{"id":"https://openalex.org/W2766666366","doi":"https://doi.org/10.1109/avss.2017.8078543","title":"Structured LSTM for human-object interaction detection and anticipation","display_name":"Structured LSTM for human-object interaction detection and anticipation","publication_year":2017,"publication_date":"2017-08-01","ids":{"openalex":"https://openalex.org/W2766666366","doi":"https://doi.org/10.1109/avss.2017.8078543","mag":"2766666366"},"language":"en","primary_location":{"id":"doi:10.1109/avss.2017.8078543","is_oa":false,"landing_page_url":"https://doi.org/10.1109/avss.2017.8078543","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)","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/A5023991597","display_name":"Anh Minh Truong","orcid":"https://orcid.org/0000-0003-2376-927X"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Anh Minh Truong","raw_affiliation_strings":["School of Information Science, Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science, Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100915330","display_name":"Atsuo Yoshitaka","orcid":null},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsuo Yoshitaka","raw_affiliation_strings":["School of Information Science, Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science, Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2771,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.65295703,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9977999925613403,"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.9947999715805054,"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/affordance","display_name":"Affordance","score":0.7512571811676025},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.7394288778305054},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7308487296104431},{"id":"https://openalex.org/keywords/anticipation","display_name":"Anticipation (artificial intelligence)","score":0.7230022549629211},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5999576449394226},{"id":"https://openalex.org/keywords/human-interaction","display_name":"Human interaction","score":0.4865800142288208},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4466281235218048},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.42246368527412415}],"concepts":[{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.7512571811676025},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.7394288778305054},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7308487296104431},{"id":"https://openalex.org/C176777502","wikidata":"https://www.wikidata.org/wiki/Q4774623","display_name":"Anticipation (artificial intelligence)","level":2,"score":0.7230022549629211},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5999576449394226},{"id":"https://openalex.org/C2987082051","wikidata":"https://www.wikidata.org/wiki/Q223642","display_name":"Human interaction","level":2,"score":0.4865800142288208},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4466281235218048},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.42246368527412415},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/avss.2017.8078543","is_oa":false,"landing_page_url":"https://doi.org/10.1109/avss.2017.8078543","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1933657216","https://openalex.org/W1950788856","https://openalex.org/W1976352662","https://openalex.org/W1983705368","https://openalex.org/W1985912834","https://openalex.org/W2018162157","https://openalex.org/W2064675550","https://openalex.org/W2114216982","https://openalex.org/W2126661535","https://openalex.org/W2129947832","https://openalex.org/W2132734311","https://openalex.org/W2146055337","https://openalex.org/W2146502635","https://openalex.org/W2156303437","https://openalex.org/W2307035320","https://openalex.org/W2402406079","https://openalex.org/W2494646816","https://openalex.org/W2952587893","https://openalex.org/W2963165299","https://openalex.org/W3099037876","https://openalex.org/W6640754710","https://openalex.org/W6677265961","https://openalex.org/W6679404632","https://openalex.org/W6681435938","https://openalex.org/W6682864246","https://openalex.org/W6698200468"],"related_works":["https://openalex.org/W1972718289","https://openalex.org/W1791514435","https://openalex.org/W2346831895","https://openalex.org/W2248634132","https://openalex.org/W3049116993","https://openalex.org/W1541884709","https://openalex.org/W2795727972","https://openalex.org/W4386875132","https://openalex.org/W2470899375","https://openalex.org/W2620072267"],"abstract_inverted_index":{"Understanding":[0],"human":[1,22,103,110,118],"activities":[2,23],"is":[3],"one":[4],"of":[5,15,46,61,79,99,117,123,147],"the":[6,42,51,77,115,121,126,162],"important":[7],"tasks":[8],"in":[9,44,95,165],"computer":[10],"vision.":[11],"Although":[12],"a":[13,38,141],"lot":[14],"efforts":[16],"have":[17,56],"been":[18],"made,":[19],"recognizing":[20],"complex":[21],"such":[24],"as":[25,37],"human-object":[26,32,93,106,134,143],"interactions":[27,33,94],"remains":[28],"challenging.":[29],"In":[30,71],"general,":[31],"can":[34],"be":[35],"considered":[36],"temporal":[39,68],"sequence":[40],"with":[41,87,150],"transition":[43],"relationships":[45,82,127],"humans":[47,86],"and":[48,85,91,105,125,155,168],"objects":[49,84,124,129],"over":[50],"time.":[52],"Recently,":[53],"many":[54],"studies":[55],"shown":[57],"sequential":[58],"learning":[59],"power":[60],"Long":[62],"Short-Term":[63],"Memory":[64],"(LSTM)":[65],"for":[66,89,132],"long-term":[67],"dependency":[69],"problems.":[70],"this":[72],"work,":[73],"we":[74,112],"focus":[75],"on":[76,120,140],"problem":[78],"modeling":[80],"spatio-temporal":[81],"between":[83,128],"LSTM":[88],"detecting":[90,167],"anticipating":[92,169],"daily":[96],"life.":[97],"Instead":[98],"considering":[100],"only":[101],"how":[102],"pose":[104],"relations":[107],"change":[108],"during":[109],"activity,":[111],"also":[113],"take":[114],"impact":[116],"activity":[119],"state":[122],"into":[130],"account":[131],"labeling":[133],"interaction.":[135],"We":[136],"evaluated":[137],"our":[138],"method":[139],"challenging":[142],"interaction":[144,170],"dataset":[145],"consisting":[146],"120":[148],"videos":[149],"different":[151],"high-level":[152],"activities,":[153],"sub-activities":[154],"object":[156],"affordances.":[157],"The":[158],"experimental":[159],"results":[160],"showed":[161],"significant":[163],"improvements":[164],"both":[166],"activities.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}