{"id":"https://openalex.org/W2579317665","doi":null,"title":"Unsupervised alignment of actions in video with text descriptions","display_name":"Unsupervised alignment of actions in video with text descriptions","publication_year":2016,"publication_date":"2016-07-09","ids":{"openalex":"https://openalex.org/W2579317665","mag":"2579317665"},"language":"en","primary_location":{"id":"mag:2579317665","doi":null,"is_oa":false,"landing_page_url":"http://dblp.uni-trier.de/db/conf/ijcai/ijcai2016.html#SongNMKSLGK16","pdf_url":null,"source":{"id":"https://openalex.org/S4306419999","display_name":"International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Joint Conference on Artificial Intelligence","raw_type":null},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004261476","display_name":"Young Chol Song","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Young Chol Song","raw_affiliation_strings":["Department of Computer Science, University of Rochester, Rochester NY#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Rochester, Rochester NY#TAB#","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033760431","display_name":"Iftekhar Naim","orcid":"https://orcid.org/0000-0002-2119-3273","observed_orcids":["https://orcid.org/0000-0002-2119-3273"]},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Iftekhar Naim","raw_affiliation_strings":["Google and Department of Computer Science, University of Rochester, Rochester, NY#TAB#"],"raw_orcid":"https://orcid.org/0000-0002-2119-3273","affiliations":[{"raw_affiliation_string":"Google and Department of Computer Science, University of Rochester, Rochester, NY#TAB#","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071194728","display_name":"Abdullah Al Mamun","orcid":"https://orcid.org/0000-0002-7075-0662","observed_orcids":["https://orcid.org/0000-0002-7075-0662"]},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abdullah Al Mamun","raw_affiliation_strings":["Department of Computer Science, University of Rochester, Rochester NY#TAB#"],"raw_orcid":"https://orcid.org/0000-0002-7075-0662","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Rochester, Rochester NY#TAB#","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kaustubh Kulkarni","orcid":"https://orcid.org/0000-0001-6526-4873","observed_orcids":["https://orcid.org/0000-0001-6526-4873"]},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kaustubh Kulkarni","raw_affiliation_strings":["Yahoo, Japan and Indian Institute of Technology Delhi, New Delhi, India#TAB#"],"raw_orcid":"https://orcid.org/0000-0001-6526-4873","affiliations":[{"raw_affiliation_string":"Yahoo, Japan and Indian Institute of Technology Delhi, New Delhi, India#TAB#","institution_ids":["https://openalex.org/I68891433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103677687","display_name":"Parag Singla","orcid":"https://orcid.org/0009-0000-9190-9794","observed_orcids":["https://orcid.org/0009-0000-9190-9794"]},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Parag Singla","raw_affiliation_strings":["Indian Institute of Technology Delhi,  New Delhi, India"],"raw_orcid":"https://orcid.org/0009-0000-9190-9794","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Delhi,  New Delhi, India","institution_ids":["https://openalex.org/I68891433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055469774","display_name":"Jiebo Luo","orcid":"https://orcid.org/0000-0002-4516-9729","observed_orcids":["https://orcid.org/0000-0002-4516-9729"]},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiebo Luo","raw_affiliation_strings":["Department of Computer Science, University of Rochester, Rochester NY#TAB#"],"raw_orcid":"https://orcid.org/0000-0002-4516-9729","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Rochester, Rochester NY#TAB#","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020945377","display_name":"Daniel Gildea","orcid":"https://orcid.org/0000-0002-7858-2624","observed_orcids":["https://orcid.org/0000-0002-7858-2624"]},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Gildea","raw_affiliation_strings":["Department of Computer Science, University of Rochester, Rochester NY#TAB#"],"raw_orcid":"https://orcid.org/0000-0002-7858-2624","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Rochester, Rochester NY#TAB#","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105508446","display_name":"Henry Kautz","orcid":"https://orcid.org/0000-0001-5219-2970","observed_orcids":["https://orcid.org/0000-0001-5219-2970"]},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Henry Kautz","raw_affiliation_strings":["Department of Computer Science, University of Rochester, Rochester NY#TAB#"],"raw_orcid":"https://orcid.org/0000-0001-5219-2970","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Rochester, Rochester NY#TAB#","institution_ids":["https://openalex.org/I5388228"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1161,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.94903886,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":87,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2025","last_page":"2031"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.6381999850273132,"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":0.6381999850273132,"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":0.28220000863075256,"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":0.0406000018119812,"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/unsupervised-alignment","display_name":"unsupervised