{"id":"https://openalex.org/W2610147864","doi":"https://doi.org/10.1109/icpr.2016.7899735","title":"Video2vec: Learning semantic spatio-temporal embeddings for video representation","display_name":"Video2vec: Learning semantic spatio-temporal embeddings for video representation","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2610147864","doi":"https://doi.org/10.1109/icpr.2016.7899735","mag":"2610147864"},"language":"en","primary_location":{"id":"doi:10.1109/icpr.2016.7899735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2016.7899735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 23rd International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5069951623","display_name":"Sheng-Hung Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sheng-Hung Hu","raw_affiliation_strings":["Arizona State University, Tempe, AZ, US"],"affiliations":[{"raw_affiliation_string":"Arizona State University, Tempe, AZ, US","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100610029","display_name":"Yikang Li","orcid":"https://orcid.org/0000-0003-4666-9642"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yikang Li","raw_affiliation_strings":["School of Electrical Engineering, Arizona State University, Tempe, Arizona"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Arizona State University, Tempe, Arizona","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032615847","display_name":"Baoxin Li","orcid":"https://orcid.org/0000-0002-9294-4572"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Baoxin Li","raw_affiliation_strings":["School of Computer Science, Arizona State University, Tempe, Arizona"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Arizona State University, Tempe, Arizona","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5069951623"],"corresponding_institution_ids":["https://openalex.org/I55732556"],"apc_list":null,"apc_paid":null,"fwci":1.169,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.86045614,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"abs 1502 4681","issue":null,"first_page":"811","last_page":"816"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.996999979019165,"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":0.9912999868392944,"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/computer-science","display_name":"Computer science","score":0.8042298555374146},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5596687197685242},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.508258044719696},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4998292922973633},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41511833667755127},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33614397048950195}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8042298555374146},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5596687197685242},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.508258044719696},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4998292922973633},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41511833667755127},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33614397048950195},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr.2016.7899735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2016.7899735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 23rd International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W93016980","https://openalex.org/W1041917003","https://openalex.org/W1574113434","https://openalex.org/W1614298861","https://openalex.org/W1686810756","https://openalex.org/W1805946669","https://openalex.org/W1867429401","https://openalex.org/W1923332106","https://openalex.org/W1923404803","https://openalex.org/W1944615693","https://openalex.org/W1947481528","https://openalex.org/W2020163092","https://openalex.org/W2024868105","https://openalex.org/W2064675550","https://openalex.org/W2108598243","https://openalex.org/W2116435618","https://openalex.org/W2124386111","https://openalex.org/W2126574503","https://openalex.org/W2128532956","https://openalex.org/W2131427930","https://openalex.org/W2139501017","https://openalex.org/W2156303437","https://openalex.org/W2157331557","https://openalex.org/W2950577311","https://openalex.org/W2952186347","https://openalex.org/W2952453038","https://openalex.org/W2953111739","https://openalex.org/W2963173190","https://openalex.org/W2964241990","https://openalex.org/W4296262844","https://openalex.org/W6600983433","https://openalex.org/W6640257725","https://openalex.org/W6648737282","https://openalex.org/W6677326919","https://openalex.org/W6682864246"],"related_works":["https://openalex.org/W2384888906","https://openalex.org/W2144190808","https://openalex.org/W2376314740","https://openalex.org/W2366644548","https://openalex.org/W2357241418","https://openalex.org/W2611614995","https://openalex.org/W2469626427","https://openalex.org/W2115485936","https://openalex.org/W3107474891","https://openalex.org/W2248073783"],"abstract_inverted_index":{"We":[0,90],"propose":[1],"to":[2,9,63,71,78],"learn":[3,64],"semantic":[4,74,80],"spatio-temporal":[5,57],"embeddings":[6],"for":[7,46],"videos":[8],"support":[10],"high-level":[11,88],"video":[12,84,99,107],"analysis.":[13,89],"The":[14,55],"first":[15],"step":[16],"of":[17,26,29,51,82,96],"the":[18,52,72,83,92,113],"proposed":[19],"embedding":[20,75],"employs":[21],"a":[22,65,68,79],"deep":[23],"architecture":[24],"consisting":[25],"two":[27],"channels":[28],"convolutional":[30],"neural":[31],"networks":[32],"(capturing":[33],"appearance":[34],"and":[35,94,109],"local":[36],"motion)":[37],"followed":[38],"by":[39,101],"their":[40],"corresponding":[41],"Gated":[42],"Recurrent":[43],"Unit":[44],"encoders":[45],"capturing":[47],"longer-term":[48],"temporal":[49],"structure":[50],"CNN":[53],"features.":[54],"resultant":[56],"representation":[58,100],"(a":[59],"vector)":[60],"is":[61],"used":[62],"mapping":[66],"via":[67],"multilayer":[69],"perceptron":[70],"word2vec":[73],"space,":[76],"leading":[77],"interpretation":[81],"vector":[85],"that":[86],"supports":[87],"demonstrate":[91],"usefulness":[93],"effectiveness":[95],"this":[97],"new":[98],"experiments":[102],"on":[103],"action":[104],"recognition,":[105],"zero-shot":[106],"classification,":[108],"\u201cword-to-video\u201d":[110],"retrieval,":[111],"using":[112],"UCF-101":[114],"dataset.":[115]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}