{"id":"https://openalex.org/W4405786372","doi":"https://doi.org/10.1109/iros58592.2024.10801790","title":"PhotoBot: Reference-Guided Interactive Photography via Natural Language","display_name":"PhotoBot: Reference-Guided Interactive Photography via Natural Language","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405786372","doi":"https://doi.org/10.1109/iros58592.2024.10801790"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10801790","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801790","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5082379912","display_name":"Oliver Limoyo","orcid":"https://orcid.org/0000-0001-6886-2633"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oliver Limoyo","raw_affiliation_strings":["Samsung AI Centre,Montr&#x00E9;al,Canada,H3A 3G4"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung AI Centre,Montr&#x00E9;al,Canada,H3A 3G4","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103241142","display_name":"Jimmy Li","orcid":"https://orcid.org/0000-0003-1090-7004"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jimmy Li","raw_affiliation_strings":["Samsung AI Centre,Montr&#x00E9;al,Canada,H3A 3G4"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung AI Centre,Montr&#x00E9;al,Canada,H3A 3G4","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078746457","display_name":"Dmitriy Rivkin","orcid":"https://orcid.org/0000-0003-4136-4831"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dmitriy Rivkin","raw_affiliation_strings":["Samsung AI Centre,Montr&#x00E9;al,Canada,H3A 3G4"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung AI Centre,Montr&#x00E9;al,Canada,H3A 3G4","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001210516","display_name":"Jonathan Kelly","orcid":"https://orcid.org/0000-0002-5528-6136"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jonathan Kelly","raw_affiliation_strings":["University of Toronto Institute for Aerospace Studies,STARS Laboratory,Toronto,Canada,M5S 1A4"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto Institute for Aerospace Studies,STARS Laboratory,Toronto,Canada,M5S 1A4","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075441381","display_name":"Gregory Dudek","orcid":"https://orcid.org/0000-0001-5040-4925"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gregory Dudek","raw_affiliation_strings":["Samsung AI Centre,Montr&#x00E9;al,Canada,H3A 3G4"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung AI Centre,Montr&#x00E9;al,Canada,H3A 3G4","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5259,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.7241666,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2479","last_page":"2486"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9739999771118164,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9739999771118164,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9684000015258789,"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/T11439","display_name":"Video Analysis and Summarization","score":0.96670001745224,"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/computer-science","display_name":"Computer science","score":0.7281544208526611},{"id":"https://openalex.org/keywords/photography","display_name":"Photography","score":0.6818037629127502},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.5958775281906128},{"id":"https://openalex.org/keywords/computational-photography","display_name":"Computational photography","score":0.5006754398345947},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4732699394226074},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.38782256841659546},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34224170446395874},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3292185962200165},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.17408040165901184},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.14055922627449036},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10937309265136719},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.10844963788986206},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.0866757333278656},{"id":"https://openalex.org/keywords/archaeology","display_name":"Archaeology","score":0.07620090246200562}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7281544208526611},{"id":"https://openalex.org/C119657128","wikidata":"https://www.wikidata.org/wiki/Q11633","display_name":"Photography","level":2,"score":0.6818037629127502},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.5958775281906128},{"id":"https://openalex.org/C146044194","wikidata":"https://www.wikidata.org/wiki/Q5157334","display_name":"Computational photography","level":4,"score":0.5006754398345947},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4732699394226074},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.38782256841659546},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34224170446395874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3292185962200165},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.17408040165901184},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.14055922627449036},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10937309265136719},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.10844963788986206},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.0866757333278656},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.07620090246200562}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10801790","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801790","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1511924373","https://openalex.org/W1970381346","https://openalex.org/W1991544872","https://openalex.org/W2005327470","https://openalex.org/W2018123352","https://openalex.org/W2046434485","https://openalex.org/W2050923626","https://openalex.org/W2078807908","https://openalex.org/W2085261163","https://openalex.org/W2102747584","https://openalex.org/W2140499715","https://openalex.org/W2151103935","https://openalex.org/W2171398004","https://openalex.org/W2899294986","https://openalex.org/W2964306141","https://openalex.org/W2970641574","https://openalex.org/W3034373437","https://openalex.org/W3132585206","https://openalex.org/W3159481202","https://openalex.org/W3200033334","https://openalex.org/W4312424618","https://openalex.org/W4323571866","https://openalex.org/W4383066545","https://openalex.org/W4390099597","https://openalex.org/W6631353684","https://openalex.org/W6684727228","https://openalex.org/W6774312191","https://openalex.org/W6799626271","https://openalex.org/W6811470611","https://openalex.org/W6853116092"],"related_works":["https://openalex.org/W2361248577","https://openalex.org/W3010334531","https://openalex.org/W2804670141","https://openalex.org/W2994735104","https://openalex.org/W2027349390","https://openalex.org/W1983639621","https://openalex.org/W2188751381","https://openalex.org/W1988828630","https://openalex.org/W1997064583","https://openalex.org/W2802215956"],"abstract_inverted_index":{"We":[0,23,42,127,164],"introduce":[1],"PhotoBot,":[2],"a":[3,20,39,44,64,76,97,123,132,136],"framework":[4],"for":[5,117],"fully":[6],"automated":[7],"photo":[8],"acquisition":[9],"based":[10,74],"on":[11,75],"an":[12,50,118],"interplay":[13],"between":[14],"high-level":[15],"human":[16,162],"language":[17,46,66,78],"guidance":[18],"and":[19,49,61,88],"robot":[21],"photographer.":[22],"propose":[24],"to":[25,29,53,69,171],"communicate":[26],"photography":[27],"suggestions":[28],"the":[30,55,85,89],"user":[31,140],"via":[32,58],"reference":[33,56,72,86,173],"images":[34,57,73],"that":[35,143,167],"are":[36,148],"selected":[37],"from":[38,96],"curated":[40],"gallery.":[41],"leverage":[43],"visual":[45],"model":[47,67],"(VLM)":[48],"object":[51],"detector":[52],"characterize":[54],"textual":[59],"descriptions":[60],"then":[62],"use":[63],"large":[65],"(LLM)":[68],"retrieve":[70],"relevant":[71],"user\u2019s":[77],"query":[79],"through":[80],"text-based":[81],"reasoning.":[82],"To":[83],"correspond":[84],"image":[87],"observed":[90],"scene,":[91],"we":[92,112],"exploit":[93],"pretrained":[94],"features":[95],"vision":[98],"transformer":[99],"capable":[100],"of":[101],"capturing":[102],"semantic":[103],"similarity":[104],"across":[105],"marked":[106],"appearance":[107],"variations.":[108],"Using":[109],"these":[110],"features,":[111],"compute":[113],"suggested":[114],"pose":[115],"adjustments":[116],"RGB-D":[119],"camera":[120],"by":[121,146,156,161],"solving":[122],"perspective-n-point":[124],"(PnP)":[125],"problem.":[126],"demonstrate":[128],"our":[129],"approach":[130],"using":[131],"manipulator":[133],"equipped":[134],"with":[135],"wrist":[137],"camera.":[138],"Our":[139],"studies":[141],"show":[142,166],"photos":[144],"taken":[145,155],"PhotoBot":[147,168],"often":[149],"more":[150],"aesthetically":[151],"pleasing":[152],"than":[153],"those":[154],"users":[157],"themselves,":[158],"as":[159,176],"measured":[160],"feedback.":[163],"also":[165],"can":[169],"generalize":[170],"other":[172],"sources":[174],"such":[175],"paintings.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
