{"id":"https://openalex.org/W4388936587","doi":"https://doi.org/10.1109/tcsvt.2023.3336371","title":"SPT: Spatial Pyramid Transformer for Image Captioning","display_name":"SPT: Spatial Pyramid Transformer for Image Captioning","publication_year":2023,"publication_date":"2023-11-23","ids":{"openalex":"https://openalex.org/W4388936587","doi":"https://doi.org/10.1109/tcsvt.2023.3336371"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2023.3336371","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3336371","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Transactions on Circuits and Systems for Video Technology","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/A5084439574","display_name":"Haonan Zhang","orcid":"https://orcid.org/0000-0003-1015-7338"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haonan Zhang","raw_affiliation_strings":["Center for Future Media and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0003-1015-7338","affiliations":[{"raw_affiliation_string":"Center for Future Media and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087623065","display_name":"Pengpeng Zeng","orcid":"https://orcid.org/0000-0002-0672-3790"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengpeng Zeng","raw_affiliation_strings":["Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-0672-3790","affiliations":[{"raw_affiliation_string":"Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066645546","display_name":"Lianli Gao","orcid":"https://orcid.org/0000-0002-2522-6394"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianli Gao","raw_affiliation_strings":["Center for Future Media and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-2522-6394","affiliations":[{"raw_affiliation_string":"Center for Future Media and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090700061","display_name":"Xinyu Lyu","orcid":"https://orcid.org/0000-0003-2479-8881"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyu Lyu","raw_affiliation_strings":["Center for Future Media and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0003-2479-8881","affiliations":[{"raw_affiliation_string":"Center for Future Media and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036987388","display_name":"Jingkuan Song","orcid":"https://orcid.org/0000-0002-2549-8322"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingkuan Song","raw_affiliation_strings":["Sichuan Provincial People's Hospital, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-2549-8322","affiliations":[{"raw_affiliation_string":"Sichuan Provincial People's Hospital, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052993469","display_name":"Heng Tao Shen","orcid":"https://orcid.org/0000-0002-2999-2088"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Tao Shen","raw_affiliation_strings":["Center for Future Media and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-2999-2088","affiliations":[{"raw_affiliation_string":"Center for Future Media and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.2972,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.94048212,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"34","issue":"6","first_page":"4829","last_page":"4842"},"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":0.9983000159263611,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9965000152587891,"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":0.8118434548377991},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7763649225234985},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.648213267326355},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6322380304336548},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.5195877552032471},{"id":"https://openalex.org/keywords/image-resolution","display_name":"Image resolution","score":0.5091163516044617},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4791497588157654},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.42644357681274414},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3927091062068939},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3242504596710205},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3202030062675476},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.278744101524353},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11151781678199768}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8118434548377991},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7763649225234985},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.648213267326355},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6322380304336548},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.5195877552032471},{"id":"https://openalex.org/C205372480","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Image resolution","level":2,"score":0.5091163516044617},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4791497588157654},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.42644357681274414},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3927091062068939},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3242504596710205},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3202030062675476},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.278744101524353},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11151781678199768},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2023.3336371","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3336371","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2546663186","display_name":null,"funder_award_id":"62020106008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6864684409","display_name":null,"funder_award_id":"62122018","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7314976618","display_name":"\u878d\u5408\u81ea\u7136\u8bed\u8a00\u5904\u7406\u7684\u6df1\u5ea6\u89c6\u89c9\u7406\u89e3\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"61872064","