{"id":"https://openalex.org/W3109302927","doi":"https://doi.org/10.1109/icra48506.2021.9560745","title":"Batteries, camera, action! Learning a semantic control space for expressive robot cinematography","display_name":"Batteries, camera, action! Learning a semantic control space for expressive robot cinematography","publication_year":2021,"publication_date":"2021-05-30","ids":{"openalex":"https://openalex.org/W3109302927","doi":"https://doi.org/10.1109/icra48506.2021.9560745","mag":"3109302927"},"language":"en","primary_location":{"id":"doi:10.1109/icra48506.2021.9560745","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9560745","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2011.10118","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062522127","display_name":"Rogerio Bonatti","orcid":"https://orcid.org/0000-0003-3015-9613"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["IL","US"],"is_corresponding":true,"raw_author_name":"Rogerio Bonatti","raw_affiliation_strings":["Carnegie Mellon University","Facebook AI Research","Facebook AI Research#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Facebook AI Research#TAB#","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089730590","display_name":"Arthur Bucker","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arthur Bucker","raw_affiliation_strings":["University of S\u00e3o Paulo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of S\u00e3o Paulo","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032584934","display_name":"Sebastian Scherer","orcid":"https://orcid.org/0000-0002-8373-4688"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sebastian Scherer","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014515988","display_name":"Mustafa Mukadam","orcid":"https://orcid.org/0000-0002-5683-1642"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Mustafa Mukadam","raw_affiliation_strings":["Facebook AI Research","Facebook AI Research#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Facebook AI Research#TAB#","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011498939","display_name":"Jessica K. Hodgins","orcid":"https://orcid.org/0000-0002-1778-883X"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Jessica Hodgins","raw_affiliation_strings":["Facebook AI Research","Facebook AI Research#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Facebook AI Research#TAB#","institution_ids":["https://openalex.org/I2252078561"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5062522127"],"corresponding_institution_ids":["https://openalex.org/I2252078561","https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.0971,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.34238674,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"7302","last_page":"7308"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9997000098228455,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9997000098228455,"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":0.9986000061035156,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9979000091552734,"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":0.8107035160064697},{"id":"https://openalex.org/keywords/viewpoints","display_name":"Viewpoints","score":0.603558361530304},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5840001106262207},{"id":"https://openalex.org/keywords/cinematography","display_name":"Cinematography","score":0.5734120011329651},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5251443386077881},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5232669115066528},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4625259041786194},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4357702136039734},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4295850098133087},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4157227873802185},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3783341646194458}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8107035160064697},{"id":"https://openalex.org/C2776035091","wikidata":"https://www.wikidata.org/wiki/Q7928819","display_name":"Viewpoints","level":2,"score":0.603558361530304},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5840001106262207},{"id":"https://openalex.org/C100991257","wikidata":"https://www.wikidata.org/wiki/Q590870","display_name":"Cinematography","level":2,"score":0.5734120011329651},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5251443386077881},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5232669115066528},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4625259041786194},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4357702136039734},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4295850098133087},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4157227873802185},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3783341646194458},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icra48506.2021.9560745","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9560745","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2011.10118","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.10118","pdf_url":"https://arxiv.org/pdf/2011.10118","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":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":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3109302927","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2011.10118","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":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":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2011.10118","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.10118","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":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":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2011.10118","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.10118","pdf_url":"https://arxiv.org/pdf/2011.10118","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":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":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3109302927.pdf","grobid_xml":"https://content.openalex.org/works/W3109302927.