{"id":"https://openalex.org/W3205981128","doi":"https://doi.org/10.1145/3474085.3475179","title":"Semi-Autoregressive Image Captioning","display_name":"Semi-Autoregressive Image Captioning","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3205981128","doi":"https://doi.org/10.1145/3474085.3475179","mag":"3205981128"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475179","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475179","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","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/A5100378208","display_name":"Yan Xu","orcid":"https://orcid.org/0000-0002-0271-044X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xu Yan","raw_affiliation_strings":["Key Lab of Intell. Info. Process., Inst. of Comput. Tech., CAS, Beijing, China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Lab of Intell. Info. Process., Inst. of Comput. Tech., CAS, Beijing, China, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011717108","display_name":"Zhengcong Fei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhengcong Fei","raw_affiliation_strings":["Key Lab of Intell. Info. Process., Inst. of Comput. Tech., CAS, Beijing, China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Lab of Intell. Info. Process., Inst. of Comput. Tech., CAS, Beijing, China, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088012221","display_name":"Zekang Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zekang Li","raw_affiliation_strings":["Key Lab of Intell. Info. Process., Inst. of Comput. Tech., CAS, Beijing, China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Lab of Intell. Info. Process., Inst. of Comput. Tech., CAS, Beijing, China, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100669242","display_name":"Shuhui Wang","orcid":"https://orcid.org/0000-0002-5931-0527"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuhui Wang","raw_affiliation_strings":["Key Lab of Intell. Info. Process., Inst. of Comput. Tech., CAS, Beijing, China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Lab of Intell. Info. Process., Inst. of Comput. Tech., CAS, Beijing, China, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028597017","display_name":"Qingming Huang","orcid":"https://orcid.org/0000-0001-7542-296X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qingming Huang","raw_affiliation_strings":["Key Lab of Intell. Info. Process., Inst. of Comput. Tech., CAS, Beijing, China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Lab of Intell. Info. Process., Inst. of Comput. Tech., CAS, Beijing, China, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111504451","display_name":"Qi Tian","orcid":"https://orcid.org/0009-0003-2676-5300"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Tian","raw_affiliation_strings":["Cloud BU, Huawei Technologies, Shenzhen, China, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Cloud BU, Huawei Technologies, Shenzhen, China, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100378208"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6332,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.85996732,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2708","last_page":"2716"},"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":0.9933000206947327,"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":0.9929999709129333,"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":0.9610013961791992},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.8786311745643616},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7659573554992676},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.6722928285598755},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5832663774490356},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5565229058265686},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4806074798107147},{"id":"https://openalex.org/keywords/star-model","display_name":"STAR model","score":0.4644610285758972},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45086485147476196},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4376472234725952},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4107775092124939},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3860480487346649},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3626856803894043},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.228822261095047},{"id":"https://openalex.org/keywords/autoregressive-integrated-moving-average","display_name":"Autoregressive integrated moving average","score":0.22845321893692017},{"id":"https://openalex.org/keywords/time-series","display_name":"Time series","score":0.21603494882583618},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.1447400152683258},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13412511348724365}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9610013961791992},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.8786311745643616},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7659573554992676},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.6722928285598755},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5832663774490356},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5565229058265686},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4806074798107147},{"id":"https://openalex.org/C194657046","wikidata":"https://www.wikidata.org/wiki/Q7394685","display_name":"STAR