{"id":"https://openalex.org/W4319777846","doi":"https://doi.org/10.1109/tcsvt.2023.3243725","title":"Cross on Cross Attention: Deep Fusion Transformer for Image Captioning","display_name":"Cross on Cross Attention: Deep Fusion Transformer for Image Captioning","publication_year":2023,"publication_date":"2023-02-09","ids":{"openalex":"https://openalex.org/W4319777846","doi":"https://doi.org/10.1109/tcsvt.2023.3243725"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2023.3243725","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3243725","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/A5100345320","display_name":"Jing Zhang","orcid":"https://orcid.org/0000-0001-6270-7771"},"institutions":[{"id":"https://openalex.org/I143593769","display_name":"East China University of Science and Technology","ror":"https://ror.org/01vyrm377","country_code":"CN","type":"education","lineage":["https://openalex.org/I143593769"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jing Zhang","raw_affiliation_strings":["Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-6270-7771","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, China","institution_ids":["https://openalex.org/I143593769"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081492347","display_name":"Yingshuai Xie","orcid":"https://orcid.org/0000-0001-8752-4672"},"institutions":[{"id":"https://openalex.org/I143593769","display_name":"East China University of Science and Technology","ror":"https://ror.org/01vyrm377","country_code":"CN","type":"education","lineage":["https://openalex.org/I143593769"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingshuai Xie","raw_affiliation_strings":["Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8752-4672","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, China","institution_ids":["https://openalex.org/I143593769"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012569030","display_name":"Weichao Ding","orcid":"https://orcid.org/0000-0002-8892-3760"},"institutions":[{"id":"https://openalex.org/I143593769","display_name":"East China University of Science and Technology","ror":"https://ror.org/01vyrm377","country_code":"CN","type":"education","lineage":["https://openalex.org/I143593769"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weichao Ding","raw_affiliation_strings":["Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8892-3760","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, China","institution_ids":["https://openalex.org/I143593769"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100621319","display_name":"Zhe Wang","orcid":"https://orcid.org/0000-0002-3759-2041"},"institutions":[{"id":"https://openalex.org/I143593769","display_name":"East China University of Science and Technology","ror":"https://ror.org/01vyrm377","country_code":"CN","type":"education","lineage":["https://openalex.org/I143593769"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhe Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-3759-2041","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, China","institution_ids":["https://openalex.org/I143593769"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100345320"],"corresponding_institution_ids":["https://openalex.org/I143593769"],"apc_list":null,"apc_paid":null,"fwci":9.9597,"has_fulltext":false,"cited_by_count":88,"citation_normalized_percentile":{"value":0.98804916,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"33","issue":"8","first_page":"4257","last_page":"4268"},"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":0.9979000091552734,"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":0.9921000003814697,"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":0.8173213005065918},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7775717973709106},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7098408937454224},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6180024147033691},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5381823778152466},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5142337679862976},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4890314042568207},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.45231950283050537},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4162941575050354},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.41203656792640686},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38702496886253357},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3239437937736511},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32143548130989075},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23030787706375122}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8173213005065918},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7775717973709106},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7098408937454224},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6180024147033691},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5381823778152466},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5142337679862976},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4890314042568207},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.45231950283050537},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4162941575050354},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.41203656792640686},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38702496886253357},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3239437937736511},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32143548130989075},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23030787706375122},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2023.3243725","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3243725","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/G6893319343","display_name":null,"funder_award_id":"22ZR1418400","funder_id":"https://openalex.org/F4320309612","funder_display_name":"Natural