{"id":"https://openalex.org/W2408482550","doi":"https://doi.org/10.1109/icassp.2016.7471995","title":"Towards optimal vlad for human action recognition from still images","display_name":"Towards optimal vlad for human action recognition from still images","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2408482550","doi":"https://doi.org/10.1109/icassp.2016.7471995","mag":"2408482550"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7471995","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7471995","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100701997","display_name":"Lei Zhang","orcid":"https://orcid.org/0000-0001-6892-5067"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Zhang","raw_affiliation_strings":["College of Information and Communication Engineering, Harbin Engineering University, Harbin, PRC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information and Communication Engineering, Harbin Engineering University, Harbin, PRC","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026486701","display_name":"Xiantong Zhen","orcid":"https://orcid.org/0000-0001-5213-0462"},"institutions":[{"id":"https://openalex.org/I125749732","display_name":"Western University","ror":"https://ror.org/02grkyz14","country_code":"CA","type":"education","lineage":["https://openalex.org/I125749732"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Xiantong Zhen","raw_affiliation_strings":["University of Western Ontario, London, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Western Ontario, London, ON, Canada","institution_ids":["https://openalex.org/I125749732"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101508830","display_name":"Jiqing Han","orcid":"https://orcid.org/0000-0002-4297-4300"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiqing Han","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Harbin, PRC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, PRC","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1006,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.34910111,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1841","last_page":"1845"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998999834060669,"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/T10812","display_name":"Human Pose and Action Recognition","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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9986000061035156,"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":0.9973999857902527,"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/ambiguity","display_name":"Ambiguity","score":0.7533397674560547},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7394036650657654},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5910809636116028},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5559751391410828},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.5527787804603577},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.45713624358177185},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4434165954589844},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.44226551055908203},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3834476172924042}],"concepts":[{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.7533397674560547},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7394036650657654},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5910809636116028},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5559751391410828},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.5527787804603577},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.45713624358177185},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4434165954589844},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.44226551055908203},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3834476172924042},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7471995","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7471995","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1606858007","https://openalex.org/W1679894842","https://openalex.org/W1970183457","https://openalex.org/W1979818636","https://openalex.org/W1984309565","https://openalex.org/W1991598519","https://openalex.org/W2012592962","https://openalex.org/W2022625376","https://openalex.org/W2027922120","https://openalex.org/W2037513725","https://openalex.org/W2038765747","https://openalex.org/W2050964073","https://openalex.org/W2059589342","https://openalex.org/W2066364337","https://openalex.org/W2068143350","https://openalex.org/W2117103983","https://openalex.org/W2118585731","https://openalex.org/W2131846894","https://openalex.org/W2155490028","https://openalex.org/W2162915993","https://openalex.org/W2169177311","https://openalex.org/W2171896402","https://openalex.org/W2179553611","https://openalex.org/W6636412649","https://openalex.org/W6645258248","https://openalex.org/W6648368125","https://openalex.org/W6667221643","https://openalex.org/W6677656871","https://openalex.org/W6685292306"],"related_works":["https://openalex.org/W2353179089","https://openalex.org/W2923538289","https://openalex.org/W2353125546","https://openalex.org/W2470643824","https://openalex.org/W4400595174","https://openalex.org/W2349635380","https://openalex.org/W4353089801","https://openalex.org/W2353819554","https://openalex.org/W1576128429","https://openalex.org/W2269464716"],"abstract_inverted_index":{"Human":[0],"action":[1,74,170],"recognition":[2,75,171],"from":[3,76,172],"still":[4,77,173],"image":[5,42],"has":[6,36,106],"recently":[7],"drawn":[8],"increasing":[9],"attention":[10],"in":[11,40,87],"human":[12,73,169],"behavior":[13],"analysis":[14],"vision":[15],"and":[16,27,62,92,105,115,145],"also":[17],"poses":[18],"great":[19,50],"challenges":[20],"due":[21,56],"to":[22,57,120,136,163],"the":[23,101,112,127,138,165],"huge":[24],"inter":[25],"ambiguity":[26],"intra":[28],"variability.":[29],"Vector":[30],"of":[31,52,103,129],"locally":[32],"aggregated":[33],"descriptors":[34],"(VLAD)":[35],"achieved":[37],"state-of-the-art":[38,181],"performance":[39,102,128,179],"many":[41],"classification":[43],"tasks":[44],"based":[45],"on":[46,159],"local":[47],"features.":[48],"The":[49,95],"success":[51],"VLAD":[53,70,81,88,104],"is":[54],"largely":[55,125],"its":[58],"high":[59],"descriptive":[60],"ability":[61],"computational":[63],"efficiency.":[64],"In":[65],"this":[66],"paper,":[67],"towards":[68],"optimal":[69],"representations":[71],"for":[72,151,168],"images,":[78],"we":[79,131],"improve":[80],"by":[82],"tackling":[83],"two":[84,160],"important":[85],"issues":[86],"including":[89],"empty":[90,96,113],"cavity":[91,97,114],"assignment":[93,139],"ambiguity.":[94],"issue":[98],"severely":[99],"compromises":[100],"long":[107],"been":[108],"overlooked.":[109],"We":[110,154],"investigate":[111],"provide":[116,147],"an":[117],"effective":[118],"solution":[119],"deal":[121],"with":[122,180],"it,":[123],"which":[124,141],"improves":[126],"VLAD;":[130],"propose":[132],"middle":[133],"level":[134],"assignments":[135],"conquer":[137],"ambiguity,":[140],"are":[142],"more":[143,148],"reliable":[144],"can":[146],"useful":[149],"information":[150],"realistic":[152],"activity.":[153],"have":[155],"conducted":[156],"extensive":[157],"experiments":[158],"widely-used":[161],"benchmarks":[162],"validate":[164],"proposed":[166],"method":[167,176],"images.":[174],"Our":[175],"produces":[177],"competitive":[178],"algorithms.":[182]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}