{"id":"https://openalex.org/W4383066545","doi":"https://doi.org/10.1109/icra48891.2023.10161403","title":"ANSEL Photobot: A Robot Event Photographer with Semantic Intelligence","display_name":"ANSEL Photobot: A Robot Event Photographer with Semantic Intelligence","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383066545","doi":"https://doi.org/10.1109/icra48891.2023.10161403"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10161403","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10161403","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","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/A5078746457","display_name":"Dmitriy Rivkin","orcid":"https://orcid.org/0000-0003-4136-4831"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Dmitriy Rivkin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","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":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082760890","display_name":"Nikhil Kakodkar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikhil Kakodkar","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109496264","display_name":"David Meger","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Meger","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","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":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058737924","display_name":"Michael Jenkin","orcid":"https://orcid.org/0000-0002-2969-0012"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Jenkin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100372152","display_name":"Xue Liu","orcid":"https://orcid.org/0000-0001-5252-3442"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xue Liu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5050008610","display_name":"Francois R. Hogan","orcid":"https://orcid.org/0000-0002-0749-7764"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Francois Hogan","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5078746457"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8597,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.75113656,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"8262","last_page":"8268"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998000264167786,"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":0.9983000159263611,"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":0.802210807800293},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.7259522676467896},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6410269737243652},{"id":"https://openalex.org/keywords/documentation","display_name":"Documentation","score":0.6024572253227234},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5968320369720459},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5439884066581726},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5102682113647461},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4476555287837982},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.44450661540031433},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40747660398483276},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14467832446098328}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.802210807800293},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.7259522676467896},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6410269737243652},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.6024572253227234},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5968320369720459},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5439884066581726},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5102682113647461},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4476555287837982},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.44450661540031433},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40747660398483276},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14467832446098328},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/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/icra48891.2023.10161403","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10161403","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2005327470","https://openalex.org/W2038325949","https://openalex.org/W2090744467","https://openalex.org/W2116262665","https://openalex.org/W2139009685","https://openalex.org/W2144628267","https://openalex.org/W2168359206","https://openalex.org/W2171398004","https://openalex.org/W2341528187","https://openalex.org/W2561620318","https://openalex.org/W2587004249","https://openalex.org/W2774384911","https://openalex.org/W2891189147","https://openalex.org/W2902616437","https://openalex.org/W2912253819","https://openalex.org/W2963508075","https://openalex.org/W2990071020","https://openalex.org/W3016201367","https://openalex.org/W3038694458","https://openalex.org/W3099932909","https://openalex.org/W3101998545","https://openalex.org/W3132585206","https://openalex.org/W3166396011","https://openalex.org/W4224308101","https://openalex.org/W4225323055","https://openalex.org/W4226399820","https://openalex.org/W4283363598","https://openalex.org/W4285069854","https://openalex.org/W4285428875","https://openalex.org/W4287107550","https://openalex.org/W4288089799","https://openalex.org/W4292779060","https://openalex.org/W4385245566","https://openalex.org/W6731856959","https://openalex.org/W6739901393","https://openalex.org/W6769627184","https://openalex.org/W6778883912","https://openalex.org/W6797265648"],"related_works":["https://openalex.org/W2618286804","https://openalex.org/W2329643025","https://openalex.org/W3131163342","https://openalex.org/W2166271660","https://openalex.org/W2092256833","https://openalex.org/W2142369114","https://openalex.org/W2002770077","https://openalex.org/W2361728394","https://openalex.org/W2352631095","https://openalex.org/W2408577762"],"abstract_inverted_index":{"Our":[0],"work":[1],"examines":[2],"the":[3,19,82,91,98,116],"way":[4],"in":[5,18,45,97],"which":[6],"large":[7],"language":[8,48],"models":[9],"can":[10],"be":[11],"used":[12],"for":[13],"robotic":[14],"planning":[15],"and":[16,50],"sampling":[17],"context":[20],"of":[21,38,58,70],"automated":[22],"photographic":[23],"documentation.":[24],"Specifically,":[25],"we":[26,61],"illustrate":[27],"how":[28],"to":[29,65,79,89,94,115],"produce":[30],"a":[31,55,67,77,87],"photo-taking":[32],"robot":[33],"with":[34],"an":[35,59,63],"exceptional":[36],"level":[37],"semantic":[39],"awareness":[40],"by":[41,106,118,124],"leveraging":[42],"recent":[43],"advances":[44],"general":[46],"purpose":[47],"(LM)":[49],"vision-language":[51],"(VLM)":[52],"models.":[53],"Given":[54],"high-level":[56],"description":[57],"event":[60,117],"use":[62,86],"LM":[64],"generate":[66],"natural-language":[68],"list":[69],"photo":[71,103],"descriptions":[72,96],"that":[73],"one":[74],"would":[75],"expect":[76],"photographer":[78],"capture":[80],"at":[81],"event.":[83],"We":[84],"then":[85],"VLM":[88],"identify":[90],"best":[92],"matches":[93],"these":[95],"robot's":[99],"video":[100],"stream.":[101],"The":[102],"portfolios":[104],"generated":[105,123],"our":[107],"method":[108],"are":[109],"consistently":[110],"rated":[111],"as":[112],"more":[113],"appropriate":[114],"human":[119],"evaluators":[120],"than":[121],"those":[122],"existing":[125],"methods.":[126]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}