{"id":"https://openalex.org/W2765097853","doi":"https://doi.org/10.1145/3126686.3126755","title":"CTC Network with Statistical Language Modeling for Action Sequence Recognition in Videos","display_name":"CTC Network with Statistical Language Modeling for Action Sequence Recognition in Videos","publication_year":2017,"publication_date":"2017-10-23","ids":{"openalex":"https://openalex.org/W2765097853","doi":"https://doi.org/10.1145/3126686.3126755","mag":"2765097853"},"language":"en","primary_location":{"id":"doi:10.1145/3126686.3126755","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3126686.3126755","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the on Thematic Workshops of ACM Multimedia 2017","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://t2r2.star.titech.ac.jp/rrws/file/CTT100755473/ATD100000413/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044887605","display_name":"Mengxi Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mengxi Lin","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101261291","display_name":"Nakamasa Inoue","orcid":"https://orcid.org/0009-0006-1145-0914"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nakamasa Inoue","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081629487","display_name":"Koichi Shinoda","orcid":"https://orcid.org/0000-0003-1095-3203"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Koichi Shinoda","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"393","last_page":"401"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":1.0,"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":1.0,"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":0.9994000196456909,"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/T11309","display_name":"Music and Audio Processing","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.766496479511261},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6509040594100952},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5641383528709412},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5344440340995789},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5076688528060913},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.45447900891304016},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4467700123786926},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.4401874840259552},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.05840834975242615}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.766496479511261},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6509040594100952},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5641383528709412},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5344440340995789},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5076688528060913},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.45447900891304016},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4467700123786926},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.4401874840259552},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.05840834975242615},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3126686.3126755","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3126686.3126755","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the on Thematic Workshops of ACM Multimedia 2017","raw_type":"proceedings-article"},{"id":"pmh:oai:irdb.nii.ac.jp:00897:0004114228","is_oa":true,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100755473","pdf_url":"http://t2r2.star.titech.ac.jp/rrws/file/CTT100755473/ATD100000413/","source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc. ACM Multimedia Thematic Workshop","raw_type":"conference paper"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:00897:0004114228","is_oa":true,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100755473","pdf_url":"http://t2r2.star.titech.ac.jp/rrws/file/CTT100755473/ATD100000413/","source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc. ACM Multimedia Thematic Workshop","raw_type":"conference paper"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.550000011920929}],"awards":[],"funders":[{"id":"https://openalex.org/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2765097853.pdf","grobid_xml":"https://content.openalex.org/works/W2765097853.grobid-xml"},"referenced_works_count":71,"referenced_works":["https://openalex.org/W17156489","https://openalex.org/W24089286","https://openalex.org/W28988658","https://openalex.org/W179875071","https://openalex.org/W281892562","https://openalex.org/W846669277","https://openalex.org/W1021004080","https://openalex.org/W1522734439","https://openalex.org/W1534763723","https://openalex.org/W1586939924","https://openalex.org/W1597533204","https://openalex.org/W1631260214","https://openalex.org/W1644652583","https://openalex.org/W1710082047","https://openalex.org/W1900913856","https://openalex.org/W1947481528","https://openalex.org/W1966385142","https://openalex.org/W1971029034","https://openalex.org/W1983364832","https://openalex.org/W1988650444","https://openalex.org/W2020163092","https://openalex.org/W2024868105","https://openalex.org/W2063689849","https://openalex.org/W2064675550","https://openalex.org/W2079735306","https://openalex.org/W2082092506","https://openalex.org/W2084341401","https://openalex.org/W2097117768","https://openalex.org/W2097927681","https://openalex.org/W2099614498","https://openalex.org/W2103924867","https://openalex.org/W2105101328","https://openalex.org/W2108333036","https://openalex.org/W2108598243","https://openalex.org/W2108710284","https://openalex.org/W2121227244","https://openalex.org/W2125838338","https://openalex.org/W2126579184","https://openalex.org/W2127141656","https://openalex.org/W2134237567","https://openalex.org/W2136583886","https://openalex.org/W2152563462","https://openalex.org/W2155520241","https://openalex.org/W2156303437","https://openalex.org/W2168347767","https://openalex.org/W2189149359","https://openalex.org/W2193413348","https://openalex.org/W2250660307","https://openalex.org/W2293858598","https://openalex.org/W2314362175","https://openalex.org/W2342662179","https://openalex.org/W2413641397","https://openalex.org/W2461621749","https://openalex.org/W2463824207","https://openalex.org/W2471695703","https://openalex.org/W2477205648","https://openalex.org/W2491875666","https://openalex.org/W2510642588","https://openalex.org/W2530494944","https://openalex.org/W2593722617","https://openalex.org/W2604113307","https://openalex.org/W2611071497","https://openalex.org/W2618530766","https://openalex.org/W2759336060","https://openalex.org/W2950186769","https://openalex.org/W2962795934","https://openalex.org/W2963211739","https://openalex.org/W2963843052","https://openalex.org/W2964308564","https://openalex.org/W3147600416","https://openalex.org/W4233559841"],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W1563618553","https://openalex.org/W142374489","https://openalex.org/W2359001871","https://openalex.org/W2148757832","https://openalex.org/W1803932089","https://openalex.org/W2374918184","https://openalex.org/W1538473846","https://openalex.org/W2351428524","https://openalex.org/W1569841287"],"abstract_inverted_index":{"We":[0,61],"propose":[1],"a":[2,30],"method":[3,23,64,90],"for":[4],"recognizing":[5],"an":[6,48],"action":[7,42],"sequence":[8],"in":[9,47],"which":[10,83],"several":[11],"actions":[12],"are":[13,18],"concatenated":[14],"and":[15,29],"their":[16],"boundaries":[17],"not":[19],"given.":[20],"The":[21,51],"proposed":[22],"combines":[24],"Connectionist":[25],"Temporal":[26],"Classification":[27],"(CTC)":[28],"statistical":[31,52],"language":[32,53,76],"model.":[33],"CTC":[34],"can":[35,55],"learn":[36,56],"the":[37,57,66,72,75,87],"nature":[38],"of":[39],"each":[40],"element":[41],"given":[43],"no":[44],"boundary":[45],"information":[46],"end-to-end":[49],"manner.":[50],"model":[54],"relationship":[58],"between":[59],"actions.":[60],"evaluate":[62],"our":[63],"on":[65],"Breakfast":[67],"dataset.":[68],"When":[69],"we":[70],"use":[71],"trigram":[73],"as":[74],"model,":[77],"its":[78],"accuracy":[79],"rate":[80],"is":[81,84],"43.4%,":[82],"better":[85],"than":[86],"state-of-the-art":[88],"ECTC":[89],"by":[91],"6.7":[92],"percentage":[93],"points.":[94]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}