{"id":"https://openalex.org/W2607741023","doi":"https://doi.org/10.18653/v1/p17-2011","title":"An Analysis of Action Recognition Datasets for Language and Vision Tasks","display_name":"An Analysis of Action Recognition Datasets for Language and Vision Tasks","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2607741023","doi":"https://doi.org/10.18653/v1/p17-2011","mag":"2607741023"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p17-2011","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-2011","pdf_url":"https://www.aclweb.org/anthology/P17-2011.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 55th Annual Meeting of the Association for\n          Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P17-2011.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041111343","display_name":"Spandana Gella","orcid":"https://orcid.org/0000-0003-2725-4476"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Spandana Gella","raw_affiliation_strings":["Institute for Language, Cognition and Computation School of Informatics, University of Edinburgh 10 Crichton Street, Edinburgh EH8 9AB","Microsoft (United States), Redmond, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Language, Cognition and Computation School of Informatics, University of Edinburgh 10 Crichton Street, Edinburgh EH8 9AB","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Microsoft (United States), Redmond, United States","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054936589","display_name":"Frank Keller","orcid":"https://orcid.org/0000-0002-8242-4362"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Frank Keller","raw_affiliation_strings":["Institute for Language, Cognition and Computation School of Informatics, University of Edinburgh 10 Crichton Street, Edinburgh EH8 9AB","School of Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Language, Cognition and Computation School of Informatics, University of Edinburgh 10 Crichton Street, Edinburgh EH8 9AB","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"64","last_page":"71"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9994000196456909,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9923999905586243,"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/computer-science","display_name":"Computer science","score":0.763738751411438},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.7313235998153687},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.7110179662704468},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6961275935173035},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6674199104309082},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5559515953063965},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5025465488433838},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4985620975494385},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47336265444755554},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35918986797332764}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.763738751411438},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.7313235998153687},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.7110179662704468},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6961275935173035},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6674199104309082},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5559515953063965},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5025465488433838},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4985620975494385},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47336265444755554},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35918986797332764},{"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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.18653/v1/p17-2011","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-2011","pdf_url":"https://www.aclweb.org/anthology/P17-2011.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 55th Annual Meeting of the Association for\n          Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1704.07129","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1704.07129","pdf_url":"https://arxiv.org/pdf/1704.07129","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":"","raw_type":"text"},{"id":"mag:2607741023","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1704.07129","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:oai:pure.ed.ac.uk:openaire/f2e37a25-41fd-47a4-bdb7-2f1e773b396a","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/f2e37a25-41fd-47a4-bdb7-2f1e773b396a","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Gella, S & Keller, F 2017, An Analysis of Action Recognition Datasets for Language and Vision Tasks. in Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Short Papers). pp. 64-71, 55th annual meeting of the Association for Computational Linguistics (ACL), Vancouver, Canada, 30/07/17. https://doi.org/10.18653/v1/P17-2011","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/f2e37a25-41fd-47a4-bdb7-2f1e773b396a","is_oa":true,"landing_page_url":"http://aclweb.org/anthology/P17-2011","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Gella, S & Keller, F 2017, An Analysis of Action Recognition Datasets for Language and Vision Tasks. in Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Short Papers). pp. 64-71, 55th annual meeting of the Association for Computational Linguistics (ACL), Vancouver, Canada, 30/07/17. https://doi.org/10.18653/v1/P17-2011","raw_type":"contributionToPeriodical"},{"id":"doi:10.48550/arxiv.1704.07129","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1704.07129","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":"doi:10.18653/v1/p17-2011","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-2011","pdf_url":"https://www.aclweb.org/anthology/P17-2011.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 55th Annual Meeting of the Association for\n          Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8100000023841858,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2607741023.pdf","grobid_xml":"https://content.openalex.org/works/W2607741023.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1551928752","https://openalex.org/W1749884237","https://openalex.org/W1858383477","https://openalex.org/W1889081078","https://openalex.org/W1892016050","https://openalex.org/W1927052826","https://openalex.org/W2011132078","https://openalex.org/W2014788385","https://openalex.org/W2027815734","https://openalex.org/W2031489346","https://openalex.org/W2037227137","https://openalex.org/W2038765747","https://openalex.org/W2039217078","https://openalex.org/W2050964073","https://openalex.org/W2052065843","https://openalex.org/W2080873731","https://openalex.org/W2081580037","https://openalex.org/W2088911157","https://openalex.org/W2102153514","https://openalex.org/W2115792525","https://openalex.org/W2117539524","https://openalex.org/W2124386111","https://openalex.org/W2147625498","https://openalex.org/W2161969291","https://openalex.org/W2169393274","https://openalex.org/W2202226326","https://openalex.org/W2214124602","https://openalex.org/W2251353663","https://openalex.org/W2295107390","https://openalex.org/W2331817973","https://openalex.org/W2339712187","https://openalex.org/W2423576022","https://openalex.org/W2471164729","https://openalex.org/W2518268700","https://openalex.org/W2949474740","https://openalex.org/W2950761309","https://openalex.org/W2952686080","https://openalex.org/W2952997040","https://openalex.org/W2953238423"],"related_works":["https://openalex.org/W2963736289","https://openalex.org/W2472931974","https://openalex.org/W1975325338","https://openalex.org/W2963540523","https://openalex.org/W2460546314","https://openalex.org/W3112077297","https://openalex.org/W2799406003","https://openalex.org/W3162506348","https://openalex.org/W2808428154","https://openalex.org/W2988326850","https://openalex.org/W2551567353","https://openalex.org/W156899190","https://openalex.org/W2888211297","https://openalex.org/W3178036561","https://openalex.org/W3103971440","https://openalex.org/W2496096353","https://openalex.org/W2889445722","https://openalex.org/W2764131040","https://openalex.org/W2900438761","https://openalex.org/W3209072383"],"abstract_inverted_index":{"A":[0],"large":[1],"amount":[2],"of":[3,19,59,92],"recent":[4],"research":[5],"has":[6],"focused":[7],"on":[8,48,73],"tasks":[9],"that":[10],"combine":[11],"language":[12],"and":[13,21,36,54,69,84,89],"vision,":[14],"resulting":[15],"in":[16,94],"a":[17,56,86],"proliferation":[18],"datasets":[20,76],"methods.":[22],"One":[23],"such":[24],"task":[25],"is":[26],"action":[27],"recognition,":[28],"whose":[29],"applications":[30],"include":[31],"image":[32,37],"annotation,":[33],"scene":[34],"understanding":[35],"retrieval.":[38],"In":[39],"this":[40,52],"survey,":[41],"we":[42],"categorize":[43],"the":[44],"existing":[45,60],"approaches":[46],"based":[47],"how":[49],"they":[50],"conceptualize":[51],"problem":[53],"provide":[55,85],"detailed":[57],"review":[58],"datasets,":[61],"highlighting":[62],"their":[63],"diversity":[64],"as":[65,67],"well":[66],"advantages":[68],"disadvantages.":[70],"We":[71],"focus":[72],"recently":[74],"developed":[75],"which":[77],"link":[78],"visual":[79],"information":[80],"with":[81],"linguistic":[82],"resources":[83],"fine-grained":[87],"syntactic":[88],"semantic":[90],"analysis":[91],"actions":[93],"images.":[95]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}