{"id":"https://openalex.org/W2740264161","doi":"https://doi.org/10.1109/iccv.2017.476","title":"Spatial-Aware Object Embeddings for Zero-Shot Localization and Classification of Actions","display_name":"Spatial-Aware Object Embeddings for Zero-Shot Localization and Classification of Actions","publication_year":2017,"publication_date":"2017-10-01","ids":{"openalex":"https://openalex.org/W2740264161","doi":"https://doi.org/10.1109/iccv.2017.476","mag":"2740264161"},"language":"en","primary_location":{"id":"doi:10.1109/iccv.2017.476","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv.2017.476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://handle.uba.uva.nl/personal/pure/en/publications/spatialaware-object-embeddings-for-zeroshot-localization-and-classification-of-actions(a6f56b38-4305-494e-8a9b-a74f8e602942).html","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000845063","display_name":"Pascal Mettes","orcid":"https://orcid.org/0000-0001-9275-5942"},"institutions":[{"id":"https://openalex.org/I4210135670","display_name":"Amsterdam University of the Arts","ror":"https://ror.org/04dde1554","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210135670"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Pascal Mettes","raw_affiliation_strings":["University of Amsterdam","University of Amsterdam, Amsterdam, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]},{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024508073","display_name":"Cees G. M. Snoek","orcid":"https://orcid.org/0000-0001-9092-1556"},"institutions":[{"id":"https://openalex.org/I4210135670","display_name":"Amsterdam University of the Arts","ror":"https://ror.org/04dde1554","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210135670"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Cees G. M. Snoek","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5411,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.75520813,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4453","last_page":"4462"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","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/T10812","display_name":"Human Pose and Action Recognition","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9980000257492065,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9955999851226807,"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/embedding","display_name":"Embedding","score":0.8195397853851318},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.7880368232727051},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6266765594482422},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5836161375045776},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5459800958633423},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.48873233795166016},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.48571261763572693},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.44273674488067627},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.43922486901283264},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41757577657699585},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.4160487651824951},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3575454354286194}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.8195397853851318},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.7880368232727051},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6266765594482422},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5836161375045776},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5459800958633423},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.48873233795166016},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.48571261763572693},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.44273674488067627},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.43922486901283264},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41757577657699585},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.4160487651824951},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3575454354286194},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1109/iccv.2017.476","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv.2017.476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:dare.uva.nl:openaire_cris_publications/a6f56b38-4305-494e-8a9b-a74f8e602942","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/spatialaware-object-embeddings-for-zeroshot-localization-and-classification-of-actions(a6f56b38-4305-494e-8a9b-a74f8e602942).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Mettes, P & Snoek, C G M 2017, Spatial-Aware Object Embeddings for Zero-Shot Localization and Classification of Actions. in 2017 IEEE International Conference on Computer Vision : ICCV 2017 : proceedings : 22-29 October 2017, Venice, Italy. IEEE Computer Society, Los Alamitos, California, pp. 4453-4462, 2017 IEEE International Conference on Computer Vision, Venice, Italy, 22/10/17. https://doi.org/10.1109/ICCV.2017.476","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:arXiv.org:1707.09145","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1707.09145","pdf_url":"https://arxiv.org/pdf/1707.09145","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":null,"raw_type":"text"},{"id":"pmh:oai:dare.uva.nl:openaire/a6f56b38-4305-494e-8a9b-a74f8e602942","is_oa":true,"landing_page_url":"https://hdl.handle.net/11245.1/a6f56b38-4305-494e-8a9b-a74f8e602942","pdf_url":"https://pure.uva.nl/ws/files/22820782/Spatial_Aware_Object_Embeddings.pdf","source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Mettes, P & Snoek, C G M 2017, Spatial-Aware Object Embeddings for Zero-Shot Localization and Classification of Actions. in 2017 IEEE International Conference on Computer Vision : ICCV 2017 : proceedings : 22-29 October 2017, Venice, Italy. IEEE Computer Society, Los Alamitos, California, pp. 4453-4462, 2017 IEEE International Conference on Computer Vision, Venice, Italy, 22/10/17. https://doi.org/10.1109/ICCV.2017.476","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"mag:2740264161","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1707.09145.pdf","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":"pmh:uvapub:oai:dare.uva.nl:publications/a6f56b38-4305-494e-8a9b-a74f8e602942","is_oa":true,"landing_page_url":"https://dare.uva.nl/personal/pure/en/publications/spatialaware-object-embeddings-for-zeroshot-localization-and-classification-of-actions(a6f56b38-4305-494e-8a9b-a74f8e602942).