{"id":"https://openalex.org/W4389666751","doi":"https://doi.org/10.1109/iros55552.2023.10341402","title":"Multimodal Diffusion Segmentation Model for Object Segmentation from Manipulation Instructions","display_name":"Multimodal Diffusion Segmentation Model for Object Segmentation from Manipulation Instructions","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389666751","doi":"https://doi.org/10.1109/iros55552.2023.10341402"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10341402","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10341402","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5091150900","display_name":"Yui Iioka","orcid":"https://orcid.org/0009-0002-1353-4549"},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yui Iioka","raw_affiliation_strings":["Keio University,Yokohama, Kanagawa,Japan,223-8522"],"affiliations":[{"raw_affiliation_string":"Keio University,Yokohama, Kanagawa,Japan,223-8522","institution_ids":["https://openalex.org/I203951103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045226559","display_name":"Yu Yoshida","orcid":null},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yu Yoshida","raw_affiliation_strings":["Keio University,Yokohama, Kanagawa,Japan,223-8522"],"affiliations":[{"raw_affiliation_string":"Keio University,Yokohama, Kanagawa,Japan,223-8522","institution_ids":["https://openalex.org/I203951103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022777199","display_name":"Yuiga Wada","orcid":"https://orcid.org/0000-0003-3804-4546"},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuiga Wada","raw_affiliation_strings":["Keio University,Yokohama, Kanagawa,Japan,223-8522"],"affiliations":[{"raw_affiliation_string":"Keio University,Yokohama, Kanagawa,Japan,223-8522","institution_ids":["https://openalex.org/I203951103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021832682","display_name":"Shumpei Hatanaka","orcid":"https://orcid.org/0009-0006-6338-3098"},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shumpei Hatanaka","raw_affiliation_strings":["Keio University,Yokohama, Kanagawa,Japan,223-8522"],"affiliations":[{"raw_affiliation_string":"Keio University,Yokohama, Kanagawa,Japan,223-8522","institution_ids":["https://openalex.org/I203951103"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033744547","display_name":"Komei Sugiura","orcid":"https://orcid.org/0000-0002-0261-0510"},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Komei Sugiura","raw_affiliation_strings":["Keio University,Yokohama, Kanagawa,Japan,223-8522"],"affiliations":[{"raw_affiliation_string":"Keio University,Yokohama, Kanagawa,Japan,223-8522","institution_ids":["https://openalex.org/I203951103"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5091150900"],"corresponding_institution_ids":["https://openalex.org/I203951103"],"apc_list":null,"apc_paid":null,"fwci":0.6149,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.70702385,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"7590","last_page":"7597"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9988999962806702,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9988999962806702,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9987999796867371,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.996399998664856,"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/segmentation","display_name":"Segmentation","score":0.7836127281188965},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6969625353813171},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6685754060745239},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6656622886657715},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5989629030227661},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5922908186912537},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.5881307125091553},{"id":"https://openalex.org/keywords/segmentation-based-object-categorization","display_name":"Segmentation-based object categorization","score":0.5054659843444824},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.48885577917099},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3627225160598755}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7836127281188965},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6969625353813171},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6685754060745239},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6656622886657715},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5989629030227661},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5922908186912537},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.5881307125091553},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.5054659843444824},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.48885577917099},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3627225160598755},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros55552.2023.10341402","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10341402","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8628264844","display_name":null,"funder_award_id":"20H04269/23H03478","funder_id":"https://openalex.org/F4320320212","funder_display_name":"Japan