{"id":"https://openalex.org/W3161934848","doi":"https://doi.org/10.1109/jas.2020.1003402","title":"Global-Attention-Based Neural Networks for Vision Language Intelligence","display_name":"Global-Attention-Based Neural Networks for Vision Language Intelligence","publication_year":2021,"publication_date":"2021-05-31","ids":{"openalex":"https://openalex.org/W3161934848","doi":"https://doi.org/10.1109/jas.2020.1003402","mag":"3161934848"},"language":"en","primary_location":{"id":"doi:10.1109/jas.2020.1003402","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jas.2020.1003402","pdf_url":null,"source":{"id":"https://openalex.org/S2484288132","display_name":"IEEE/CAA Journal of Automatica Sinica","issn_l":"2329-9266","issn":["2329-9266","2329-9274"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/CAA Journal of Automatica Sinica","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/A5100383827","display_name":"Pei Liu","orcid":"https://orcid.org/0000-0002-3795-6140"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]},{"id":"https://openalex.org/I4210125143","display_name":"Chengdu University","ror":"https://ror.org/034z67559","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210125143"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Pei Liu","raw_affiliation_strings":["College of Computer Science, Sichuan University, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I4210125143","https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037482637","display_name":"Yingjie Zhou","orcid":"https://orcid.org/0000-0002-1129-0213"},"institutions":[{"id":"https://openalex.org/I4210125143","display_name":"Chengdu University","ror":"https://ror.org/034z67559","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210125143"]},{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingjie Zhou","raw_affiliation_strings":["College of Computer Science, Sichuan University, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I4210125143","https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027770821","display_name":"Dezhong Peng","orcid":"https://orcid.org/0000-0002-0987-8472"},"institutions":[{"id":"https://openalex.org/I4210125143","display_name":"Chengdu University","ror":"https://ror.org/034z67559","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210125143"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dezhong Peng","raw_affiliation_strings":["College of Computer Science, Sichuan University, Chengdu","Shenzhen Peng Cheng Laboratory, Shenzhen, China","Sichuan Zhiqian Technology Co., Ltd., Chengdu"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Sichuan University, Chengdu","institution_ids":["https://openalex.org/I4210125143","https://openalex.org/I24185976"]},{"raw_affiliation_string":"Shenzhen Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"Sichuan Zhiqian Technology Co., Ltd., Chengdu","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001469325","display_name":"Dapeng Wu","orcid":"https://orcid.org/0000-0003-1755-0183"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dapeng Wu","raw_affiliation_strings":["University of Florida, Gainesville, FL, USA"],"affiliations":[{"raw_affiliation_string":"University of Florida, Gainesville, FL, USA","institution_ids":["https://openalex.org/I33213144"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100383827"],"corresponding_institution_ids":["https://openalex.org/I24185976","https://openalex.org/I4210125143"],"apc_list":null,"apc_paid":null,"fwci":1.7483,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.86614822,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"8","issue":"7","first_page":"1243","last_page":"1252"},"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":0.9936000108718872,"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":0.9891999959945679,"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":0.942710280418396},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8305511474609375},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.7512587308883667},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6462347507476807},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6058334112167358},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5452589988708496},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5431784987449646},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.488297700881958},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4681829512119293},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4619256854057312},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4589042067527771},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.4303930401802063},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4204847812652588},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38043612241744995},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32657545804977417},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10561719536781311},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07193008065223694}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.942710280418396},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8305511474609375},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7512587308883667},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6462347507476807},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6058334112167358},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5452589988708496},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5431784987449646},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.488297700881958},