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2017 IEEE International Conference on Computer Vision : ICCV 2017: proceedings : 22-29 October 2017, Venice, Italy, 4453 - 4462","raw_type":"info:eu-repo/semantics/conferencepaper"},{"id":"doi:10.48550/arxiv.1707.09145","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1707.09145","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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:dare.uva.nl:openaire_cris_publications/a6f56b38-4305-494e-8a9b-a74f8e602942","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/spatialaware-object-embeddings-for-zeroshot-localization-and-classification-of-actions(a6f56b38-4305-494e-8a9b-a74f8e602942).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Mettes, P & Snoek, C G M 2017, Spatial-Aware Object Embeddings for Zero-Shot Localization and Classification of Actions. in 2017 IEEE International Conference on Computer Vision : ICCV 2017 : proceedings : 22-29 October 2017, Venice, Italy. IEEE Computer Society, Los Alamitos, California, pp. 4453-4462, 2017 IEEE International Conference on Computer Vision, Venice, Italy, 22/10/17. https://doi.org/10.1109/ICCV.2017.476","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":85,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W43954826","https://openalex.org/W1534763723","https://openalex.org/W1797109199","https://openalex.org/W1805946669","https://openalex.org/W1923332106","https://openalex.org/W1945129080","https://openalex.org/W1950136256","https://openalex.org/W1989560997","https://openalex.org/W2016016818","https://openalex.org/W2016053056","https://openalex.org/W2018068650","https://openalex.org/W2021899621","https://openalex.org/W2034014085","https://openalex.org/W2042328763","https://openalex.org/W2046589395","https://openalex.org/W2050964073","https://openalex.org/W2053619738","https://openalex.org/W2059042271","https://openalex.org/W2064851185","https://openalex.org/W2084793887","https://openalex.org/W2095242101","https://openalex.org/W2095661305","https://openalex.org/W2097117768","https://openalex.org/W2098517267","https://openalex.org/W2100771357","https://openalex.org/W2101194540","https://openalex.org/W2105101328","https://openalex.org/W2106833577","https://openalex.org/W2108598243","https://openalex.org/W2128305246","https://openalex.org/W2128532956","https://openalex.org/W2131042978","https://openalex.org/W2131311058","https://openalex.org/W2131590007","https://openalex.org/W2142194269","https://openalex.org/W2142540378","https://openalex.org/W2146950091","https://openalex.org/W2155983176","https://openalex.org/W2163292664","https://openalex.org/W2168356304","https://openalex.org/W2182587296","https://openalex.org/W2209594346","https://openalex.org/W2212903133","https://openalex.org/W2221298318","https://openalex.org/W2250384498","https://openalex.org/W2280837843","https://openalex.org/W2289324734","https://openalex.org/W2308045930","https://openalex.org/W2346746376","https://openalex.org/W2398000642","https://openalex.org/W2473032611","https://openalex.org/W2516449915","https://openalex.org/W2519055561","https://openalex.org/W2520613337","https://openalex.org/W2525183655","https://openalex.org/W2544736008","https://openalex.org/W2560129302","https://openalex.org/W2740126389","https://openalex.org/W2950076437","https://openalex.org/W2950133940","https://openalex.org/W2950179405","https://openalex.org/W2950286390","https://openalex.org/W2950690336","https://openalex.org/W2950966695","https://openalex.org/W2951015399","https://openalex.org/W2951478746","https://openalex.org/W2952186347","https://openalex.org/W2953106684","https://openalex.org/W4298212933","https://openalex.org/W6600983433","https://openalex.org/W6601825177","https://openalex.org/W6605536666","https://openalex.org/W6620707391","https://openalex.org/W6632082525","https://openalex.org/W6639102338","https://openalex.org/W6664172992","https://openalex.org/W6676297131","https://openalex.org/W6679512744","https://openalex.org/W6679761776","https://openalex.org/W6682691769","https://openalex.org/W6682864246","https://openalex.org/W6712452756","https://openalex.org/W6726638544","https://openalex.org/W6742360996"],"related_works":["https://openalex.org/W2963405520","https://openalex.org/W3196863488","https://openalex.org/W3011865685","https://openalex.org/W3178489527","https://openalex.org/W3022491485","https://openalex.org/W2963441581","https://openalex.org/W2460402606","https://openalex.org/W2946234575","https://openalex.org/W1882891049","https://openalex.org/W2901904725","https://openalex.org/W2808989867","https://openalex.org/W2520761760","https://openalex.org/W3011483492","https://openalex.org/W2962732599","https://openalex.org/W2952038832","https://openalex.org/W2971656825","https://openalex.org/W2997129483","https://openalex.org/W3015218924","https://openalex.org/W3209706285","https://openalex.org/W3088333848"],"abstract_inverted_index":{"We":[0],"aim":[1],"for":[2,23],"zero-shot":[3,25,133],"localization":[4,114,134,148],"and":[5,51,64,87,96,115,135],"classification":[6,21,116,136],"of":[7,47,55],"human":[8],"actions":[9],"in":[10,59,98,131],"video.":[11],"Where":[12],"traditional":[13],"approaches":[14],"rely":[15],"on":[16,45,118],"global":[17,78],"attribute":[18],"or":[19],"object":[20,34,52,73,79,88,94],"scores":[22],"their":[24],"knowledge":[26],"transfer,":[27],"our":[28,43,82,125,138],"main":[29],"contribution":[30],"is":[31,57,141],"a":[32,60,104],"spatial-aware":[33,100,139],"embedding.":[35],"To":[36],"arrive":[37],"at":[38],"spatial":[39,69],"awareness,":[40,74],"we":[41,75,91],"build":[42],"embedding":[44,62,83,101,140],"top":[46],"freely":[48],"available":[49],"actor":[50,86],"detectors.":[53],"Relevance":[54],"objects":[56],"determined":[58],"word":[61],"space":[63],"further":[65],"enforced":[66],"with":[67,110,144],"estimated":[68],"preferences.":[70],"Besides":[71],"local":[72],"also":[76],"embed":[77],"awareness":[80],"into":[81],"to":[84,102],"maximize":[85],"interaction.":[89],"Finally,":[90],"exploit":[92],"the":[93,99,132],"positions":[95],"sizes":[97],"demonstrate":[103],"new":[105],"spatiotemporal":[106],"action":[107,121,147],"retrieval":[108],"scenario":[109],"composite":[111],"queries.":[112],"Action":[113],"experiments":[117],"four":[119],"contemporary":[120],"video":[122],"datasets":[123],"support":[124],"proposal.":[126],"Apart":[127],"from":[128],"state-of-the-art":[129],"results":[130],"settings,":[137],"even":[142],"competitive":[143],"recent":[145],"supervised":[146],"alternatives.":[149]},"counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}