{"id":"https://openalex.org/W4389665503","doi":"https://doi.org/10.1109/iros55552.2023.10342467","title":"Semantic Scene Difference Detection in Daily Life Patroling by Mobile Robots Using Pre-Trained Large-Scale Vision-Language Model","display_name":"Semantic Scene Difference Detection in Daily Life Patroling by Mobile Robots Using Pre-Trained Large-Scale Vision-Language Model","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389665503","doi":"https://doi.org/10.1109/iros55552.2023.10342467"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10342467","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10342467","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/A5048932127","display_name":"Yoshiki Obinata","orcid":"https://orcid.org/0000-0003-1429-4401"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yoshiki Obinata","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano- Informatics,Tokyo,Japan,113\u20138656"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano- Informatics,Tokyo,Japan,113\u20138656","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087094940","display_name":"Kento Kawaharazuka","orcid":"https://orcid.org/0000-0002-7464-7187"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kento Kawaharazuka","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano- Informatics,Tokyo,Japan,113\u20138656"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano- Informatics,Tokyo,Japan,113\u20138656","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050690629","display_name":"Naoaki Kanazawa","orcid":"https://orcid.org/0009-0002-3527-3087"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoaki Kanazawa","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano- Informatics,Tokyo,Japan,113\u20138656"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano- Informatics,Tokyo,Japan,113\u20138656","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103222994","display_name":"Naoya Yamaguchi","orcid":"https://orcid.org/0000-0003-1790-1502"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoya Yamaguchi","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano- Informatics,Tokyo,Japan,113\u20138656"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano- Informatics,Tokyo,Japan,113\u20138656","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077740097","display_name":"Naoto Tsukamoto","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoto Tsukamoto","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano- Informatics,Tokyo,Japan,113\u20138656"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano- Informatics,Tokyo,Japan,113\u20138656","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028545634","display_name":"Iori Yanokura","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Iori Yanokura","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano- Informatics,Tokyo,Japan,113\u20138656"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano- Informatics,Tokyo,Japan,113\u20138656","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003800040","display_name":"Shingo Kitagawa","orcid":"https://orcid.org/0000-0001-5096-0702"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shingo Kitagawa","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano- Informatics,Tokyo,Japan,113\u20138656"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano- Informatics,Tokyo,Japan,113\u20138656","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020858329","display_name":"Koki Shinjo","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Koki Shinjo","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano- Informatics,Tokyo,Japan,113\u20138656"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano- Informatics,Tokyo,Japan,113\u20138656","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101836795","display_name":"Kei Okada","orcid":"https://orcid.org/0000-0001-6606-6692"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kei Okada","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano- Informatics,Tokyo,Japan,113\u20138656"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano- Informatics,Tokyo,Japan,113\u20138656","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047218430","display_name":"Masayuki Inaba","orcid":"https://orcid.org/0000-0003-1273-1567"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masayuki Inaba","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano- Informatics,Tokyo,Japan,113\u20138656"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano- Informatics,Tokyo,Japan,113\u20138656","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5048932127"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.9839,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.78594436,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3228","last_page":"3233"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994000196456909,"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":0.9994000196456909,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/computer-science","display_name":"Computer science","score":0.7940564155578613},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6678774356842041},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6236081123352051},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.5587328672409058},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5567742586135864},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.5174887180328369},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5083078742027283},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4819500148296356},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.47081881761550903},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44300615787506104},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.41503477096557617},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.41122931241989136},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37047669291496277},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.36603057384490967},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.26364773511886597}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7940564155578613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6678774356842041},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6236081123352051},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.5587328672409058},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5567742586135864},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.5174887180328369},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5083078742027283},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4819500148296356},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.47081881761550903},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44300615787506104},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.41503477096557617},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.41122931241989136},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37047669291496277},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.36603057384490967},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26364773511886597},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros55552.2023.10342467","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10342467","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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1933349210","https://openalex.org/W1959608418","https://openalex.org/W2007321142","https://openalex.org/W2193145675","https://openalex.org/W2896457183","https://openalex.org/W2963800628","https://openalex.org/W3016473712","https://openalex.org/W3096831136","https://openalex.org/W3106250896","https://openalex.org/W3216015240","https://openalex.org/W4282919422","https://openalex.org/W4283819124","https://openalex.org/W4288089799","https://openalex.org/W4292779060","https://openalex.org/W4312956471","https://openalex.org/W4383108296","https://openalex.org/W4383108320","https://openalex.org/W4385245566","https://openalex.org/W4390480939","https://openalex.org/W6637373629","https://openalex.org/W6640963894","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6756121852","https://openalex.org/W6769627184","https://openalex.org/W6776148200","https://openalex.org/W6778883912","https://openalex.org/W6791353385","https://openalex.org/W6811476558","https://openalex.org/W6839015040","https://openalex.org/W6839459284","https://openalex.org/W6839745749","https://openalex.org/W6850615942"],"related_works":["https://openalex.org/W3135697610","https://openalex.org/W2085033728","https://openalex.org/W4285411112","https://openalex.org/W2171299904","https://openalex.org/W1647606319","https://openalex.org/W2922442631","https://openalex.org/W4390494008","https://openalex.org/W2053596378","https://openalex.org/W2168523118","https://openalex.org/W2943623134"],"abstract_inverted_index":{"It":[0],"is":[1,121,127],"important":[2],"for":[3],"daily":[4,59,180],"life":[5,60,181],"support":[6],"robots":[7],"to":[8,34,53,81,89,129,150,172,176],"detect":[9,54,82],"changes":[10,56,84,132,177],"in":[11,23,57,100,109,133,154,178],"their":[12],"environment":[13,61,157,182],"and":[14,27,93,97,126],"perform":[15],"tasks.":[16],"In":[17,48,137,165],"the":[18,36,58,63,101,134,142,166,179],"field":[19],"of":[20,66,103,144],"anomaly":[21,110],"detection":[22],"computer":[24],"vision,":[25],"probabilistic":[26],"deep":[28,106],"learning":[29],"methods":[30,40,108],"have":[31],"been":[32],"used":[33],"calculate":[35,41],"image":[37,46,92,96],"distance.":[38],"These":[39],"distances":[42],"by":[43,85,124,147],"focusing":[44],"on":[45],"pixels.":[47],"contrast,":[49],"this":[50,112,145],"study":[51],"aims":[52],"semantic":[55,83,130],"using":[62,158],"current":[64,95],"development":[65],"large-scale":[67],"vision-language":[68],"models.":[69],"Using":[70],"its":[71],"Visual":[72],"Question":[73],"Answering":[74],"(VQA)":[75],"model,":[76],"we":[77,140],"propose":[78],"a":[79,90,94,151,155,159],"method":[80,113,146],"applying":[86,148],"multiple":[87],"questions":[88],"reference":[91],"obtaining":[98],"answers":[99],"form":[102],"sentences.":[104],"Unlike":[105],"learning-based":[107],"detection,":[111],"does":[114],"not":[115,122],"require":[116],"any":[117],"training":[118],"or":[119],"fine-tuning,":[120],"affected":[123],"noise,":[125],"sensitive":[128],"state":[131],"real":[135],"world.":[136],"our":[138],"experiments,":[139],"demonstrated":[141],"effectiveness":[143],"it":[149,168],"patrol":[152],"task":[153],"real-life":[156],"mobile":[160],"robot,":[161],"Fetch":[162],"Mobile":[163],"Manipulator.":[164],"future,":[167],"may":[169],"be":[170],"possible":[171],"add":[173],"explanatory":[174],"power":[175],"through":[183],"spoken":[184],"language.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
