{"id":"https://openalex.org/W7134808314","doi":"https://doi.org/10.1145/3757279.3785641","title":"SCOPE: Real-Time Natural Language Camera Agent at the Edge","display_name":"SCOPE: Real-Time Natural Language Camera Agent at the Edge","publication_year":2026,"publication_date":"2026-03-10","ids":{"openalex":"https://openalex.org/W7134808314","doi":"https://doi.org/10.1145/3757279.3785641"},"language":null,"primary_location":{"id":"doi:10.1145/3757279.3785641","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3757279.3785641","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2606.02951","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128677398","display_name":"Nikolaj Hindsbo","orcid":null},"institutions":[{"id":"https://openalex.org/I174135032","display_name":"Bellevue College","ror":"https://ror.org/05gr4yv49","country_code":"US","type":"education","lineage":["https://openalex.org/I174135032"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nikolaj Hindsbo","raw_affiliation_strings":["Armada, Bellevue, USA"],"raw_orcid":"https://orcid.org/0009-0000-5472-2461","affiliations":[{"raw_affiliation_string":"Armada, Bellevue, USA","institution_ids":["https://openalex.org/I174135032"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102964416","display_name":"Sina Ehsani","orcid":"https://orcid.org/0000-0002-6009-7612"},"institutions":[{"id":"https://openalex.org/I174135032","display_name":"Bellevue College","ror":"https://ror.org/05gr4yv49","country_code":"US","type":"education","lineage":["https://openalex.org/I174135032"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sina Ehsani","raw_affiliation_strings":["Armada, Bellevue, USA"],"raw_orcid":"https://orcid.org/0000-0002-6009-7612","affiliations":[{"raw_affiliation_string":"Armada, Bellevue, USA","institution_ids":["https://openalex.org/I174135032"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111565609","display_name":"Pragyana Mishra","orcid":"https://orcid.org/0000-0002-6111-797X"},"institutions":[{"id":"https://openalex.org/I174135032","display_name":"Bellevue College","ror":"https://ror.org/05gr4yv49","country_code":"US","type":"education","lineage":["https://openalex.org/I174135032"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pragyana Mishra","raw_affiliation_strings":["Armada, Bellevue, USA"],"raw_orcid":"https://orcid.org/0000-0002-6111-797X","affiliations":[{"raw_affiliation_string":"Armada, Bellevue, USA","institution_ids":["https://openalex.org/I174135032"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I174135032"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20727126,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"553","last_page":"561"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8507999777793884,"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":0.8507999777793884,"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/T12031","display_name":"Speech and dialogue systems","score":0.013399999588727951,"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/T13904","display_name":"Artificial Intelligence Applications","score":0.007799999788403511,"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/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.460999995470047},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.42419999837875366},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.39980000257492065},{"id":"https://openalex.org/keywords/edge-detection","display_name":"Edge detection","score":0.3693000078201294},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.32100000977516174}],"concepts":[{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6654000282287598},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5985000133514404},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5875999927520752},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.460999995470047},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.42419999837875366},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.39980000257492065},{"id":"https://openalex.org/C193536780","wikidata":"https://www.wikidata.org/wiki/Q1513153","display_name":"Edge detection","level":4,"score":0.3693000078201294},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3264999985694885},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.32100000977516174},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.3052000105381012},{"id":"https://openalex.org/C119657128","wikidata":"https://www.wikidata.org/wiki/Q11633","display_name":"Photography","level":2,"score":0.29820001125335693},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.2689000070095062}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3757279.3785641","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3757279.3785641","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2606.02951","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.02951","pdf_url":"https://arxiv.org/pdf/2606.02951","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2606.02951","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.02951","pdf_url":"https://arxiv.org/pdf/2606.02951","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6704133749008179}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7134808314.pdf","grobid_xml":"https://content.openalex.org/works/W7134808314.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W2950697717","https://openalex.org/W2963037989","https://openalex.org/W2963800628","https://openalex.org/W3034758614","https://openalex.org/W3083410900","https://openalex.org/W4224912544","https://openalex.org/W4383097638","https://openalex.org/W4390873321","https://openalex.org/W4391376827","https://openalex.org/W4394828156","https://openalex.org/W4403589924","https://openalex.org/W4403788644","https://openalex.org/W4407794264","https://openalex.org/W4412431580","https://openalex.org/W4415798077"],"related_works":[],"abstract_inverted_index":{"Deploying":[0],"language-driven":[1],"agents":[2,18],"in":[3,74],"robotics":[4],"requires":[5],"evaluations":[6],"that":[7],"reflect":[8],"real-world":[9],"task":[10],"demands:":[11],"natural-language":[12],"instructions":[13],"with":[14],"reproducible":[15],"outcomes.":[16],"Such":[17],"must":[19],"connect":[20],"language":[21],"models":[22],"to":[23],"callable":[24],"perception":[25],"and":[26,29,38,45,50,62,79,89],"control":[27,61,90],"tools,":[28],"be":[30],"assessed":[31],"using":[32,96],"deployment-critical":[33],"metrics":[34],"including":[35],"latency,":[36],"accuracy,":[37],"error":[39],"modes.":[40],"We":[41],"present":[42],"SCOPE":[43,71],"(Simulation":[44],"Camera":[46],"Operations":[47],"for":[48,55,68],"Perception":[49],"Evaluation),":[51],"a":[52,75,81],"modular":[53],"agent":[54],"natural-language,":[56],"open-vocabulary":[57],"pan\u2013tilt\u2013zoom":[58],"(PTZ)":[59],"camera":[60],"visual":[63],"scene":[64],"understanding,":[65],"designed":[66],"explicitly":[67],"edge":[69],"deployment.":[70],"operates":[72],"both":[73],"Blender-based":[76],"simulation":[77],"environment":[78],"on":[80],"physical":[82],"PTZ":[83],"camera,":[84],"executing":[85],"all":[86],"perception,":[87],"planning,":[88],"locally":[91],"at":[92],"the":[93],"deployment":[94],"site":[95],"edge-accessible":[97],"compute.":[98]},"counts_by_year":[],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2026-03-11T00:00:00"}
