{"id":"https://openalex.org/W2765938137","doi":"https://doi.org/10.1145/3123266.3123362","title":"Detecting Temporal Proposal for Action Localization with Tree-structured Search Policy","display_name":"Detecting Temporal Proposal for Action Localization with Tree-structured Search Policy","publication_year":2017,"publication_date":"2017-10-19","ids":{"openalex":"https://openalex.org/W2765938137","doi":"https://doi.org/10.1145/3123266.3123362","mag":"2765938137"},"language":"en","primary_location":{"id":"doi:10.1145/3123266.3123362","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3123266.3123362","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th 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/A5011424573","display_name":"Xinyang Jiang","orcid":"https://orcid.org/0000-0002-4991-0596"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xinyang Jiang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063062444","display_name":"Siliang Tang","orcid":"https://orcid.org/0000-0002-7356-9711"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siliang Tang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397616","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0002-5070-4511"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079260216","display_name":"Zhou Zhao","orcid":"https://orcid.org/0000-0001-6121-0384"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Zhao","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100343712","display_name":"Yin Zhang\u22c6","orcid":"https://orcid.org/0000-0002-1772-0763"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yin Zhang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004882141","display_name":"Fei Wu","orcid":"https://orcid.org/0000-0003-2139-8807"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Wu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008666077","display_name":"Yueting Zhuang","orcid":"https://orcid.org/0000-0001-9017-2508"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yueting Zhuang","raw_affiliation_strings":["Zhejiang University, Hangzhou, Colombia"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, Colombia","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5011424573"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14987325,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1069","last_page":"1077"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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":0.9986000061035156,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.8814406394958496},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.790389895439148},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6177265644073486},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6033762097358704},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5724639296531677},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5332337021827698},{"id":"https://openalex.org/keywords/sliding-window-protocol","display_name":"Sliding window protocol","score":0.524392306804657},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.5118443369865417},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.496664822101593},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.46103596687316895},{"id":"https://openalex.org/keywords/visual-search","display_name":"Visual search","score":0.44187551736831665},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.418606162071228},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41609904170036316},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.35340073704719543},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33991342782974243},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08330392837524414}],"concepts":[{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.8814406394958496},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.790389895439148},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6177265644073486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6033762097358704},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5724639296531677},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5332337021827698},{"id":"https://openalex.org/C102392041","wikidata":"https://www.wikidata.org/wiki/Q592860","display_name":"Sliding window protocol","level":3,"score":0.524392306804657},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.5118443369865417},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.496664822101593},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.46103596687316895},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.44187551736831665},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.418606162071228},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41609904170036316},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.35340073704719543},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33991342782974243},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08330392837524414},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3123266.3123362","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3123266.3123362","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1923332106","https://openalex.org/W1927052826","https://openalex.org/W1950136256","https://openalex.org/W2010181071","https://openalex.org/W2018068650","https://openalex.org/W2033740597","https://openalex.org/W2088049833","https://openalex.org/W2102605133","https://openalex.org/W2105101328","https://openalex.org/W2131042978","https://openalex.org/W2133858838","https://openalex.org/W2145339207","https://openalex.org/W2156303437","https://openalex.org/W2179488730","https://openalex.org/W2292288263","https://openalex.org/W2407521645","https://openalex.org/W2469312016","https://openalex.org/W2567210518","https://openalex.org/W2953106684","https://openalex.org/W2963321993","https://openalex.org/W2964214371","https://openalex.org/W3103081334"],"related_works":["https://openalex.org/W2329500892","https://openalex.org/W28991112","https://openalex.org/W2370726991","https://openalex.org/W2109115373","https://openalex.org/W2390901981","https://openalex.org/W2369710579","https://openalex.org/W2353818951","https://openalex.org/W4327728159","https://openalex.org/W3158447592","https://openalex.org/W3014558862"],"abstract_inverted_index":{"Understanding":[0],"the":[1,47,89,100,107,121,129,142],"semantics":[2,24],"in":[3,11,25,94],"videos":[4],"is":[5,116,135,150],"a":[6,41,56,63,67,84,95,114,132,158],"complex":[7],"but":[8],"crucial":[9],"task":[10],"video":[12,52,75,92,103],"analysis.":[13],"This":[14],"paper":[15],"focuses":[16],"on":[17,88],"localizing":[18],"category-independent":[19],"events,":[20],"actions":[21],"or":[22],"other":[23],"an":[26,78],"untrimmed":[27],"video,":[28],"referred":[29],"as":[30],"salient":[31,85,125,139,155],"temporal":[32],"proposal":[33,86,108,133,140],"localization.":[34],"Traditional":[35],"methods":[36],"like":[37],"sliding":[38],"window":[39],"have":[40],"high":[42],"computational":[43],"cost":[44],"due":[45],"to":[46,82,118,127,137,152],"densely":[48],"sampling":[49],"of":[50,72,102],"different":[51],"segments.":[53],"We":[54],"propose":[55],"reinforcement":[57],"learning":[58],"based":[59,87],"method,":[60],"which":[61],"trains":[62],"localizer":[64,115],"that":[65,147],"learns":[66],"search":[68,80,112],"policy":[69],"that,":[70],"instead":[71],"exploring":[73],"every":[74],"segment,":[76],"finds":[77],"optimal":[79],"path":[81],"locate":[83],"currently":[90],"observing":[91],"segment":[93],"tree":[96],"structure,":[97],"therefore":[98],"reduces":[99],"number":[101],"segments":[104],"fed":[105],"into":[106],"detector.":[109],"In":[110],"each":[111],"step,":[113],"trained":[117,136],"iteratively":[119],"select":[120],"next":[122],"sub-region":[123],"containing":[124],"proposals":[126,156],"continue":[128],"search,":[130],"and":[131,161],"detector":[134],"recognize":[138],"from":[141],"sub-regions.":[143],"The":[144],"experiments":[145],"demonstrate":[146],"our":[148],"method":[149],"able":[151],"precisely":[153],"detect":[154],"with":[157,162],"comparable":[159],"recall":[160],"much":[163],"fewer":[164],"candidate":[165],"windows.":[166]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}