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W1597864774","https://openalex.org/W1985351089","https://openalex.org/W2003856922","https://openalex.org/W2024236092","https://openalex.org/W2043181832","https://openalex.org/W2044807399","https://openalex.org/W2062400178","https://openalex.org/W2069703923","https://openalex.org/W2083366168","https://openalex.org/W2114025269","https://openalex.org/W2116705992","https://openalex.org/W2122594606","https://openalex.org/W2135046866","https://openalex.org/W2136249537","https://openalex.org/W2145598468","https://openalex.org/W2149628368","https://openalex.org/W2152825437","https://openalex.org/W2153975459","https://openalex.org/W2163293471","https://openalex.org/W2163693807","https://openalex.org/W2165232124","https://openalex.org/W2187089797","https://openalex.org/W2465194975","https://openalex.org/W2470632190","https://openalex.org/W2539497058","https://openalex.org/W2615547864","https://openalex.org/W2736730865","https://openalex.org/W2887852442","https://openalex.org/W2889714752","https://openalex.org/W2910515822","https://openalex.org/W2940678350","https://openalex.org/W2996629713","https://openalex.org/W2999798211","https://openalex.org/W3003268826","https://openalex.org/W3003412316","https://openalex.org/W3041967313","https://openalex.org/W3048609641","https://openalex.org/W3082203493","https://openalex.org/W3130996446","https://openalex.org/W3133263625","https://openalex.org/W3141505394","https://openalex.org/W4230425944","https://openalex.org/W4234180230","https://openalex.org/W4238856935","https://openalex.org/W4243859311","https://openalex.org/W6678407303","https://openalex.org/W6680228594","https://openalex.org/W6771522894"],"related_works":["https://openalex.org/W2808318865","https://openalex.org/W3108837054","https://openalex.org/W2046193221","https://openalex.org/W2612576664","https://openalex.org/W2996570742","https://openalex.org/W3129596473","https://openalex.org/W3110984360","https://openalex.org/W2766808627","https://openalex.org/W2963771886","https://openalex.org/W2798140514","https://openalex.org/W2942836719","https://openalex.org/W3206133017","https://openalex.org/W3186522912","https://openalex.org/W3007848634","https://openalex.org/W2520647562","https://openalex.org/W3175843755","https://openalex.org/W2625043437","https://openalex.org/W2019336354","https://openalex.org/W3204916529","https://openalex.org/W3176504418"],"abstract_inverted_index":{"Aerial":[0],"vehicles":[1],"are":[2,166],"revolutionizing":[3],"the":[4,172],"way":[5],"filmmakers":[6],"can":[7,139],"capture":[8],"shots":[9,86,164],"of":[10,44,59,78,85,94,106,143,175],"actors":[11],"by":[12,157,168],"composing":[13],"novel":[14],"aerial":[15],"and":[16,35,91,118,128,193,197],"dynamic":[17],"viewpoints.":[18],"However,":[19],"despite":[20],"great":[21],"advancements":[22],"in":[23,65,87,96,190],"autonomous":[24],"flight":[25],"technology,":[26],"generating":[27],"expressive":[28],"camera":[29,62,150],"behaviors":[30],"is":[31],"still":[32],"a":[33,41,53,66,76,82,88,97,104,120,135,141],"challenge":[34],"requires":[36],"non-technical":[37],"users":[38],"to":[39,100,187],"edit":[40],"large":[42],"number":[43],"unintuitive":[45],"control":[46,122],"parameters.":[47,152],"In":[48],"this":[49],"work,":[50],"we":[51,74,113,133],"develop":[52],"data-driven":[54],"framework":[55,99],"that":[56,138,159,165,183],"enables":[57],"editing":[58],"these":[60],"complex":[61],"positioning":[63],"parameters":[64],"semantic":[67,107,121,145],"space":[68,123],"(e.g.":[69],"calm,":[70],"enjoyable,":[71],"establishing).":[72],"First,":[73],"generate":[75],"database":[77],"video":[79,146,198],"clips":[80],"with":[81],"diverse":[83],"range":[84],"photo-realistic":[89],"simulator,":[90],"use":[92],"hundreds":[93],"participants":[95,169],"crowd-sourcing":[98],"obtain":[101],"scores":[102],"for":[103,109,177],"set":[105,142],"descriptors":[108,117,147],"each":[110,178],"clip.":[111],"Next,":[112],"analyze":[114],"correlations":[115],"between":[116],"build":[119],"based":[124],"on":[125],"cinematography":[126],"guidelines":[127],"human":[129],"perception":[130],"studies.":[131],"Finally,":[132],"learn":[134],"generative":[136],"model":[137,161],"map":[140],"desired":[144],"into":[148],"low-level":[149],"trajectory":[151],"We":[153,180],"evaluate":[154],"our":[155,160,184],"system":[156],"demonstrating":[158],"successfully":[162],"generates":[163],"rated":[167],"as":[170],"having":[171],"expected":[173],"degrees":[174],"expression":[176],"descriptor.":[179],"also":[181],"show":[182],"models":[185],"generalize":[186],"different":[188],"scenes":[189],"both":[191],"simulation":[192],"real-world":[194],"experiments.":[195],"Data":[196],"found":[199],"at:":[200],"https://sites.google.com/view/robotcam.":[201]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-10T00:00:00"}