Society for the Promotion of Science London"}],"funders":[{"id":"https://openalex.org/F4320320212","display_name":"Japan Society for the Promotion of Science London","ror":"https://ror.org/02m7axw05"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W2064675550","https://openalex.org/W2251512949","https://openalex.org/W2302548814","https://openalex.org/W2489434015","https://openalex.org/W2896457183","https://openalex.org/W2907143950","https://openalex.org/W2947311533","https://openalex.org/W2953626316","https://openalex.org/W2962716343","https://openalex.org/W2963109634","https://openalex.org/W2964339842","https://openalex.org/W2997544875","https://openalex.org/W3014494055","https://openalex.org/W3034578524","https://openalex.org/W3035097537","https://openalex.org/W3036167779","https://openalex.org/W3093025045","https://openalex.org/W3094502228","https://openalex.org/W3112077297","https://openalex.org/W3138516171","https://openalex.org/W3158482044","https://openalex.org/W3159619744","https://openalex.org/W3166396011","https://openalex.org/W3171547673","https://openalex.org/W3193171560","https://openalex.org/W3196798710","https://openalex.org/W3206209177","https://openalex.org/W4200631575","https://openalex.org/W4221167437","https://openalex.org/W4225832925","https://openalex.org/W4225981824","https://openalex.org/W4281633595","https://openalex.org/W4307504011","https://openalex.org/W4312351765","https://openalex.org/W4312933868","https://openalex.org/W4386066126","https://openalex.org/W6637373629","https://openalex.org/W6743963275","https://openalex.org/W6755207826","https://openalex.org/W6779823529","https://openalex.org/W6784333009","https://openalex.org/W6791353385","https://openalex.org/W6794797104","https://openalex.org/W6795288823","https://openalex.org/W6797397777","https://openalex.org/W6805547681","https://openalex.org/W6839015040"],"related_works":["https://openalex.org/W3144569342","https://openalex.org/W2945274617","https://openalex.org/W1986655823","https://openalex.org/W2185902295","https://openalex.org/W2103507220","https://openalex.org/W2055202857","https://openalex.org/W2371519352","https://openalex.org/W4205800335","https://openalex.org/W2386644571","https://openalex.org/W2372421320"],"abstract_inverted_index":{"In":[0,106],"this":[1,107],"study,":[2],"we":[3,109,153],"aim":[4],"to":[5,17,26,145,188],"develop":[6],"a":[7,11,35,119,134,155,203],"model":[8],"that":[9,181,197],"comprehends":[10],"natural":[12],"language":[13],"instruction":[14],"(e.g.,":[15],"\u201cGo":[16],"the":[18,23,27,31,39,51,54,61,64,67,71,74,79,111,122,129,160,199],"living":[19],"room":[20],"and":[21,33,77,125,140,163],"get":[22],"nearest":[24],"pillow":[25],"radio":[28],"art":[29],"on":[30,93,159],"wall\u201d)":[32],"generates":[34,118],"segmentation":[36,83,95,190],"mask":[37,100,120],"for":[38,57,103],"target":[40,68,184],"everyday":[41],"object.":[42],"The":[43,192],"task":[44],"is":[45],"challenging":[46],"because":[47],"it":[48,127],"requires":[49],"(1)":[50],"understanding":[52],"of":[53,66,70,81,169,194,198,206],"referring":[55,173],"expressions":[56,174],"multiple":[58,75],"objects":[59],"in":[60,121,128,186],"instruction,":[62],"(2)":[63],"prediction":[65],"phrase":[69],"sentence":[72],"among":[73],"phrases,":[76],"(3)":[78],"generation":[80],"pixel-wise":[82,189],"masks":[84],"rather":[85],"than":[86],"bounding":[87],"boxes.":[88],"Studies":[89],"have":[90],"been":[91],"conducted":[92],"language-based":[94],"methods;":[96],"however,":[97],"they":[98],"sometimes":[99],"irrelevant":[101],"regions":[102],"complex":[104,172],"sentences.":[105],"paper,":[108],"propose":[110],"Multimodal":[112],"Diffusion":[113],"Segmentation":[114],"Model":[115],"(MDSM),":[116],"which":[117],"first":[123],"stage":[124],"refines":[126],"second":[130],"stage.":[131],"We":[132],"introduce":[133],"crossmodal":[135,147],"parallel":[136],"feature":[137,182],"extraction":[138],"mechanism":[139],"extend":[141],"diffusion":[142],"probabilistic":[143],"models":[144],"handle":[146],"features.":[148],"To":[149],"validate":[150],"our":[151],"model,":[152],"built":[154],"new":[156],"dataset":[157,167],"based":[158],"well-known":[161],"Matterport3D":[162],"REVERIE":[164],"datasets.":[165],"This":[166],"consists":[168],"instructions":[170],"with":[171],"accompanied":[175],"by":[176,202],"real":[177],"indoor":[178],"environmental":[179],"images":[180],"various":[183],"objects,":[185],"addition":[187],"masks.":[191],"performance":[193],"MDSM":[195],"surpassed":[196],"baseline":[200],"method":[201],"large":[204],"margin":[205],"+10.13":[207],"mean":[208],"IoU.":[209]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}