{"id":"https://openalex.org/W3196620563","doi":"https://doi.org/10.1145/3463945.3469054","title":"Be Specific, Be Clear: Bridging Machine and Human Captions by Scene-Guided Transformer","display_name":"Be Specific, Be Clear: Bridging Machine and Human Captions by Scene-Guided Transformer","publication_year":2021,"publication_date":"2021-08-21","ids":{"openalex":"https://openalex.org/W3196620563","doi":"https://doi.org/10.1145/3463945.3469054","mag":"3196620563"},"language":"en","primary_location":{"id":"doi:10.1145/3463945.3469054","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3463945.3469054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 Workshop on Multi-Modal Pre-Training for Multimedia Understanding","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/A5067298679","display_name":"Yupan Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yupan Huang","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042319392","display_name":"Zhaoyang Zeng","orcid":"https://orcid.org/0000-0002-4712-9210"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaoyang Zeng","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101633465","display_name":"Yutong Lu","orcid":"https://orcid.org/0000-0001-5315-3375"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yutong Lu","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5067298679"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":0.3843,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.60751634,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4","last_page":"13"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9986000061035156,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9732999801635742,"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/bridging","display_name":"Bridging (networking)","score":0.8480011820793152},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7007910013198853},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6123085021972656},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.2627108693122864},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.19738885760307312},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.1646243929862976},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.08677491545677185}],"concepts":[{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.8480011820793152},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7007910013198853},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6123085021972656},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.2627108693122864},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.19738885760307312},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.1646243929862976},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.08677491545677185}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3463945.3469054","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3463945.3469054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 Workshop on Multi-Modal Pre-Training for Multimedia Understanding","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W17540453","https://openalex.org/W68733909","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W1986209830","https://openalex.org/W2036167211","https://openalex.org/W2056621158","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2123301721","https://openalex.org/W2134670479","https://openalex.org/W2152161678","https://openalex.org/W2154652894","https://openalex.org/W2162915993","https://openalex.org/W2183341477","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2506483933","https://openalex.org/W2549139847","https://openalex.org/W2552161745","https://openalex.org/W2564898401","https://openalex.org/W2575842049","https://openalex.org/W2737258237","https://openalex.org/W2745461083","https://openalex.org/W2795151422","https://openalex.org/W2798662960","https://openalex.org/W2886641317","https://openalex.org/W2890531016","https://openalex.org/W2913618459","https://openalex.org/W2913822893","https://openalex.org/W2950028154","https://openalex.org/W2950178297","https://openalex.org/W2952423790","https://openalex.org/W2953022248","https://openalex.org/W2953106684","https://openalex.org/W2962861647","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2963170456","https://openalex.org/W2963403868","https://openalex.org/W2964121744","https://openalex.org/W2965129775","https://openalex.org/W2965597639","https://openalex.org/W2970013683","https://openalex.org/W2970608575","https://openalex.org/W2971183306","https://openalex.org/W2971310675","https://openalex.org/W2981646256","https://openalex.org/W2984138079","https://openalex.org/W2986670728","https://openalex.org/W2987327987","https://openalex.org/W2990069284","https://openalex.org/W2990818246","https://openalex.org/W2997591391","https://openalex.org/W3006819232","https://openalex.org/W3009270862","https://openalex.org/W3103651098","https://openalex.org/W3104752576","https://openalex.org/W3184784418"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W4388870064","https://openalex.org/W4235186151","https://openalex.org/W2056057048","https://openalex.org/W2054685365","https://openalex.org/W2272354214","https://openalex.org/W2120383820","https://openalex.org/W2043010663","https://openalex.org/W2667588871","https://openalex.org/W4248308508"],"abstract_inverted_index":{"Automatically":[0],"generating":[1],"natural":[2],"language":[3,61],"descriptions":[4],"for":[5,16,164],"images,":[6,52],"i.e.,":[7],"image":[8,27,86,110,167],"captioning,":[9],"is":[10,54],"one":[11],"of":[12,22,40,43,51,80,181],"the":[13,41,100,152,162,177,184,197,208],"primary":[14],"goals":[15],"multimedia":[17],"understanding.":[18],"The":[19,117],"recent":[20],"success":[21],"deep":[23],"neural":[24],"networks":[25],"in":[26,130,196,207],"captioning":[28],"has":[29],"been":[30],"accompanied":[31],"by":[32,161],"region-based":[33,128],"bottom-up-attention":[34],"features.":[35],"Region-based":[36],"features":[37,129],"are":[38],"representative":[39],"contents":[42],"local":[44],"regions":[45],"while":[46],"lacking":[47],"an":[48,114,165],"overall":[49,68,85,166],"understanding":[50,69],"which":[53],"critical":[55],"to":[56,74,104,133,201],"more":[57,106,146],"specific":[58,76,107,147],"and":[59,70,77,84,108,157,173,179,191,199,204],"clear":[60,78],"expression.":[62],"Visual":[63],"scene":[64,121,192],"perception":[65],"can":[66,188],"facilitate":[67,134],"provide":[71],"prior":[72],"knowledge":[73,125],"generate":[75,105],"captions":[79],"objects,":[81],"object":[82,127,135],"relations,":[83],"scenes.":[87],"In":[88],"this":[89],"paper,":[90],"we":[91],"propose":[92],"a":[93],"Scene-Guided":[94],"Transformer":[95],"(SG-Transformer)":[96],"model":[97],"that":[98],"leverages":[99],"scene-level":[101,158],"global":[102,120],"context":[103,122],"descriptive":[109],"captions.":[111],"SG-Transformer":[112],"adopts":[113],"encoder-decoder":[115],"architecture.":[116],"encoder":[118,163,198],"aggregates":[119],"as":[123],"external":[124],"with":[126],"attention":[131],"learning":[132],"relation":[136],"reasoning.":[137],"It":[138],"also":[139],"incorporates":[140],"high-level":[141],"auxiliary":[142],"scene-guided":[143,186],"tasks":[144],"towards":[145],"visual":[148,194],"representation":[149],"learning.":[150],"Then":[151],"decoder":[153],"integrates":[154],"both":[155,202],"object-level":[156,190],"information":[159],"refined":[160],"perception.":[168],"Extensive":[169],"experiments":[170],"on":[171],"MSCOCO":[172],"Flickr30k":[174],"benchmarks":[175],"show":[176],"superiority":[178],"generality":[180],"SG-Transformer.":[182],"Besides,":[183],"proposed":[185],"approach":[187],"enrich":[189],"graph":[193],"representations":[195],"generalize":[200],"RNN-":[203],"Transformer-based":[205],"architectures":[206],"decoder.":[209]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}