["Beijing Jiaotong University & Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University & Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091558139","display_name":"Runmin Cong","orcid":"https://orcid.org/0000-0003-0972-4008"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runmin Cong","raw_affiliation_strings":["Beijing Jiaotong University & Beijing Key Laboratory of Advanced Information Science and Network Technology & City Univeristy of Hong Kong, Beijing, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University & Beijing Key Laboratory of Advanced Information Science and Network Technology & City Univeristy of Hong Kong, Beijing, Hong Kong, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040427384","display_name":"Qinwei Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinwei Lin","raw_affiliation_strings":["Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017116858","display_name":"Lin Ma","orcid":"https://orcid.org/0000-0002-7331-6132"},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Ma","raw_affiliation_strings":["Meituan, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Meituan, Beijing, China","institution_ids":["https://openalex.org/I4210087373"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110515489","display_name":"Feng Li","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Li","raw_affiliation_strings":["Beijing Jiaotong University & Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University & Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362745","display_name":"Yao Zhao","orcid":"https://orcid.org/0000-0002-8581-9554"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Zhao","raw_affiliation_strings":["Beijing Jiaotong University & Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University & Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008386708","display_name":"Sam Kwong","orcid":"https://orcid.org/0000-0001-7484-7261"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Sam Kwong","raw_affiliation_strings":["City Univeristy of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"City Univeristy of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100374170"],"corresponding_institution_ids":["https://openalex.org/I21193070"],"apc_list":null,"apc_paid":null,"fwci":8.1392,"has_fulltext":false,"cited_by_count":103,"citation_normalized_percentile":{"value":0.98325824,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2094","last_page":"2102"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":1.0,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":1.0,"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/T11094","display_name":"Face Recognition and Perception","score":0.9764000177383423,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9643999934196472,"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/rgb-color-model","display_name":"RGB color model","score":0.7453507781028748},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7016491889953613},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.696898877620697},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6475597023963928},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6098421216011047},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5797431468963623},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5696064829826355},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.49528446793556213},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.43600308895111084},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.430111825466156},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4104246497154236},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10255572199821472}],"concepts":[{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.7453507781028748},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7016491889953613},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.696898877620697},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6475597023963928},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6098421216011047},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5797431468963623},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5696064829826355},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49528446793556213},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.43600308895111084},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.430111825466156},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4104246497154236},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10255572199821472},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3474085.3475364","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475364","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G3549125173","display_name":null,"funder_award_id":"2020T130050,2019M660438","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G5432095370","display_name":null,"funder_award_id":"Z201100006820016","funder_id":"https://openalex.org/F4320334978","funder_display_name":"Beijing Nova