{"id":"https://openalex.org/W2527457059","doi":"https://doi.org/10.1145/2964284.2967199","title":"Exploiting Objects with LSTMs for Video Categorization","display_name":"Exploiting Objects with LSTMs for Video Categorization","publication_year":2016,"publication_date":"2016-09-29","ids":{"openalex":"https://openalex.org/W2527457059","doi":"https://doi.org/10.1145/2964284.2967199","mag":"2527457059"},"language":"en","primary_location":{"id":"doi:10.1145/2964284.2967199","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2964284.2967199","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM international conference on Multimedia","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/A5100355570","display_name":"Yongqing Sun","orcid":"https://orcid.org/0000-0003-3116-2371"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yongqing Sun","raw_affiliation_strings":["NTT Media Intelligence Laboratories, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026167547","display_name":"Zuxuan Wu","orcid":"https://orcid.org/0000-0002-8689-5807"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zuxuan Wu","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101875912","display_name":"Xi Wang","orcid":"https://orcid.org/0000-0001-8918-7905"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Wang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061864794","display_name":"Hiroyuki Arai","orcid":"https://orcid.org/0000-0002-1057-3641"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroyuki Arai","raw_affiliation_strings":["NTT Media Intelligence Laboratories, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026941386","display_name":"Tetsuya Kinebuchi","orcid":"https://orcid.org/0000-0002-4255-2642"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuya Kinebuchi","raw_affiliation_strings":["NTT Media Intelligence Laboratories, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047962986","display_name":"Yu\u2013Gang Jiang","orcid":"https://orcid.org/0000-0002-1907-8567"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Gang Jiang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4916,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.88262283,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"142","last_page":"146"},"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9988999962806702,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8646076917648315},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.8075531721115112},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.7549573183059692},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.712982714176178},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4146963059902191},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3798145353794098},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3363944888114929}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8646076917648315},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.8075531721115112},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.7549573183059692},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.712982714176178},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4146963059902191},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3798145353794098},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3363944888114929}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2964284.2967199","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2964284.2967199","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320335773","display_name":"National High-tech Research and Development Program","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W1947481528","https://openalex.org/W1965555842","https://openalex.org/W2016053056","https://openalex.org/W2079735306","https://openalex.org/W2095242101","https://openalex.org/W2097117768","https://openalex.org/W2102605133","https://openalex.org/W2105101328","https://openalex.org/W2108598243","https://openalex.org/W2142194269","https://openalex.org/W2143612262","https://openalex.org/W2156303437","https://openalex.org/W2156406284","https://openalex.org/W2161565164","https://openalex.org/W2342662179","https://openalex.org/W2473032611","https://openalex.org/W2563717578","https://openalex.org/W2618530766","https://openalex.org/W2952453038","https://openalex.org/W2962835968"],"related_works":["https://openalex.org/W2165912799","https://openalex.org/W2735662278","https://openalex.org/W2382615723","https://openalex.org/W4311804456","https://openalex.org/W1987484445","https://openalex.org/W2623658258","https://openalex.org/W2143413548","https://openalex.org/W1969219540","https://openalex.org/W2370459448","https://openalex.org/W2105067402"],"abstract_inverted_index":{"Temporal":[0],"dynamics":[1,75],"play":[2],"an":[3,35],"important":[4],"role":[5],"for":[6,88,110],"video":[7,90],"classification.":[8],"In":[9,78],"this":[10],"paper,":[11],"we":[12,44,62,85,97],"propose":[13],"to":[14,19,37,57,71],"leverage":[15,63],"high-level":[16],"semantic":[17],"features":[18,48,68],"open":[20],"the":[21,25,66,73,95,116,121],"\"black":[22],"box\"":[23],"of":[24,124],"state-of-the-art":[26,51],"temporal":[27,74,122],"model,":[28],"Long":[29],"Short":[30],"Term":[31],"Memory":[32],"(LSTM),":[33],"with":[34,65,80],"aim":[36],"understand":[38],"what":[39,99],"is":[40,55,100],"learned.":[41],"More":[42],"specifically,":[43],"first":[45],"extract":[46],"object":[47],"from":[49],"a":[50,112],"CNN":[52],"model":[53,118],"that":[54],"trained":[56],"recognize":[58],"20K":[59],"objects.":[60,127],"Then":[61],"LSTM":[64,117],"extracted":[67],"as":[69],"inputs":[70],"capture":[72],"in":[76],"videos.":[77],"combination":[79],"spatial":[81],"and":[82],"motion":[83],"information,":[84],"achieve":[86],"improvements":[87],"supervised":[89],"categorization.":[91],"Furthermore,":[92],"by":[93,102],"masking":[94],"inputs,":[96],"demonstrate":[98],"learned":[101],"LSTM,":[103],"namely":[104],"(i)":[105],"which":[106],"objects":[107],"are":[108],"crucial":[109],"recognizing":[111],"class-of-interest;":[113],"(ii)":[114],"how":[115],"could":[119],"assist":[120],"localization":[123],"these":[125],"detected":[126]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}