{"id":"https://openalex.org/W3034150475","doi":"https://doi.org/10.1145/3372278.3390679","title":"Actor-Critic Sequence Generation for Relative Difference Captioning","display_name":"Actor-Critic Sequence Generation for Relative Difference Captioning","publication_year":2020,"publication_date":"2020-06-02","ids":{"openalex":"https://openalex.org/W3034150475","doi":"https://doi.org/10.1145/3372278.3390679","mag":"3034150475"},"language":"en","primary_location":{"id":"doi:10.1145/3372278.3390679","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3372278.3390679","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 International Conference on Multimedia Retrieval","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/A5020427859","display_name":"Zhengcong Fei","orcid":"https://orcid.org/0000-0001-5980-0879"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhengcong Fei","raw_affiliation_strings":["Institute of Computing Technology, CAS & University of Chinese Academy of Science, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, CAS & University of Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5020427859"],"corresponding_institution_ids":["https://openalex.org/I4210090176"],"apc_list":null,"apc_paid":null,"fwci":0.7816,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.73845533,"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":"100","last_page":"107"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T11714","display_name":"Multimodal Machine Learning Applications","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/T10812","display_name":"Human Pose and Action Recognition","score":0.9962999820709229,"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":0.9866999983787537,"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/closed-captioning","display_name":"Closed captioning","score":0.9287823438644409},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.8337103128433228},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7887449860572815},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6363840103149414},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5282971858978271},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4984276294708252},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4541586637496948},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.445789635181427},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4426718056201935},{"id":"https://openalex.org/keywords/value-network","display_name":"Value network","score":0.4255565106868744},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.41850197315216064},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4170563220977783},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38804084062576294},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.21489858627319336},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11577498912811279},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08275452256202698}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9287823438644409},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.8337103128433228},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7887449860572815},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6363840103149414},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5282971858978271},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4984276294708252},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4541586637496948},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.445789635181427},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4426718056201935},{"id":"https://openalex.org/C89249532","wikidata":"https://www.wikidata.org/wiki/Q7912758","display_name":"Value network","level":3,"score":0.4255565106868744},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.41850197315216064},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4170563220977783},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38804084062576294},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.21489858627319336},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11577498912811279},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08275452256202698},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"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/C4216890","wikidata":"https://www.wikidata.org/wiki/Q815823","display_name":"Business model","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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:10.1145/3372278.3390679","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3372278.3390679","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7400000095367432,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1515851193","https://openalex.org/W1895577753","https://openalex.org/W1969616664","https://openalex.org/W2079125479","https://openalex.org/W2101105183","https://openalex.org/W2117539524","https://openalex.org/W2119717200","https://openalex.org/W2552161745","https://openalex.org/W2574790321","https://openalex.org/W2603266952","https://openalex.org/W2607151106","https://openalex.org/W2610366607","https://openalex.org/W2745461083","https://openalex.org/W2890531016","https://openalex.org/W2895692661","https://openalex.org/W2962887844","https://openalex.org/W2963084599","https://openalex.org/W2963448089","https://openalex.org/W2964018924","https://openalex.org/W3171399186","https://openalex.org/W6629956336"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2993670781","https://openalex.org/W2768698792","https://openalex.org/W3201942433"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"a":[3,14,28,50,56,60,64,70,99,122],"new":[4],"task":[5,30],"named":[6],"relative":[7],"difference":[8,19,71],"caption":[9],"which":[10,54],"aims":[11],"to":[12,16,67,81,101,108],"generate":[13],"sentence":[15],"tell":[17],"the":[18,21,74,83,90,94,132,137],"between":[20],"given":[22],"image":[23],"pair.":[24],"Difference":[25],"description":[26],"is":[27],"crucial":[29],"for":[31],"developing":[32],"intelligent":[33],"machines":[34],"that":[35,46],"can":[36],"understand":[37],"and":[38,43,59,93,111,117,147],"handle":[39],"changeable":[40],"visual":[41],"scenes":[42],"applications.":[44],"Towards":[45],"end,":[47],"we":[48,120],"propose":[49],"reinforcement":[51],"learning-based":[52],"model,":[53],"utilizes":[55],"policy":[57,75],"network":[58,62,76,96],"value":[61,95],"in":[63,142],"decision":[65],"procedure":[66],"collaboratively":[68],"produce":[69],"caption.":[72],"Specifically,":[73],"works":[77],"as":[78,98,127],"an":[79],"actor":[80],"estimate":[82],"probability":[84],"of":[85,139],"next":[86],"word":[87],"based":[88],"on":[89,131],"current":[91,109],"state":[92],"serves":[97],"critic":[100],"predict":[102],"all":[103],"possible":[104],"extension":[105],"values":[106],"according":[107],"action":[110],"state.":[112],"To":[113],"encourage":[114],"generating":[115],"correct":[116],"meaningful":[118],"descriptions,":[119],"leverage":[121],"visual-linguistic":[123],"similarity-based":[124],"reward":[125],"function":[126],"feedback.":[128],"Empirical":[129],"results":[130],"recently":[133],"released":[134],"dataset":[135],"demonstrate":[136],"effectiveness":[138],"our":[140],"method":[141],"comparison":[143],"with":[144],"various":[145],"baselines":[146],"model":[148],"variants.":[149]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}