Program"},{"id":"https://openalex.org/G5651167196","display_name":null,"funder_award_id":"62002014,U1936212","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320334978","display_name":"Beijing Nova Program","ror":"https://ror.org/034k14f91"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W20683899","https://openalex.org/W1565402342","https://openalex.org/W1772076007","https://openalex.org/W1901129140","https://openalex.org/W1976409045","https://openalex.org/W2039298799","https://openalex.org/W2108598243","https://openalex.org/W2337762808","https://openalex.org/W2461758788","https://openalex.org/W2752782242","https://openalex.org/W2766912043","https://openalex.org/W2767623212","https://openalex.org/W2793668851","https://openalex.org/W2884585870","https://openalex.org/W2887522866","https://openalex.org/W2909381593","https://openalex.org/W2943125866","https://openalex.org/W2948300571","https://openalex.org/W2955058313","https://openalex.org/W2957414648","https://openalex.org/W2963091558","https://openalex.org/W2963572583","https://openalex.org/W2963868681","https://openalex.org/W2967085153","https://openalex.org/W2969377765","https://openalex.org/W3002301267","https://openalex.org/W3006465601","https://openalex.org/W3022015146","https://openalex.org/W3034320133","https://openalex.org/W3035284915","https://openalex.org/W3035357085","https://openalex.org/W3035687312","https://openalex.org/W3092729213","https://openalex.org/W3097336090","https://openalex.org/W3097725659","https://openalex.org/W3102864715","https://openalex.org/W3104979525","https://openalex.org/W3105291825","https://openalex.org/W3108421143","https://openalex.org/W3108608656","https://openalex.org/W3108812909","https://openalex.org/W3108822985","https://openalex.org/W3108948422","https://openalex.org/W3120113457","https://openalex.org/W3155677196"],"related_works":["https://openalex.org/W2385859805","https://openalex.org/W2530972254","https://openalex.org/W4390516098","https://openalex.org/W2161474341","https://openalex.org/W2374013449","https://openalex.org/W4302615923","https://openalex.org/W2181948922","https://openalex.org/W73545470","https://openalex.org/W3203142394","https://openalex.org/W2351061015"],"abstract_inverted_index":{"The":[0],"popularity":[1],"and":[2,11,18,40,56,82,156,215],"promotion":[3],"of":[4,21,68,79,99,107,137,159],"depth":[5,41,57,63,139,160],"maps":[6],"have":[7,25],"brought":[8],"new":[9],"vigor":[10],"vitality":[12],"into":[13],"salient":[14],"object":[15,154],"detection":[16],"(SOD),":[17],"a":[19,84,174,182],"mass":[20],"RGB-D":[22,92],"SOD":[23],"algorithms":[24],"been":[26],"proposed,":[27],"mainly":[28],"concentrating":[29],"on":[30,201],"how":[31],"to":[32,103,117,133,162,190],"better":[33],"integrate":[34],"cross-modality":[35,45,121],"features":[36,140,161,189],"from":[37,73],"RGB":[38,55,70,131,164],"image":[39],"map.":[42],"For":[43],"the":[44,69,77,97,104,119,124,135,138,146,153,163,192,196],"interaction":[46],"in":[47,141,166,195],"feature":[48,105,197],"encoder,":[49],"existing":[50],"methods":[51,212],"either":[52],"indiscriminately":[53],"treat":[54],"modalities,":[58],"or":[59],"only":[60],"habitually":[61],"utilize":[62],"cues":[64],"as":[65],"auxiliary":[66],"information":[67],"branch.":[71],"Different":[72],"them,":[74],"we":[75,171],"reconsider":[76],"status":[78],"two":[80,100,113],"modalities":[81,101],"propose":[83],"novel":[85],"Cross-modality":[86],"Discrepant":[87],"Interaction":[88],"Network":[89],"(CDINet)":[90],"for":[91],"SOD,":[93],"which":[94,180],"differentially":[95],"models":[96],"dependence":[98],"according":[102],"representations":[106],"different":[108],"layers.":[109],"To":[110],"this":[111],"end,":[112],"components":[114],"are":[115],"designed":[116],"implement":[118],"effective":[120],"interaction:":[122],"1)":[123],"RGB-induced":[125],"Detail":[126],"Enhancement":[127,149],"(RDE)":[128],"module":[129,151],"leverages":[130],"modality":[132],"enhance":[134],"details":[136],"low-level":[142],"encoder":[143,168,188],"stage.":[144,169],"2)":[145],"Depth-induced":[147],"Semantic":[148],"(DSE)":[150],"transfers":[152],"positioning":[155],"internal":[157],"consistency":[158],"branch":[165],"high-level":[167],"Furthermore,":[170],"also":[172],"design":[173],"Dense":[175],"Decoding":[176],"Reconstruction":[177],"(DDR)":[178],"structure,":[179],"constructs":[181],"semantic":[183],"block":[184],"by":[185],"combining":[186],"multi-level":[187],"upgrade":[191],"skip":[193],"connection":[194],"decoding.":[198],"Extensive":[199],"experiments":[200],"five":[202],"benchmark":[203],"datasets":[204],"demonstrate":[205],"that":[206],"our":[207],"network":[208],"outperforms":[209],"$15$":[210],"state-of-the-art":[211],"both":[213],"quantitatively":[214],"qualitatively.":[216],"Our":[217],"code":[218],"is":[219],"publicly":[220],"available":[221],"at:https://rmcong.github.io/proj_CDINet.html.":[222]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":24},{"year":2023,"cited_by_count":35},{"year":2022,"cited_by_count":25}],"updated_date":"2026-03-22T08:09:32.410652","created_date":"2025-10-10T00:00:00"}