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4681829512119293},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4619256854057312},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4589042067527771},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4303930401802063},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4204847812652588},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38043612241744995},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32657545804977417},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10561719536781311},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07193008065223694},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jas.2020.1003402","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jas.2020.1003402","pdf_url":null,"source":{"id":"https://openalex.org/S2484288132","display_name":"IEEE/CAA Journal of Automatica Sinica","issn_l":"2329-9266","issn":["2329-9266","2329-9274"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/CAA Journal of Automatica Sinica","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7829778773","display_name":null,"funder_award_id":"61971296,U19A2078,61836011,61801315","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W648786980","https://openalex.org/W1514535095","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1902237438","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2133459682","https://openalex.org/W2154652894","https://openalex.org/W2171361956","https://openalex.org/W2194775991","https://openalex.org/W2302086703","https://openalex.org/W2506483933","https://openalex.org/W2549365021","https://openalex.org/W2552161745","https://openalex.org/W2556388456","https://openalex.org/W2558834163","https://openalex.org/W2564898401","https://openalex.org/W2575842049","https://openalex.org/W2604522653","https://openalex.org/W2739107216","https://openalex.org/W2745461083","https://openalex.org/W2809456172","https://openalex.org/W2885013662","https://openalex.org/W2890531016","https://openalex.org/W2896457183","https://openalex.org/W2936497627","https://openalex.org/W2951036431","https://openalex.org/W2962861647","https://openalex.org/W2963084599","https://openalex.org/W2963150697","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963499433","https://openalex.org/W2964308564","https://openalex.org/W2966014552","https://openalex.org/W2970569830","https://openalex.org/W2971310675","https://openalex.org/W2973642807","https://openalex.org/W2981165461","https://openalex.org/W2986670728","https://openalex.org/W2992478697","https://openalex.org/W3034655362","https://openalex.org/W4288329833","https://openalex.org/W4288365749","https://openalex.org/W4385245566","https://openalex.org/W6620707391","https://openalex.org/W6621543089","https://openalex.org/W6630875275","https://openalex.org/W6639102338","https://openalex.org/W6679434410","https://openalex.org/W6682631176","https://openalex.org/W6685230081","https://openalex.org/W6739901393","https://openalex.org/W6752527106","https://openalex.org/W6755207826","https://openalex.org/W6761451552","https://openalex.org/W6763643401","https://openalex.org/W6767200354","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W3217195652","https://openalex.org/W2368824897","https://openalex.org/W1508050556","https://openalex.org/W1910862367","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":{"In":[0,168],"this":[1],"paper,":[2],"we":[3,171],"develop":[4],"a":[5,21,56],"novel":[6],"global-attention-based":[7],"neural":[8],"network":[9],"(GANN)":[10],"for":[11,43,85,99,110,200],"vision":[12],"language":[13],"intelligence,":[14],"specifically,":[15],"image":[16,111,201],"captioning":[17],"(language":[18],"description":[19],"of":[20,60,89,102,107,137,164,194],"given":[22],"image).":[23],"As":[24],"many":[25],"previous":[26],"works,":[27],"the":[28,39,45,62,66,72,79,90,100,104,116,121,146,151,157,165,174,186,192,195],"encoder-decoder":[29],"framework":[30],"is":[31,41,97,142],"adopted":[32],"in":[33,37,133,156,161],"our":[34,169],"proposed":[35,175,196],"model,":[36,176],"which":[38],"encoder":[40],"responsible":[42],"encoding":[44],"region":[46,108],"proposal":[47],"features":[48,82],"and":[49,65,113,177],"extracting":[50],"global":[51,74,94,147,197],"caption":[52,63,75,95,138,148],"feature":[53,76,96,132,149],"based":[54],"on":[55,120,185],"specially":[57],"designed":[58],"module":[59],"predicting":[61],"objects,":[64],"decoder":[67,91,117,166],"generates":[68],"captions":[69],"by":[70,144],"taking":[71],"obtained":[73],"along":[77],"with":[78,183],"encoded":[80],"visual":[81,131],"as":[83,126],"inputs":[84],"each":[86,134,162],"attention":[87,152,198],"head":[88,163],"layer.":[92,167],"The":[93],"introduced":[98],"purpose":[101],"exploring":[103],"latent":[105],"contributions":[106],"proposals":[109,124],"captioning,":[112],"further":[114],"helping":[115],"better":[118],"focus":[119],"most":[122],"relevant":[123],"so":[125],"to":[127],"extract":[128],"more":[129],"accurate":[130],"time":[135],"step":[136],"generation.":[139],"Our":[140],"GANN":[141,184],"implemented":[143],"incorporating":[145],"into":[150],"weight":[153],"calculation":[154],"phase":[155],"word":[158],"predication":[159],"process":[160],"experiments,":[170],"qualitatively":[172],"analyzed":[173],"quantitatively":[178],"evaluated":[179],"several":[180],"state-of-the-art":[181],"schemes":[182],"MS-COCO":[187],"dataset.":[188],"Experimental":[189],"results":[190],"demonstrate":[191],"effectiveness":[193],"mechanism":[199],"captioning.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":2}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}