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8027008232","display_name":"\u534f\u540c\u6df1\u5ea6\u89c6\u9891\u7406\u89e3\u3001\u63cf\u8ff0\u548c\u89c6\u89c9\u95ee\u7b54\u7684\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"61772116","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":88,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1586939924","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2109255472","https://openalex.org/W2122180654","https://openalex.org/W2133512280","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2425121537","https://openalex.org/W2463955103","https://openalex.org/W2506483933","https://openalex.org/W2549139847","https://openalex.org/W2554906389","https://openalex.org/W2575842049","https://openalex.org/W2608988379","https://openalex.org/W2745461083","https://openalex.org/W2796207103","https://openalex.org/W2885013662","https://openalex.org/W2886641317","https://openalex.org/W2890531016","https://openalex.org/W2896457183","https://openalex.org/W2901988662","https://openalex.org/W2905145027","https://openalex.org/W2943568678","https://openalex.org/W2948358897","https://openalex.org/W2951019013","https://openalex.org/W2951390634","https://openalex.org/W2962681491","https://openalex.org/W2962990649","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2963843052","https://openalex.org/W2964110616","https://openalex.org/W2981165461","https://openalex.org/W2981750519","https://openalex.org/W2984138079","https://openalex.org/W2984862483","https://openalex.org/W2986670728","https://openalex.org/W2990818246","https://openalex.org/W3034221024","https://openalex.org/W3034339250","https://openalex.org/W3034655362","https://openalex.org/W3035284526","https://openalex.org/W3035365026","https://openalex.org/W3035372819","https://openalex.org/W3035392611","https://openalex.org/W3035497460","https://openalex.org/W3039060838","https://openalex.org/W3136792391","https://openalex.org/W3138516171","https://openalex.org/W3167939936","https://openalex.org/W3174794493","https://openalex.org/W3174873881","https://openalex.org/W3176425931","https://openalex.org/W3187679738","https://openalex.org/W3191818374","https://openalex.org/W3205021045","https://openalex.org/W3205398323","https://openalex.org/W3217340782","https://openalex.org/W4213453379","https://openalex.org/W4214633470","https://openalex.org/W4214692497","https://openalex.org/W4282968790","https://openalex.org/W4283793362","https://openalex.org/W4285186657","https://openalex.org/W4285197287","https://openalex.org/W4285602612","https://openalex.org/W4292828275","https://openalex.org/W4312289196","https://openalex.org/W4312561350","https://openalex.org/W4382240730","https://openalex.org/W4384161812","https://openalex.org/W4385245566","https://openalex.org/W4386072307","https://openalex.org/W6620707391","https://openalex.org/W6631190155","https://openalex.org/W6677969093","https://openalex.org/W6679436768","https://openalex.org/W6682631176","https://openalex.org/W6684090549","https://openalex.org/W6750041603","https://openalex.org/W6755207826","https://openalex.org/W6763643401","https://openalex.org/W6767988601","https://openalex.org/W6803537622"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W2963177403","https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W3209117276","https://openalex.org/W4388184981","https://openalex.org/W4323777661"],"abstract_inverted_index":{"The":[0],"existing":[1],"approaches":[2],"to":[3,7,23,79,99,102,111,132,169],"image":[4],"captioning":[5,172],"tend":[6],"adopt":[8],"Transformer-based":[9],"architectures":[10],"with":[11,28,39,160],"grid":[12,26,85,108],"features,":[13],"which":[14,32,97,174],"represent":[15],"the":[16,19,25,35,113,144,170,177,180],"state-of-the-art.":[17],"However,":[18],"strategies":[20],"are":[21],"prone":[22],"address":[24],"features":[27],"a":[29,62,92,121],"fixed":[30],"resolution,":[31],"often":[33],"hampers":[34],"perception":[36],"of":[37,179],"entities":[38],"various":[40],"scales.":[41],"In":[42,87,163],"addition,":[43,164],"directly":[44],"applying":[45],"them":[46],"may":[47],"also":[48],"result":[49],"in":[50],"spatial":[51,104],"and":[52,116,137],"fine-grained":[53],"semantic":[54,81],"information":[55,105],"loss.":[56],"To":[57],"this":[58],"end,":[59],"we":[60,90,119],"propose":[61],"simple":[63,122],"yet":[64],"effective":[65],"method,":[66],"named":[67],"Spatial":[68],"Pyramid":[69],"Transformer":[70],"(SPT).":[71],"Specifically,":[72],"it":[73],"adopts":[74],"several":[75],"parameter-shared":[76],"pyramid":[77],"structures":[78],"perform":[80],"interactions":[82],"across":[83],"different":[84],"resolutions.":[86],"each":[88],"layer,":[89],"design":[91],"Spatial-aware":[93],"Pseudo-supervised":[94],"(SP)":[95],"module,":[96],"aims":[98],"adaptively":[100],"resort":[101],"disrupted":[103],"among":[106],"flatted":[107],"features.":[109,140],"Moreover,":[110],"maintain":[112],"model":[114],"size":[115],"enhance":[117],"semantics,":[118],"build":[120],"weighted":[123],"residual":[124],"connection":[125],"termed":[126],"as":[127],"Scale-wise":[128],"Reinforcement":[129],"(SR)":[130],"module":[131],"simultaneously":[133],"explore":[134],"both":[135],"low-":[136],"high-level":[138],"encoded":[139],"Extensive":[141],"experiments":[142],"on":[143],"MS-COCO":[145],"benchmark":[146],"demonstrate":[147],"that":[148],"our":[149,165],"method":[150,166],"achieves":[151],"new":[152],"state-of-the-art":[153],"performance":[154],"without":[155],"bringing":[156],"excessive":[157],"parameters":[158],"compared":[159],"vanilla":[161],"transformer.":[162],"is":[167,184],"extended":[168],"video":[171],"task,":[173],"further":[175],"proves":[176],"practicability":[178],"proposed":[181],"method.":[182],"Code":[183],"available":[185],"at":[186],"https://github.com/zchoi/SPT.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":11}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}