{"id":"https://openalex.org/W4390190345","doi":"https://doi.org/10.1109/iccvw60793.2023.00200","title":"Open Scene Understanding: Grounded Situation Recognition Meets Segment Anything for Helping People with Visual Impairments","display_name":"Open Scene Understanding: Grounded Situation Recognition Meets Segment Anything for Helping People with Visual Impairments","publication_year":2023,"publication_date":"2023-10-02","ids":{"openalex":"https://openalex.org/W4390190345","doi":"https://doi.org/10.1109/iccvw60793.2023.00200"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw60793.2023.00200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://arxiv.org/pdf/2307.07757","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100767253","display_name":"Ruiping Liu","orcid":"https://orcid.org/0000-0001-8591-7712"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"funder","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ruiping Liu","raw_affiliation_strings":["Karlsruhe Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100453768","display_name":"Jiaming Zhang","orcid":"https://orcid.org/0000-0001-9146-0501"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"funder","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jiaming Zhang","raw_affiliation_strings":["Karlsruhe Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017521271","display_name":"Kunyu Peng","orcid":"https://orcid.org/0000-0002-5419-9292"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"funder","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kunyu Peng","raw_affiliation_strings":["Karlsruhe Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036575484","display_name":"Junwei Zheng","orcid":"https://orcid.org/0000-0003-1943-3239"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"funder","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Junwei Zheng","raw_affiliation_strings":["Karlsruhe Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101875568","display_name":"Ke Cao","orcid":"https://orcid.org/0009-0000-4421-0817"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"funder","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ke Cao","raw_affiliation_strings":["Karlsruhe Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100628855","display_name":"Yufan Chen","orcid":"https://orcid.org/0009-0006-5317-8867"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"funder","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yufan Chen","raw_affiliation_strings":["Karlsruhe Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027010844","display_name":"Kailun Yang","orcid":"https://orcid.org/0000-0002-1090-667X"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"funder","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kailun Yang","raw_affiliation_strings":["Hunan University"],"affiliations":[{"raw_affiliation_string":"Hunan University","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087051920","display_name":"Rainer Stiefelhagen","orcid":"https://orcid.org/0000-0001-8046-4945"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"funder","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Rainer Stiefelhagen","raw_affiliation_strings":["Karlsruhe Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology","institution_ids":["https://openalex.org/I102335020"]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.781,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.440506,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1849","last_page":"1859"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9976,"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":0.9976,"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/T10914","display_name":"Tactile and Sensory Interactions","score":0.9954,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9935,"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":[],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.816911},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5784363},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5718602},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.53395665},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.49878836},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4619821},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4510906},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.43112174},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42403695},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.41668725},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw60793.2023.00200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.07757","pdf_url":"http://arxiv.org/pdf/2307.07757","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.07757","pdf_url":"http://arxiv.org/pdf/2307.07757","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.47}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":64,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2043787485","https://openalex.org/W2108598243","https://openalex.org/W2171295735","https://openalex.org/W2194775991","https://openalex.org/W2423576022","https://openalex.org/W2506483933","https://openalex.org/W2899663614","https://openalex.org/W2946653762","https://openalex.org/W2948647700","https://openalex.org/W2963346996","https://openalex.org/W2995958891","https://openalex.org/W3024046433","https://openalex.org/W3034475678","https://openalex.org/W3096609285","https://openalex.org/W3096682293","https://openalex.org/W3097499499","https://openalex.org/W3110437118","https://openalex.org/W3123306064","https://openalex.org/W3131500599","https://openalex.org/W3131718527","https://openalex.org/W3138516171","https://openalex.org/W3162178300","https://openalex.org/W3163250643","https://openalex.org/W3169865585","https://openalex.org/W3170841864","https://openalex.org/W3174090708","https://openalex.org/W3174288891","https://openalex.org/W3180901291","https://openalex.org/W3194740919","https://openalex.org/W3207649350","https://openalex.org/W3212750552","https://openalex.org/W3217258974","https://openalex.org/W4200630531","https://openalex.org/W4210505756","https://openalex.org/W4210667216","https://openalex.org/W4213168938","https://openalex.org/W4214893857","https://openalex.org/W4225487034","https://openalex.org/W4226376247","https://openalex.org/W4229451441","https://openalex.org/W4289600407","https://openalex.org/W4292433237","https://openalex.org/W4293680532","https://openalex.org/W4306804417","https://openalex.org/W4307535372","https://openalex.org/W4308237312","https://openalex.org/W4312368691","https://openalex.org/W4312426743","https://openalex.org/W4312671791","https://openalex.org/W4312747482","https://openalex.org/W4312900708","https://openalex.org/W4312980231","https://openalex.org/W4318718936","https://openalex.org/W4319653855","https://openalex.org/W4367721677","https://openalex.org/W4382322597","https://openalex.org/W4383198112","https://openalex.org/W4386065432","https://openalex.org/W4386075561","https://openalex.org/W4390874575","https://openalex.org/W4394625604","https://openalex.org/W4401415649","https://openalex.org/W4404612908"],"related_works":["https://openalex.org/W4388145910","https://openalex.org/W4248336175","https://openalex.org/W3009369890","https://openalex.org/W28991112","https://openalex.org/W2391445434","https://openalex.org/W2381570729","https://openalex.org/W2366107444","https://openalex.org/W2329500892","https://openalex.org/W2031260042","https://openalex.org/W1976205134"],"abstract_inverted_index":{"Grounded":[0],"Situation":[1],"Recognition":[2],"(GSR)":[3],"is":[4,53],"capable":[5],"of":[6,37,50,85,89,100,138,203],"recognizing":[7],"and":[8,21,61,117,184,198],"interpreting":[9],"visual":[10,43,206],"scenes":[11],"in":[12,27,39],"a":[13,129],"contextually":[14],"intuitive":[15],"way,":[16],"yielding":[17],"salient":[18],"activities":[19],"(verbs)":[20],"the":[22,35,66,114,120,136,144,149,153,160,172,187,200],"involved":[23,86],"entities":[24,87],"(roles)":[25],"depicted":[26],"images.":[28],"In":[29,140,163],"this":[30],"work,":[31],"we":[32,69,93,123,146],"focus":[33],"on":[34,98,171,179],"application":[36,185],"GSR":[38,101,154],"assisting":[40],"people":[41,204],"with":[42,156,205],"impairments":[44],"(PVI).":[45],"However,":[46],"precise":[47],"localization":[48],"information":[49],"detected":[51],"objects":[52],"often":[54],"required":[55],"to":[56,79,112,134,142,194],"navigate":[57],"their":[58],"surroundings":[59],"confidently":[60],"make":[62],"informed":[63],"decisions.":[64],"For":[65],"first":[67],"time,":[68],"propose":[70],"an":[71,105],"Open":[72],"Scene":[73],"Understanding":[74],"(OpenSU)":[75],"system":[76,97,127,190],"that":[77],"aims":[78],"generate":[80],"pixelwise":[81],"dense":[82],"segmentation":[83],"masks":[84],"instead":[88],"bounding":[90],"boxes.":[91],"Specifically,":[92],"build":[94],"our":[95,125,166],"OpenSU":[96,126,189],"top":[99],"by":[102],"additionally":[103],"adopting":[104],"efficient":[106],"Segment":[107],"Anything":[108],"Model":[109],"(SAM).":[110],"Furthermore,":[111],"enhance":[113,195],"feature":[115],"extraction":[116],"interaction":[118],"between":[119],"encoder-decoder":[121],"structure,":[122],"construct":[124],"using":[128],"solid":[130],"pure":[131],"transformer":[132],"backbone":[133],"improve":[135],"performance":[137,170],"GSR.":[139],"order":[141],"accelerate":[143],"convergence,":[145],"replace":[147],"all":[148],"activation":[150],"functions":[151],"within":[152],"decoders":[155],"GELU,":[157],"thereby":[158],"reducing":[159],"training":[161],"duration.":[162],"quantitative":[164],"analysis,":[165],"model":[167],"achieves":[168],"state-of-the-art":[169],"SWiG":[173],"dataset.":[174],"Moreover,":[175],"through":[176],"field":[177],"testing":[178],"dedicated":[180],"assistive":[181],"technology":[182],"datasets":[183],"demonstrations,":[186],"proposed":[188],"can":[191],"be":[192,211],"used":[193],"scene":[196],"understanding":[197],"facilitate":[199],"independent":[201],"mobility":[202],"impairments.":[207],"Our":[208],"code":[209],"will":[210],"available":[212],"at":[213],"OpenSU.":[214]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4390190345","counts_by_year":[{"year":2024,"cited_by_count":8}],"updated_date":"2025-04-22T06:22:08.123368","created_date":"2023-12-26"}