{"id":"https://openalex.org/W2969136062","doi":"https://doi.org/10.1145/3336495","title":"Pseudo-3D Attention Transfer Network with Content-aware Strategy for Image Captioning","display_name":"Pseudo-3D Attention Transfer Network with Content-aware Strategy for Image Captioning","publication_year":2019,"publication_date":"2019-08-08","ids":{"openalex":"https://openalex.org/W2969136062","doi":"https://doi.org/10.1145/3336495","mag":"2969136062"},"language":"en","primary_location":{"id":"doi:10.1145/3336495","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3336495","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-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/A5101706210","display_name":"Jie Wu","orcid":"https://orcid.org/0000-0003-4611-1083"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jie Wu","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056953478","display_name":"Haifeng Hu","orcid":"https://orcid.org/0000-0002-4884-323X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haifeng Hu","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-4884-323X","affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110539042","display_name":"Liang Yang","orcid":"https://orcid.org/0000-0001-9012-3669"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Yang","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101706210"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":0.6123,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.72581738,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"15","issue":"3","first_page":"1","last_page":"19"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9975000023841858,"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":0.9836000204086304,"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":0.9231864213943481},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8259726762771606},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.7039902210235596},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6374002695083618},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6212604641914368},{"id":"https://openalex.org/keywords/attention-network","display_name":"Attention network","score":0.5887842774391174},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5680465698242188},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5389964580535889},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5247328877449036},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5195274949073792},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5105711221694946},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.48133859038352966},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.46712690591812134},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4595663845539093},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.433010458946228}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9231864213943481},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8259726762771606},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7039902210235596},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6374002695083618},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6212604641914368},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.5887842774391174},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5680465698242188},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5389964580535889},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5247328877449036},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5195274949073792},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5105711221694946},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.48133859038352966},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.46712690591812134},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4595663845539093},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.433010458946228},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3336495","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3336495","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.49000000953674316,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1786224844","display_name":null,"funder_award_id":"61673402, 61273270, and 60802069","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4228998522","display_name":null,"funder_award_id":"2017A030311029","funder_id":"https://openalex.org/F4320321921","funder_display_name":"Natural Science Foundation of Guangdong Province"},{"id":"https://openalex.org/G6618701442","display_name":null,"funder_award_id":"17lgzd08","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W648786980","https://openalex.org/W1514535095","https://openalex.org/W1527575280","https://openalex.org/W1665214252","https://openalex.org/W1686810756","https://openalex.org/W1706899115","https://openalex.org/W1773149199","https://openalex.org/W1895577753","https://openalex.org/W1895989618","https://openalex.org/W1905882502","https://openalex.org/W1931639407","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W1973321600","https://openalex.org/W2064675550","https://openalex.org/W2097117768","https://openalex.org/W2101105183","https://openalex.org/W2117539524","https://openalex.org/W2123301721","https://openalex.org/W2133564696","https://openalex.org/W2154652894","https://openalex.org/W2194775991","https://openalex.org/W2220981600","https://openalex.org/W2302086703","https://openalex.org/W2506483933","https://openalex.org/W2544271936","https://openalex.org/W2549365021","https://openalex.org/W2550553598","https://openalex.org/W2560674852","https://openalex.org/W2575842049","https://openalex.org/W2600463316","https://openalex.org/W2618530766","https://openalex.org/W2745461083","https://openalex.org/W2752047430","https://openalex.org/W2752465200","https://openalex.org/W2786849550","https://openalex.org/W2788527657","https://openalex.org/W2883112830","https://openalex.org/W2890531016","https://openalex.org/W2915236254","https://openalex.org/W2941127321","https://openalex.org/W2949376505","https://openalex.org/W2962706528","https://openalex.org/W2963084599","https://openalex.org/W2963446712","https://openalex.org/W3103022576","https://openalex.org/W3103806448","https://openalex.org/W4236965008"],"related_works":["https://openalex.org/W3135818718","https://openalex.org/W3091976719","https://openalex.org/W3012393889","https://openalex.org/W3018421652","https://openalex.org/W3192840557","https://openalex.org/W4366224123","https://openalex.org/W3021430260","https://openalex.org/W4285149559","https://openalex.org/W3209355071","https://openalex.org/W2767651786"],"abstract_inverted_index":{"In":[0],"this":[1],"article,":[2],"we":[3,43,122,166],"propose":[4,44],"a":[5,171,194],"novel":[6],"Pseudo-3D":[7,28],"Attention":[8,29],"Transfer":[9,34],"network":[10,126,152],"with":[11,102,112,197],"Content-aware":[12,39],"Strategy":[13,40],"(P3DAT-CAS)":[14],"for":[15,177],"the":[16,27,32,38,68,124,131,142,190,202,215,234],"image":[17,198],"captioning":[18,181],"task.":[19],"Our":[20],"model":[21,182],"is":[22,105,153,211,221],"composed":[23],"of":[24,50],"three":[25],"parts:":[26],"(P3DA)":[30],"network,":[31,36],"P3DA-based":[33],"(P3DAT)":[35],"and":[37,58,92,116,129,160,174,207,225,227],"(CAS).":[41],"First,":[42],"P3DA":[45,104],"to":[46,76,107,127,146,155,169,213],"take":[47],"full":[48],"advantage":[49],"three-dimensional":[51],"(3D)":[52],"information":[53,145],"in":[54,201],"convolutional":[55,73,87],"feature":[56,74,88],"maps":[57,75,89,111],"capture":[59],"more":[60,83,118,172],"details.":[61],"Most":[62],"existing":[63],"attention-based":[64,138],"models":[65],"only":[66,140],"extract":[67],"2D":[69,109],"spatial":[70,110],"representation":[71],"from":[72],"decide":[77],"which":[78],"area":[79],"should":[80],"be":[81],"paid":[82],"attention":[84,134,144,158],"to.":[85],"However,":[86,209],"are":[90],"3D":[91],"different":[93],"channel":[94],"features":[95],"can":[96],"detect":[97],"diverse":[98],"semantic":[99],"attributes":[100,115],"associated":[101],"images.":[103],"proposed":[106],"combine":[108],"1D":[113],"semantic-channel":[114],"generate":[117,189],"informative":[119],"captions.":[120],"Second,":[121],"design":[123],"transfer":[125,130,151],"maintain":[128],"key":[132],"previous":[133],"information.":[135],"The":[136,180],"traditional":[137],"approaches":[139],"utilize":[141],"current":[143],"predict":[147],"words":[148],"directly,":[149],"whereas":[150],"able":[154],"learn":[156],"long-term":[157],"dependencies":[159],"explore":[161],"global":[162],"modeling":[163],"pattern.":[164],"Finally,":[165],"present":[167],"CAS":[168,210],"provide":[170],"relevant":[173],"distinct":[175],"caption":[176],"each":[178],"image.":[179],"trained":[183],"by":[184],"maximum":[185],"likelihood":[186],"estimation":[187],"may":[188],"captions":[191],"that":[192],"have":[193],"weak":[195],"correlation":[196],"contents,":[199],"resulting":[200],"cross-modal":[203],"gap":[204],"between":[205],"vision":[206],"linguistics.":[208],"helpful":[212],"convey":[214],"meaningful":[216],"visual":[217],"contents":[218],"accurately.":[219],"P3DAT-CAS":[220],"evaluated":[222],"on":[223],"Flickr30k":[224],"MSCOCO,":[226],"it":[228],"achieves":[229],"very":[230],"competitive":[231],"performance":[232],"among":[233],"state-of-the-art":[235],"models.":[236]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-05-02T08:42:23.175194","created_date":"2025-10-10T00:00:00"}