{"id":"https://openalex.org/W2895824963","doi":"https://doi.org/10.1145/3265987.3265991","title":"Video Understanding via Convolutional Temporal Pooling Network and Multimodal Feature Fusion","display_name":"Video Understanding via Convolutional Temporal Pooling Network and Multimodal Feature Fusion","publication_year":2018,"publication_date":"2018-10-15","ids":{"openalex":"https://openalex.org/W2895824963","doi":"https://doi.org/10.1145/3265987.3265991","mag":"2895824963"},"language":"en","primary_location":{"id":"doi:10.1145/3265987.3265991","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3265987.3265991","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st Workshop and Challenge on Comprehensive Video Understanding in the Wild","raw_type":"proceedings-article"},"type":"conference-paper","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/A5033020994","display_name":"Heeseung Kwon","orcid":null},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Heeseung Kwon","raw_affiliation_strings":["POSTECH, Pohang, Rebublic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"POSTECH, Pohang, Rebublic of Korea","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060343759","display_name":"Suha Kwak","orcid":"https://orcid.org/0000-0002-4567-9091"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Suha Kwak","raw_affiliation_strings":["POSTECH, Pohang, Rebublic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"POSTECH, Pohang, Rebublic of Korea","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087650565","display_name":"Minsu Cho","orcid":"https://orcid.org/0000-0002-9442-9232"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minsu Cho","raw_affiliation_strings":["POSTECH, Pohang, Rebublic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"POSTECH, Pohang, Rebublic of Korea","institution_ids":["https://openalex.org/I123900574"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I123900574"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"35","last_page":"39"},"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":0.9970999956130981,"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":0.9858999848365784,"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/pooling","display_name":"Pooling","score":0.9016509056091309},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.826217770576477},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7269574999809265},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7179843783378601},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.581134557723999},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5805480480194092},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4798376262187958},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.45869511365890503},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4467966556549072},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4361562132835388},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35880908370018005}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.9016509056091309},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.826217770576477},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7269574999809265},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7179843783378601},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.581134557723999},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5805480480194092},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4798376262187958},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45869511365890503},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4467966556549072},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4361562132835388},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35880908370018005},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3265987.3265991","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3265987.3265991","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st Workshop and Challenge on Comprehensive Video Understanding in the Wild","raw_type":"proceedings-article"},{"id":"pmh:oai:oasis.postech.ac.kr:2014.oak/97556","is_oa":false,"landing_page_url":"https://oasis.postech.ac.kr/handle/2014.oak/97556","pdf_url":null,"source":{"id":"https://openalex.org/S4306401965","display_name":"Open Access System for Information Sharing (Pohang University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I123900574","host_organization_name":"Pohang University of Science and Technology","host_organization_lineage":["https://openalex.org/I123900574"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1595717062","https://openalex.org/W1836465849","https://openalex.org/W1947481528","https://openalex.org/W1983364832","https://openalex.org/W2025653905","https://openalex.org/W2064675550","https://openalex.org/W2095705004","https://openalex.org/W2097117768","https://openalex.org/W2105101328","https://openalex.org/W2108598243","https://openalex.org/W2117130368","https://openalex.org/W2142194269","https://openalex.org/W2156303437","https://openalex.org/W2507009361","https://openalex.org/W2580899942","https://openalex.org/W2620629206","https://openalex.org/W2706729717"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W147410782","https://openalex.org/W2900413183","https://openalex.org/W4390975304","https://openalex.org/W3022252430","https://openalex.org/W4287804464","https://openalex.org/W3103989898","https://openalex.org/W3211292372","https://openalex.org/W2810679507"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,82],"present":[4],"a":[5,49,65,74,84],"new":[6],"end-to-end":[7],"convolutional":[8],"neural":[9],"network":[10,55],"architecture":[11,39,68,111],"for":[12,27],"video":[13,43],"classification,":[14],"and":[15,21,47,112,124],"apply":[16,48],"the":[17,28,35,54,61,98,104,109,113],"model":[18,88],"to":[19,56],"action":[20,123],"scene":[22,125],"recognition":[23],"in":[24,34,97,122],"untrimmed":[25],"videos":[26],"Challenge":[29],"on":[30,103],"Comprehensive":[31],"Video":[32],"Understanding":[33],"Wild.":[36],"The":[37],"proposed":[38,110],"takes":[40],"densely":[41],"sampled":[42],"frames":[44],"as":[45],"inputs,":[46],"temporal":[50,58,78],"pooling":[51,79],"operator":[52],"inside":[53],"capture":[57],"context":[59],"of":[60,76],"input":[62],"video.":[63],"As":[64],"result,":[66],"our":[67,91],"outputs":[69],"distinct":[70],"video-level":[71,92],"features":[72,93],"with":[73,94],"set":[75],"different":[77],"operators.":[80],"Furthermore,":[81],"design":[83],"multimodal":[85,114],"feature":[86,115],"fusion":[87,116],"by":[89],"concatenating":[90],"those":[95],"given":[96],"challenge":[99,105],"dataset.":[100],"Experimental":[101],"results":[102],"dataset":[106],"demonstrate":[107],"that":[108],"approach":[117],"together":[118],"achieve":[119],"outstanding":[120],"performance":[121],"recognition.":[126]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}