{"id":"https://openalex.org/W4376852293","doi":"https://doi.org/10.1145/3573942.3574061","title":"GA-SATIC: Semi-autoregressive Transformer Image Captioning Based on Geometric Attention","display_name":"GA-SATIC: Semi-autoregressive Transformer Image Captioning Based on Geometric Attention","publication_year":2022,"publication_date":"2022-09-23","ids":{"openalex":"https://openalex.org/W4376852293","doi":"https://doi.org/10.1145/3573942.3574061"},"language":"en","primary_location":{"id":"doi:10.1145/3573942.3574061","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1145/3573942.3574061","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","raw_type":"proceedings-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/A5022045896","display_name":"Ziyi Li","orcid":"https://orcid.org/0000-0001-6810-6352"},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ziyi Li","raw_affiliation_strings":["Xi'an University of Posts and Telecommunications, China"],"raw_orcid":"https://orcid.org/0000-0001-6810-6352","affiliations":[{"raw_affiliation_string":"Xi'an University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I4210136859"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100606529","display_name":"Li Ma","orcid":"https://orcid.org/0000-0002-4359-0050"},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ma Li","raw_affiliation_strings":["Xi'an University of Posts and Telecommunications, China"],"raw_orcid":"https://orcid.org/0000-0002-4359-0050","affiliations":[{"raw_affiliation_string":"Xi'an University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I4210136859"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5022045896"],"corresponding_institution_ids":["https://openalex.org/I4210136859"],"apc_list":null,"apc_paid":null,"fwci":0.102,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.43622346,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"3","issue":null,"first_page":"547","last_page":"554"},"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":0.9954000115394592,"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":0.9947999715805054,"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/autoregressive-model","display_name":"Autoregressive model","score":0.9027875661849976},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8312155604362488},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7693561911582947},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7625287175178528},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5477858781814575},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5191356539726257},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.46351516246795654},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.45402461290359497},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.430412232875824},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40101873874664307},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3672693967819214},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36457738280296326},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3286253809928894},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3100091814994812},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1302891969680786},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0678427517414093}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.9027875661849976},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8312155604362488},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7693561911582947},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7625287175178528},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5477858781814575},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5191356539726257},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.46351516246795654},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.45402461290359497},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.430412232875824},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40101873874664307},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3672693967819214},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36457738280296326},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3286253809928894},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3100091814994812},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1302891969680786},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0678427517414093},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3573942.3574061","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1145/3573942.3574061","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1591801644","https://openalex.org/W1905882502","https://openalex.org/W2068175813","https://openalex.org/W2194775991","https://openalex.org/W2314945149","https://openalex.org/W2325719052","https://openalex.org/W2559655401","https://openalex.org/W2613718673","https://openalex.org/W2745461083","https://openalex.org/W2947912915","https://openalex.org/W2963084599","https://openalex.org/W2964080601","https://openalex.org/W2996677910","https://openalex.org/W3021792375","https://openalex.org/W3034216012","https://openalex.org/W3124149278","https://openalex.org/W3185154749","https://openalex.org/W4236060337","https://openalex.org/W4236965008","https://openalex.org/W6635446068","https://openalex.org/W6639102338","https://openalex.org/W6739901393","https://openalex.org/W6746208923","https://openalex.org/W6754564734","https://openalex.org/W6754778999","https://openalex.org/W6756147243","https://openalex.org/W6763677924","https://openalex.org/W6780578196","https://openalex.org/W6789705400","https://openalex.org/W6797423251"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","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":{"Image":[0],"captioning":[1,196],"is":[2,72,79,89,178],"a":[3,111,139,173,189],"cross-domain":[4],"task":[5],"involving":[6],"image":[7,25,50],"and":[8,30,86,161,181,195,200],"natural":[9],"language":[10],"processing.":[11],"Most":[12],"of":[13,48,54,128],"the":[14,22,31,45,55,60,68,76,83,87,101,126,133,150,155,170,185,204,210],"current":[15],"models":[16,43],"follow":[17],"an":[18,34,49],"encoder-decoder":[19],"architecture,":[20],"where":[21],"encoder":[23,148],"takes":[24],"feature":[26,46],"vectors":[27,47],"as":[28,165],"input,":[29],"decoder":[32,171],"uses":[33],"autoregressive":[35,69],"or":[36],"non-autoregressive":[37,112],"approach":[38],"for":[39],"decoding.":[40],"However,":[41],"most":[42],"extract":[44],"through":[51,158],"region":[52],"proposals":[53],"object":[56],"detector,":[57],"without":[58],"considering":[59],"relative":[61,151],"spatial":[62,152,168],"relationship":[63,153],"between":[64,154,192],"objects.":[65],"When":[66],"decoding,":[67],"decoding":[70,175,193],"method":[71],"adopted,":[73],"that":[74,209],"is,":[75],"next":[77],"word":[78],"generated":[80,84,129],"based":[81,143],"on":[82,144,203],"word,":[85],"generation":[88],"performed":[90],"step":[91],"by":[92,118],"step,":[93],"which":[94,114,177],"will":[95],"lead":[96],"to":[97,166,187,216],"high":[98],"delay":[99],"in":[100,122],"inference":[102,117],"process.":[103],"To":[104],"solve":[105],"this":[106,136],"problem,":[107],"scholars":[108],"have":[109,207],"proposed":[110],"approach,":[113],"speeds":[115],"up":[116],"generating":[119],"all":[120],"words":[121],"parallel,":[123],"but":[124],"reduces":[125],"quality":[127],"captioning.":[130],"Aiming":[131],"at":[132],"above":[134],"problems,":[135],"paper":[137],"proposes":[138],"semi-autoregressive":[140,174],"Transformer":[141],"model":[142,186,211],"geometric":[145,159],"attention.":[146],"The":[147],"integrates":[149],"detected":[156],"objects":[157],"attention":[160],"appearance":[162],"attention,":[163],"so":[164],"enhance":[167],"awareness;":[169],"adopts":[172],"method,":[176],"serialized":[179],"globally":[180],"paralleled":[182],"locally,":[183],"enabling":[184],"achieve":[188],"better":[190,213],"trade-off":[191],"speed":[194],"accuracy.":[197],"Extensive":[198],"experiments":[199],"ablation":[201],"studies":[202],"MSCOCO":[205],"dataset":[206],"shown":[208],"achieves":[212],"performance":[214],"compared":[215],"state-of-the-art":[217],"models.":[218]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}