alignment","score":0.824999988079071},{"id":"https://openalex.org/keywords/video-text-alignment","display_name":"video-text alignment","score":0.8859999775886536},{"id":"https://openalex.org/keywords/human-action-recognition","display_name":"human action recognition","score":0.675000011920929},{"id":"https://openalex.org/keywords/verb-identification","display_name":"verb identification","score":0.4480000138282776},{"id":"https://openalex.org/keywords/kitchen-activities","display_name":"kitchen activities","score":0.7009999752044678},{"id":"https://openalex.org/keywords/temporal-coherence","display_name":"temporal coherence","score":0.5849999785423279}],"concepts":[{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.8563948273658752},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8534313440322876},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6032251119613647},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5486050248146057},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5103382468223572},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4612051844596863},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4103044271469116},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2579317665","doi":null,"is_oa":false,"landing_page_url":"http://dblp.uni-trier.de/db/conf/ijcai/ijcai2016.html#SongNMKSLGK16","pdf_url":null,"source":{"id":"https://openalex.org/S4306419999","display_name":"International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Joint Conference on Artificial Intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W129606432","https://openalex.org/W180242331","https://openalex.org/W262578090","https://openalex.org/W1481820510","https://openalex.org/W1613163714","https://openalex.org/W1696716473","https://openalex.org/W1923332106","https://openalex.org/W1944615693","https://openalex.org/W1963321737","https://openalex.org/W1978383016","https://openalex.org/W1993229407","https://openalex.org/W2017169951","https://openalex.org/W2020163092","https://openalex.org/W2024405391","https://openalex.org/W2069809153","https://openalex.org/W2105101328","https://openalex.org/W2111078031","https://openalex.org/W2112724113","https://openalex.org/W2112796928","https://openalex.org/W2112999531","https://openalex.org/W2126574503","https://openalex.org/W2151103935","https://openalex.org/W2163605009","https://openalex.org/W2166118928","https://openalex.org/W2296613712","https://openalex.org/W2949594863"],"related_works":["https://openalex.org/W129606432","https://openalex.org/W4387770496","https://openalex.org/W7134847743","https://openalex.org/W4402716475","https://openalex.org/W6910765073","https://openalex.org/W2949310145","https://openalex.org/W2524331645","https://openalex.org/W7212080253","https://openalex.org/W2950255061","https://openalex.org/W3202074654"],"abstract_inverted_index":{"Advances":[0],"in":[1,37,73,147],"video":[2,11,30,39,52,74,85,112],"technology":[3],"and":[4,113,134,145,164,171],"data":[5,12],"storage":[6],"have":[7,62],"made":[8],"large":[9],"scale":[10,179],"collections":[13],"of":[14,28,71,104,162,168,181],"complex":[15],"activities":[16],"readily":[17],"accessible.":[18],"An":[19],"increasingly":[20],"popular":[21],"approach":[22],"for":[23,47,68,87],"automatically":[24],"inferring":[25],"the":[26,34,142,148],"details":[27],"a":[29,38,97,120,125,177],"is":[31],"to":[32,65,81,150],"associate":[33],"spatio-temporal":[35,84],"segments":[36,86],"with":[40,51,75,92,116,130],"its":[41],"natural":[42,49],"language":[43,50,149],"descriptions.":[44],"Most":[45],"algorithms":[46],"connecting":[48],"rely":[53],"on":[54,166,176],"pre-aligned":[55],"supervised":[56],"training":[57],"data.":[58],"Recently,":[59],"several":[60],"models":[61,161],"been":[63],"shown":[64],"be":[66],"effective":[67],"unsupervised":[69,138],"alignment":[70,139,160],"objects":[72,163],"language.":[76,93,117],"However,":[77],"it":[78],"remains":[79],"difficult":[80],"generate":[82],"good":[83],"actions":[88],"that":[89,99,123],"align":[90],"well":[91],"This":[94],"paper":[95],"presents":[96],"framework":[98],"extracts":[100],"higher":[101],"level":[102],"representations":[103],"low-level":[105],"action":[106,127,143],"features":[107],"through":[108],"hyperfeature":[109],"coding":[110],"from":[111],"aligns":[114],"them":[115],"We":[118,154],"propose":[119],"two-step":[121],"process":[122],"creates":[124],"high-level":[126],"feature":[128],"codebook":[129],"temporally":[131],"consistent":[132],"motions,":[133],"then":[135],"applies":[136],"an":[137,156],"algorithm":[140],"over":[141,158],"codewords":[144],"verbs":[146],"identify":[151],"individual":[152],"activities.":[153,185],"show":[155],"improvement":[157],"previous":[159],"nouns":[165],"videos":[167,182],"biological":[169],"experiments,":[170],"also":[172],"evaluate":[173],"our":[174],"system":[175],"larger":[178],"collection":[180],"involving":[183],"kitchen":[184]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":3}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2017-01-26T00:00:00"}