{"id":"https://openalex.org/W2937503616","doi":"https://doi.org/10.1109/icassp.2019.8682392","title":"Image Captioning with Two Cascaded Agents","display_name":"Image Captioning with Two Cascaded Agents","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2937503616","doi":"https://doi.org/10.1109/icassp.2019.8682392","mag":"2937503616"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682392","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682392","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5108745013","display_name":"Lun Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lun Huang","raw_affiliation_strings":["SECE, Shenzhen Graduate School, Peking University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SECE, Shenzhen Graduate School, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017052768","display_name":"Wenmin Wang","orcid":"https://orcid.org/0000-0003-2664-4413"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenmin Wang","raw_affiliation_strings":["SECE, Shenzhen Graduate School, Peking University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SECE, Shenzhen Graduate School, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100652027","display_name":"Gang Wang","orcid":"https://orcid.org/0000-0002-4620-6931"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Wang","raw_affiliation_strings":["SECE, Shenzhen Graduate School, Peking University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SECE, Shenzhen Graduate School, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"8693","issue":null,"first_page":"4110","last_page":"4114"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9973000288009644,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9900000095367432,"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":0.9777541160583496},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8769073486328125},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7560805082321167},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.668106734752655},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6516679525375366},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6318813562393188},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6180485486984253},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5237626433372498},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5206584334373474},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5193806290626526},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.46994832158088684},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45157307386398315},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33538782596588135},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3229385018348694},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16785800457000732},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08527913689613342}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9777541160583496},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8769073486328125},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7560805082321167},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.668106734752655},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6516679525375366},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6318813562393188},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6180485486984253},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5237626433372498},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5206584334373474},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5193806290626526},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.46994832158088684},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45157307386398315},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33538782596588135},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3229385018348694},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16785800457000732},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08527913689613342},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682392","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682392","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W8316075","https://openalex.org/W639708223","https://openalex.org/W648786980","https://openalex.org/W1484210532","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1858383477","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1931639407","https://openalex.org/W1956340063","https://openalex.org/W1969616664","https://openalex.org/W2101105183","https://openalex.org/W2119717200","https://openalex.org/W2123301721","https://openalex.org/W2147527908","https://openalex.org/W2154652894","https://openalex.org/W2176263492","https://openalex.org/W2506483933","https://openalex.org/W2575842049","https://openalex.org/W2745461083","https://openalex.org/W2832876791","https://openalex.org/W2890531016","https://openalex.org/W2951527505","https://openalex.org/W2963084599","https://openalex.org/W2963248296","https://openalex.org/W2964036520","https://openalex.org/W2964121744","https://openalex.org/W6600334730","https://openalex.org/W6621543089","https://openalex.org/W6628927728","https://openalex.org/W6630875275","https://openalex.org/W6631190155","https://openalex.org/W6639102338","https://openalex.org/W6639118148","https://openalex.org/W6682137061","https://openalex.org/W6685322675","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W2368824897","https://openalex.org/W1508050556","https://openalex.org/W1910862367","https://openalex.org/W1950940422","https://openalex.org/W2379365082","https://openalex.org/W2370747590","https://openalex.org/W2030109976","https://openalex.org/W2369260257","https://openalex.org/W2129146436","https://openalex.org/W2389120450"],"abstract_inverted_index":{"Recent":[0],"neural":[1],"models":[2],"on":[3,159],"image":[4,59],"captioning":[5,60],"usually":[6],"take":[7],"a":[8,15,30,53,57,100,134],"encoder-decoder":[9],"fashion,":[10],"where":[11],"the":[12,23,36,38,43,48,77,80,84,87,92,104,107,110,116,119,123,126,140],"decoder":[13,81,111],"predicts":[14],"single":[16,101],"word":[17,102],"at":[18],"one":[19],"step":[20],"recently":[21],"with":[22,143],"encoder":[24,28],"providing":[25],"information.":[26],"The":[27,67],"is":[29,69],"pretrained":[31],"CNN":[32],"model":[33],"typically.":[34],"Thus":[35],"decoder,":[37],"input":[39,78,117],"to":[40,79,138],"it,":[41],"and":[42,91,118,156,163],"output":[44,108],"from":[45,86],"it":[46],"become":[47],"most":[49],"important":[50],"parts":[51],"of":[52,63,103,109,115,122,128,173],"model.":[54],"We":[55],"propose":[56],"pipelined":[58],"framework":[61,127],"consisting":[62],"two":[64,129,141],"cascaded":[65,130],"agents.":[66],"former":[68],"named":[70],"as":[71,94,106],"\"semantic":[72],"adaptive":[73],"agent\"":[74,97],"which":[75,98],"generates":[76],"by":[82,112,146],"consulting":[83],"information":[85],"current":[88,120],"decoding":[89],"process,":[90],"latter":[93],"\"caption":[95],"generating":[96],"select":[99],"vocabulary":[105],"taking":[113],"consideration":[114],"states":[121],"decoder.":[124],"For":[125],"agents,":[131],"we":[132,153],"design":[133],"multi-stage":[135],"training":[136],"procedure":[137],"train":[139],"agents":[142],"different":[144],"objectives":[145],"fully":[147],"utilizing":[148],"reinforcement":[149],"learning.":[150],"In":[151],"experiments,":[152],"conduct":[154],"quantitative":[155],"qualitative":[157],"analysis":[158],"MS":[160],"COCO":[161],"dataset":[162],"our":[164],"results":[165],"can":[166],"significantly":[167],"outperform":[168],"baseline":[169],"methods":[170],"in":[171],"terms":[172],"several":[174],"evaluation":[175],"metrics.":[176]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}