{"id":"https://openalex.org/W4285602612","doi":"https://doi.org/10.24963/ijcai.2022/224","title":"S2 Transformer for Image Captioning","display_name":"S2 Transformer for Image Captioning","publication_year":2022,"publication_date":"2022-07-01","ids":{"openalex":"https://openalex.org/W4285602612","doi":"https://doi.org/10.24963/ijcai.2022/224"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2022/224","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/224","pdf_url":"https://www.ijcai.org/proceedings/2022/0224.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.ijcai.org/proceedings/2022/0224.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087623065","display_name":"Pengpeng Zeng","orcid":"https://orcid.org/0000-0002-0672-3790"},"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":"Pengpeng Zeng","raw_affiliation_strings":["University of Electronic Science and Technology of China","School of Computer Science and Engineering and Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"School of Computer Science and Engineering and Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100705309","display_name":"Haonan Zhang","orcid":"https://orcid.org/0000-0002-3871-6819"},"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":["University of Electronic Science and Technology of China","School of Computer Science and Engineering and Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"School of Computer Science and Engineering and Shenzhen Institute for Advanced Study, 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":["University of Electronic Science and Technology of China","School of Computer Science and Engineering and Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"School of Computer Science and Engineering and Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","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":["University of Electronic Science and Technology of China","School of Computer Science and Engineering and Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"School of Computer Science and Engineering and Shenzhen Institute for Advanced Study, 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":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":79,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1608","last_page":"1614"},"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":0.9962999820709229,"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":0.9943000078201294,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.9324595928192139},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7913269996643066},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7806144952774048},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.5509874820709229},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.536675751209259},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.45401185750961304},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4322197437286377},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4131524860858917},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3673873245716095},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3505905270576477},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.28040310740470886},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0800122618675232},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07365047931671143}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9324595928192139},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7913269996643066},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7806144952774048},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.5509874820709229},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.536675751209259},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.45401185750961304},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4322197437286377},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4131524860858917},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3673873245716095},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3505905270576477},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.28040310740470886},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0800122618675232},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07365047931671143},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2022/224","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/224","pdf_url":"https://www.ijcai.org/proceedings/2022/0224.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2022/224","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/224","pdf_url":"https://www.ijcai.org/proceedings/2022/0224.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.5699999928474426,"id":"https://metadata.un.org/sdg/11"}],"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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285602612.pdf","grobid_xml":"https://content.openalex.org/works/W4285602612.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1514535095","https://openalex.org/W1956340063","https://openalex.org/W2123301721","https://openalex.org/W2130942839","https://openalex.org/W2154652894","https://openalex.org/W2277195237","https://openalex.org/W2463955103","https://openalex.org/W2481240925","https://openalex.org/W2506483933","https://openalex.org/W2745461083","https://openalex.org/W2885013662","https://openalex.org/W2901988662","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2986670728","https://openalex.org/W2990818246","https://openalex.org/W3034339250","https://openalex.org/W3034655362","https://openalex.org/W3035284526","https://openalex.org/W3035497460","https://openalex.org/W3167939936","https://openalex.org/W3187679738","https://openalex.org/W3191818374","https://openalex.org/W4288329833","https://openalex.org/W4289542422","https://openalex.org/W4300614726"],"related_works":["https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W3209117276","https://openalex.org/W4388184981","https://openalex.org/W4323777661","https://openalex.org/W4288365749","https://openalex.org/W2936497627","https://openalex.org/W3013624417","https://openalex.org/W4287826556"],"abstract_inverted_index":{"Transformer-based":[0],"architectures":[1],"with":[2,119,141],"grid":[3,86],"features":[4,118],"represent":[5],"the":[6,91,125,142],"state-of-the-art":[7],"in":[8,31],"visual":[9,16],"and":[10,19,33,58,94,115],"language":[11],"reasoning":[12],"tasks,":[13],"such":[14],"as":[15],"question":[17],"answering":[18],"image-text":[20],"matching.":[21],"However,":[22],"directly":[23],"applying":[24],"them":[25],"to":[26,40,77,80,89,110],"image":[27,41,64],"captioning":[28,42],"may":[29],"result":[30],"spatial":[32,83],"fine-grained":[34],"semantic":[35],"information":[36,84],"loss.":[37],"Their":[38],"applicability":[39],"is":[43,148],"still":[44],"largely":[45],"under-explored.":[46],"Towards":[47],"this":[48],"goal,":[49],"we":[50,67,98],"propose":[51,69],"a":[52,70,100],"simple":[53,101],"yet":[54],"effective":[55],"method,":[56],"Spatial-":[57],"Scale-aware":[59],"Transformer":[60],"(S2":[61],"Transformer)":[62],"for":[63,85],"captioning.":[65],"Specifically,":[66],"firstly":[68],"Spatial-aware":[71],"Pseudo-supervised":[72],"(SP)":[73],"module,":[74,109],"which":[75],"resorts":[76],"feature":[78],"clustering":[79],"help":[81],"preserve":[82],"features.":[87],"Next,":[88],"maintain":[90],"model":[92],"size":[93],"produce":[95],"superior":[96],"results,":[97],"build":[99],"weighted":[102],"residual":[103],"connection,":[104],"named":[105],"Scale-wise":[106],"Reinforcement":[107],"(SR)":[108],"simultaneously":[111],"explore":[112],"both":[113],"low-":[114],"high-level":[116],"encoded":[117],"rich":[120],"semantics.":[121],"Extensive":[122],"experiments":[123],"on":[124],"MSCOCO":[126],"benchmark":[127],"demonstrate":[128],"that":[129],"our":[130],"method":[131],"achieves":[132],"new":[133],"state-of-art":[134],"performance":[135],"without":[136],"bringing":[137],"excessive":[138],"parameters":[139],"compared":[140],"vanilla":[143],"transformer.":[144],"The":[145],"source":[146],"code":[147],"available":[149],"at":[150],"https://github.com/zchoi/S2-Transformer":[151]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":26},{"year":2023,"cited_by_count":24},{"year":2022,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}