Science Foundation of Shanghai"}],"funders":[{"id":"https://openalex.org/F4320309612","display_name":"Natural Science Foundation of Shanghai","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1933349210","https://openalex.org/W1956340063","https://openalex.org/W2020755048","https://openalex.org/W2108598243","https://openalex.org/W2123301721","https://openalex.org/W2133564696","https://openalex.org/W2154652894","https://openalex.org/W2157331557","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2506483933","https://openalex.org/W2575842049","https://openalex.org/W2745461083","https://openalex.org/W2890531016","https://openalex.org/W2896457183","https://openalex.org/W2904551248","https://openalex.org/W2953106684","https://openalex.org/W2963084599","https://openalex.org/W2965182628","https://openalex.org/W2966683369","https://openalex.org/W2981165461","https://openalex.org/W2983141445","https://openalex.org/W2986670728","https://openalex.org/W2990818246","https://openalex.org/W3034655362","https://openalex.org/W3035160838","https://openalex.org/W3035284526","https://openalex.org/W3035497460","https://openalex.org/W3091588028","https://openalex.org/W3106925514","https://openalex.org/W3130531605","https://openalex.org/W3136792391","https://openalex.org/W3138516171","https://openalex.org/W3166396011","https://openalex.org/W3167939936","https://openalex.org/W3173220247","https://openalex.org/W3174377922","https://openalex.org/W3195680250","https://openalex.org/W4214917601","https://openalex.org/W4221143761","https://openalex.org/W4221147537","https://openalex.org/W4282968790","https://openalex.org/W4283722434","https://openalex.org/W4285186657","https://openalex.org/W4288329833","https://openalex.org/W4292828275","https://openalex.org/W4303444943","https://openalex.org/W4312344082","https://openalex.org/W4312605942","https://openalex.org/W4312924260","https://openalex.org/W4313131769","https://openalex.org/W4385245566","https://openalex.org/W6620707391","https://openalex.org/W6630875275","https://openalex.org/W6637373629","https://openalex.org/W6639102338","https://openalex.org/W6678262379","https://openalex.org/W6679434410","https://openalex.org/W6682631176","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6763643401","https://openalex.org/W6791353385","https://openalex.org/W6809536152","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W2368824897","https://openalex.org/W2221419418","https://openalex.org/W1508050556","https://openalex.org/W1910862367","https://openalex.org/W2379365082","https://openalex.org/W2370747590","https://openalex.org/W4283822356","https://openalex.org/W2030109976","https://openalex.org/W1950940422","https://openalex.org/W2369260257"],"abstract_inverted_index":{"Numerous":[0],"studies":[1],"have":[2],"shown":[3],"that":[4,154],"in-depth":[5],"mining":[6],"of":[7,17,40,98,141],"correlations":[8],"between":[9,108],"multi-modal":[10,41,77],"features":[11,42,109],"can":[12,102,158],"help":[13],"improve":[14],"the":[15,23,30,36,44,48,55,82,106,116,138,150],"accuracy":[16],"cross-modal":[18,129,134],"data":[19,130],"analysis":[20],"tasks.":[21],"However,":[22],"current":[24],"image":[25,69],"description":[26],"methods":[27],"based":[28],"on":[29,121,149],"encoder-decoder":[31],"framework":[32],"only":[33],"carry":[34],"out":[35],"interaction":[37,140],"and":[38,76,110,143,162],"fusion":[39,79],"in":[43],"encoding":[45,83],"stage":[46],"or":[47],"decoding":[49,85],"stage,":[50],"which":[51,101],"cannot":[52],"effectively":[53,103],"alleviate":[54],"semantic":[56,144],"gap.":[57],"In":[58,115],"this":[59],"paper,":[60],"we":[61],"propose":[62,88],"a":[63,73,89,118],"Deep":[64],"Fusion":[65],"Transformer":[66],"(DFT)":[67],"for":[68,105],"captioning":[70],"to":[71,84,94,126],"provide":[72],"deep":[74],"multi-feature":[75],"information":[78],"strategy":[80],"throughout":[81],"process.":[86],"We":[87],"novel":[90,119],"global":[91],"cross":[92,120,122],"encoder":[93],"align":[95],"different":[96],"types":[97],"visual":[99,142],"features,":[100],"compensate":[104],"differences":[107],"incorporate":[111],"each":[112],"other\u2019s":[113],"strengths.":[114],"decoder,":[117],"attention":[123],"is":[124,168],"proposed":[125,156],"realize":[127],"hierarchical":[128],"analysis,":[131],"extending":[132],"complex":[133],"reasoning":[135],"capabilities":[136],"through":[137],"multi-level":[139],"features.":[145],"Extensive":[146],"experiments":[147],"conducted":[148],"MSCOCO":[151],"dataset":[152],"prove":[153],"our":[155],"DFT":[157],"achieve":[159],"excellent":[160],"performance":[161],"outperform":[163],"state-of-the-art":[164],"methods.":[165],"The":[166],"code":[167],"available":[169],"at":[170],"<uri":[171],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[172],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/weimingboya/DFT</uri>":[173],".":[174]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":49},{"year":2024,"cited_by_count":25},{"year":2023,"cited_by_count":7}],"updated_date":"2026-05-31T08:46:17.908082","created_date":"2025-10-10T00:00:00"}