{"id":"https://openalex.org/W4308235695","doi":"https://doi.org/10.1109/icip46576.2022.9898069","title":"Multi-Modal Transformer for RGB-D Salient Object Detection","display_name":"Multi-Modal Transformer for RGB-D Salient Object Detection","publication_year":2022,"publication_date":"2022-10-16","ids":{"openalex":"https://openalex.org/W4308235695","doi":"https://doi.org/10.1109/icip46576.2022.9898069"},"language":"en","primary_location":{"id":"doi:10.1109/icip46576.2022.9898069","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9898069","pdf_url":null,"source":{"id":"https://openalex.org/S4363607719","display_name":"2022 IEEE International Conference on Image Processing (ICIP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Image Processing (ICIP)","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/A5015177224","display_name":"Peipei Song","orcid":"https://orcid.org/0000-0001-6764-3375"},"institutions":[{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"funder","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Peipei Song","raw_affiliation_strings":["Data61/CSIRO,Canberra,Australia,2601","Australian National University, Canberra, Australia"],"affiliations":[{"raw_affiliation_string":"Data61/CSIRO,Canberra,Australia,2601","institution_ids":["https://openalex.org/I42894916","https://openalex.org/I1292875679"]},{"raw_affiliation_string":"Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100630815","display_name":"Jing Zhang","orcid":"https://orcid.org/0000-0002-8516-0913"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jing Zhang","raw_affiliation_strings":["Australian National University,Canberra,Australia,2601"],"affiliations":[{"raw_affiliation_string":"Australian National University,Canberra,Australia,2601","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002212263","display_name":"Piotr Koniusz","orcid":"https://orcid.org/0000-0002-6340-5289"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]},{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"funder","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Piotr Koniusz","raw_affiliation_strings":["Data61/CSIRO,Canberra,Australia,2601","Australian National University, Canberra, Australia"],"affiliations":[{"raw_affiliation_string":"Data61/CSIRO,Canberra,Australia,2601","institution_ids":["https://openalex.org/I42894916","https://openalex.org/I1292875679"]},{"raw_affiliation_string":"Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072837153","display_name":"Nick Barnes","orcid":"https://orcid.org/0000-0002-9343-9535"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Nick Barnes","raw_affiliation_strings":["Australian National University,Canberra,Australia,2601"],"affiliations":[{"raw_affiliation_string":"Australian National University,Canberra,Australia,2601","institution_ids":["https://openalex.org/I118347636"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5015177224"],"corresponding_institution_ids":["https://openalex.org/I118347636","https://openalex.org/I1292875679","https://openalex.org/I42894916"],"apc_list":null,"apc_paid":null,"fwci":0.4797,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.73320975,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2466","last_page":"2470"},"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":0.9865999817848206,"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/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9782999753952026,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.7406972646713257},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.716559648513794},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6536776423454285},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6130051016807556},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5652425289154053},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.5593346953392029},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5321133732795715},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5081415176391602},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4808993339538574},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4709927439689636},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16550815105438232},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.12367609143257141}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7406972646713257},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.716559648513794},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6536776423454285},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6130051016807556},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5652425289154053},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.5593346953392029},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5321133732795715},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5081415176391602},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4808993339538574},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4709927439689636},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16550815105438232},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.12367609143257141},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip46576.2022.9898069","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9898069","pdf_url":null,"source":{"id":"https://openalex.org/S4363607719","display_name":"2022 IEEE International Conference on Image Processing (ICIP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Image Processing (ICIP)","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":33,"referenced_works":["https://openalex.org/W20683899","https://openalex.org/W1966025376","https://openalex.org/W1976409045","https://openalex.org/W1993713494","https://openalex.org/W2039298799","https://openalex.org/W2520640394","https://openalex.org/W2765838470","https://openalex.org/W2798857366","https://openalex.org/W2887522866","https://openalex.org/W2907643346","https://openalex.org/W2909381593","https://openalex.org/W2948300571","https://openalex.org/W2957414648","https://openalex.org/W2963529609","https://openalex.org/W2963868681","https://openalex.org/W3002301267","https://openalex.org/W3035357085","https://openalex.org/W3035633116","https://openalex.org/W3094502228","https://openalex.org/W3097053213","https://openalex.org/W3114152269","https://openalex.org/W3138516171","https://openalex.org/W3172863135","https://openalex.org/W3177040887","https://openalex.org/W3207668590","https://openalex.org/W3216049821","https://openalex.org/W4214520160","https://openalex.org/W4214561053","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6784333009","https://openalex.org/W6804931533","https://openalex.org/W6881026719"],"related_works":["https://openalex.org/W2329500892","https://openalex.org/W28991112","https://openalex.org/W2370726991","https://openalex.org/W2369710579","https://openalex.org/W2545348020","https://openalex.org/W4327728159","https://openalex.org/W2912751582","https://openalex.org/W2130893381","https://openalex.org/W1990856605","https://openalex.org/W3120436346"],"abstract_inverted_index":{"The":[0],"main":[1],"focus":[2],"of":[3,21,57,104],"existing":[4],"RGB-D":[5,70,96],"salient":[6,71,97],"object":[7,72,98],"detection":[8,99],"models":[9],"is":[10,80],"achieving":[11],"effective":[12],"multi-modal":[13,28,66,77],"fusion.":[14],"Due":[15],"to":[16,32,82],"the":[17,35,38,44,51,55,102],"limited":[18],"receptive":[19],"field":[20],"conventional":[22],"convolutional":[23],"neural":[24],"networks":[25,59,68],"(CNNs),":[26],"CNN-based":[27],"fusion":[29,78],"strategies":[30],"fail":[31],"extensively":[33],"model":[34],"correlation":[36],"between":[37],"two":[39],"modalities":[40],"(appearance":[41],"information":[42,49],"from":[43,50],"RGB":[45],"image":[46],"and":[47,87],"geometric":[48,88],"depth":[52],"data).":[53],"Given":[54],"success":[56],"transformer":[58,67],"for":[60,69],"long-range":[61],"dependency":[62],"modeling,":[63],"we":[64],"investigate":[65],"detection.":[73],"Specifically,":[74],"a":[75],"transformer-based":[76],"module":[79],"presented":[81],"effectively":[83],"fuse":[84],"appearance":[85],"features":[86],"features.":[89],"Experimental":[90],"results":[91],"on":[92],"six":[93],"challenging":[94],"benchmark":[95],"datasets":[100],"demonstrate":[101],"effectiveness":[103],"our":[105],"approach.":[106]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}