{"id":"https://openalex.org/W3195977921","doi":"https://doi.org/10.1109/icip42928.2021.9506078","title":"Enhancing Multi-Step Action Prediction for Active Object Detection","display_name":"Enhancing Multi-Step Action Prediction for Active Object Detection","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W3195977921","doi":"https://doi.org/10.1109/icip42928.2021.9506078","mag":"3195977921"},"language":"en","primary_location":{"id":"doi:10.1109/icip42928.2021.9506078","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip42928.2021.9506078","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Image Processing (ICIP)","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/A5030374805","display_name":"Fen Fang","orcid":"https://orcid.org/0000-0002-3834-4795"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Fen Fang","raw_affiliation_strings":["Institute for Infocomm Research,A*STAR,Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research,A*STAR,Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052143634","display_name":"Qianli Xu","orcid":"https://orcid.org/0000-0003-0105-5903"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Qianli Xu","raw_affiliation_strings":["Institute for Infocomm Research,A*STAR,Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research,A*STAR,Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036812295","display_name":"Nicolas Gauthier","orcid":"https://orcid.org/0000-0002-2225-5827"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Nicolas Gauthier","raw_affiliation_strings":["Institute for Infocomm Research,A*STAR,Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research,A*STAR,Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101524913","display_name":"Liyuan Li","orcid":"https://orcid.org/0000-0002-3758-1975"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Liyuan Li","raw_affiliation_strings":["Institute for Infocomm Research,A*STAR,Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research,A*STAR,Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077258552","display_name":"Joo\u2010Hwee Lim","orcid":"https://orcid.org/0000-0002-4103-3824"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Joo-Hwee Lim","raw_affiliation_strings":["Institute for Infocomm Research,A*STAR,Singapore","School of Computer Science and Engineering, NTU, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research,A*STAR,Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]},{"raw_affiliation_string":"School of Computer Science and Engineering, NTU, Singapore","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5030374805"],"corresponding_institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"],"apc_list":null,"apc_paid":null,"fwci":0.3843,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.6070098,"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":"2189","last_page":"2193"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9969000220298767,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9969000220298767,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9950000047683716,"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"}},{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","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/computer-science","display_name":"Computer science","score":0.7626124620437622},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.7575157880783081},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7522746324539185},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6706684827804565},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6522293090820312},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5628448724746704},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.535695493221283},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5234664678573608},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4707185626029968},{"id":"https://openalex.org/keywords/outcome","display_name":"Outcome (game theory)","score":0.44316643476486206},{"id":"https://openalex.org/keywords/active-vision","display_name":"Active vision","score":0.4138597548007965},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2517222464084625},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11597555875778198},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09889918565750122}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7626124620437622},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.7575157880783081},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7522746324539185},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6706684827804565},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6522293090820312},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5628448724746704},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.535695493221283},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5234664678573608},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4707185626029968},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.44316643476486206},{"id":"https://openalex.org/C193611912","wikidata":"https://www.wikidata.org/wiki/Q4677596","display_name":"Active vision","level":2,"score":0.4138597548007965},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2517222464084625},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11597555875778198},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09889918565750122},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.0},{"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/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"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/icip42928.2021.9506078","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip42928.2021.9506078","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1686810756","https://openalex.org/W2031060683","https://openalex.org/W2194775991","https://openalex.org/W2201581102","https://openalex.org/W2580726517","https://openalex.org/W2593769898","https://openalex.org/W2615790994","https://openalex.org/W2736057540","https://openalex.org/W2769883686","https://openalex.org/W2793770935","https://openalex.org/W2899771611","https://openalex.org/W2907503094","https://openalex.org/W2946469828","https://openalex.org/W2964112854","https://openalex.org/W3006359196","https://openalex.org/W3013821552","https://openalex.org/W3081310128","https://openalex.org/W3085046840","https://openalex.org/W3091317905","https://openalex.org/W3106250896","https://openalex.org/W3106539628","https://openalex.org/W6620707391","https://openalex.org/W6637373629","https://openalex.org/W6687681856","https://openalex.org/W6738596827","https://openalex.org/W6746605513","https://openalex.org/W6756040250","https://openalex.org/W6771876938","https://openalex.org/W6775647304","https://openalex.org/W6783097568","https://openalex.org/W6785652829"],"related_works":["https://openalex.org/W2978999882","https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W2920098477","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2586732548"],"abstract_inverted_index":{"Active":[0],"vision":[1],"for":[2],"robots":[3],"is":[4,17],"one":[5],"promising":[6],"solution":[7],"to":[8,25,30,83,106,112],"open":[9],"world":[10],"visual":[11],"detection":[12,54,141],"problems.":[13],"A":[14],"fundamental":[15],"issue":[16],"view":[18,47,136],"planning,":[19,48],"i.e.,":[20],"predicting":[21],"next":[22],"best":[23],"views":[24],"capture":[26],"images":[27],"of":[28,46,59,62,116],"interest":[29],"reduce":[31],"uncertainty.":[32],"While":[33],"multi-step":[34],"action":[35,63,66,69,85,88,107,110],"in":[36,135],"a":[37,80,91,96],"reinforcement":[38],"learning":[39],"(RL)":[40],"setup":[41],"can":[42],"boost":[43],"the":[44,57],"efficiency":[45],"existing":[49],"methods":[50],"suffer":[51],"from":[52,87],"unstable":[53],"outcome":[55],"when":[56],"Q-values":[58],"multiple":[60],"branches":[61],"advantages":[64],"(i.e.,":[65],"range":[67,86,108],"and":[68,109,128],"type)":[70],"are":[71],"combined":[72],"naively.":[73],"To":[74],"tackle":[75],"this":[76],"issue,":[77],"we":[78],"propose":[79],"novel":[81],"mechanism":[82],"disentangle":[84],"type":[89,111],"through":[90],"two-stage":[92],"training":[93,115],"strategy":[94],"on":[95,124],"deep":[97],"Q-network.":[98],"It":[99],"combines":[100],"well-crafted":[101],"loss":[102],"functions":[103],"with":[104],"respect":[105],"enforce":[113],"separated":[114],"these":[117],"two":[118,125],"branches.":[119],"We":[120],"evaluate":[121],"our":[122],"method":[123],"public":[126],"datasets":[127],"show":[129],"that":[130],"it":[131],"facilitates":[132],"substantial":[133],"gain":[134],"planning":[137],"efficiency,":[138],"while":[139],"enhancing":[140],"accuracy.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}