model","level":4,"score":0.4644610285758972},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45086485147476196},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4376472234725952},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4107775092124939},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3860480487346649},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3626856803894043},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.228822261095047},{"id":"https://openalex.org/C24338571","wikidata":"https://www.wikidata.org/wiki/Q2566298","display_name":"Autoregressive integrated moving average","level":3,"score":0.22845321893692017},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.21603494882583618},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.1447400152683258},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13412511348724365},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3474085.3475179","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475179","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","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":29,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W1895989618","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2133512280","https://openalex.org/W2154652894","https://openalex.org/W2194775991","https://openalex.org/W2296073425","https://openalex.org/W2506483933","https://openalex.org/W2626778328","https://openalex.org/W2745461083","https://openalex.org/W2767206889","https://openalex.org/W2789163545","https://openalex.org/W2803259101","https://openalex.org/W2890501761","https://openalex.org/W2890531016","https://openalex.org/W2895387432","https://openalex.org/W2949888546","https://openalex.org/W2950178297","https://openalex.org/W2953106684","https://openalex.org/W2963084599","https://openalex.org/W2965846473","https://openalex.org/W2968549119","https://openalex.org/W2972897806","https://openalex.org/W2986670728","https://openalex.org/W3034655362","https://openalex.org/W3093394956","https://openalex.org/W3141754740"],"related_works":["https://openalex.org/W2439807930","https://openalex.org/W2169518243","https://openalex.org/W2252095989","https://openalex.org/W2009692134","https://openalex.org/W1972271943","https://openalex.org/W4322096525","https://openalex.org/W2019155478","https://openalex.org/W2551914602","https://openalex.org/W2024529895","https://openalex.org/W4281893144"],"abstract_inverted_index":{"Current":[0],"state-of-the-art":[1],"approaches":[2],"for":[3,79],"image":[4,31,159,188],"captioning":[5,32,189],"typically":[6],"adopt":[7],"an":[8,128,132],"autoregressive":[9,52,113,133],"manner,":[10,134],"i.e.,":[11],"generating":[12],"descriptions":[13],"word":[14,141,144],"by":[15],"word,":[16],"which":[17,37],"suffers":[18],"from":[19],"slow":[20],"decoding":[21],"issue":[22],"and":[23,106,158],"becomes":[24],"a":[25,43,55,61,88,101,193],"bottleneck":[26],"in":[27,42,115,120,131,142,146],"real-time":[28],"applications.":[29],"Non-autoregressive":[30],"with":[33,54,149,169],"continuous":[34],"iterative":[35],"refinement,":[36],"eliminates":[38],"the":[39,51,80,139,150,153,166,175,185],"sequential":[40],"dependence":[41],"sentence":[44],"generation,":[45],"can":[46,70],"achieve":[47],"comparable":[48],"performance":[49,105],"to":[50,93,99],"counterparts":[53],"considerable":[56],"acceleration.":[57],"Nevertheless,":[58],"based":[59],"on":[60,174],"well-designed":[62],"experiment,":[63],"we":[64,86],"empirically":[65],"proved":[66],"that":[67,84,135,180],"iteration":[68],"times":[69],"be":[71],"effectively":[72],"reduced":[73],"when":[74],"providing":[75],"sufficient":[76],"prior":[77,156],"knowledge":[78],"language":[81],"decoder.":[82],"Towards":[83],"end,":[85],"propose":[87],"novel":[89],"two-stage":[90],"framework,":[91],"referred":[92],"as":[94],"Semi-Autoregressive":[95],"Image":[96],"Captioning":[97],"(SAIC),":[98],"make":[100],"better":[102],"trade-off":[103],"between":[104],"speed.":[107],"The":[108],"proposed":[109],"SAIC":[110,123,161,182],"model":[111,124,162,183],"maintains":[112],"property":[114],"global":[116],"but":[117],"relieves":[118],"it":[119,137],"local.":[121],"Specifically,":[122],"first":[125,140],"jumpily":[126],"generates":[127],"intermittent":[129],"sequence":[130],"is,":[136],"predicts":[138],"every":[143],"group":[145],"order.":[147],"Then,":[148],"help":[151],"of":[152],"partially":[154],"deterministic":[155],"information":[157],"features,":[160],"non-autoregressively":[163],"fills":[164],"all":[165],"skipped":[167],"words":[168],"one":[170],"iteration.":[171],"Experimental":[172],"results":[173],"MS":[176],"COCO":[177],"benchmark":[178],"demonstrate":[179],"our":[181],"outperforms":[184],"preceding":[186],"non-autoregressive":[187],"models":[190],"while":[191],"obtaining":[192],"competitive":[194],"inference":[195],"speedup.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}