{"id":"https://openalex.org/W3082436432","doi":"https://doi.org/10.1145/3386725","title":"Constrained LSTM and Residual Attention for Image Captioning","display_name":"Constrained LSTM and Residual Attention for Image Captioning","publication_year":2020,"publication_date":"2020-07-05","ids":{"openalex":"https://openalex.org/W3082436432","doi":"https://doi.org/10.1145/3386725","mag":"3082436432"},"language":"en","primary_location":{"id":"doi:10.1145/3386725","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3386725","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","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":null,"display_name":"Liang Yang","orcid":"https://orcid.org/0000-0002-4884-323X"},"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":"Liang Yang","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, Guangdong, People.s Republic of China"],"raw_orcid":"https://orcid.org/0000-0002-4884-323X","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, Guangdong, People.s Republic of China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056953478","display_name":"Haifeng Hu","orcid":"https://orcid.org/0000-0002-4884-323X"},"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":"Haifeng Hu","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, Guangdong, People.s Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, Guangdong, People.s Republic of China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051867844","display_name":"Songlong Xing","orcid":"https://orcid.org/0000-0002-2734-1695"},"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":"Songlong Xing","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, Guangdong, People.s Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, Guangdong, People.s Republic of China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076619736","display_name":"Xinlong Lu","orcid":"https://orcid.org/0009-0009-3047-178X"},"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":"Xinlong Lu","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, Guangdong, People.s Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, Guangdong, People.s Republic of China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":2.4917,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.91198703,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"16","issue":"3","first_page":"1","last_page":"18"},"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":0.9944999814033508,"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":0.9922999739646912,"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/closed-captioning","display_name":"Closed captioning","score":0.9346832036972046},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8098957538604736},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6823409795761108},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6206972599029541},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6172758340835571},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6165004968643188},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5617757439613342},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5555762648582458},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.49936532974243164},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.4772765040397644},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.41693341732025146},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3619294762611389},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11042523384094238}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9346832036972046},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8098957538604736},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6823409795761108},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6206972599029541},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6172758340835571},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6165004968643188},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5617757439613342},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5555762648582458},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.49936532974243164},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.4772765040397644},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.41693341732025146},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3619294762611389},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11042523384094238},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3386725","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3386725","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.75,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1786224844","display_name":null,"funder_award_id":"61673402, 61273270, and 60802069","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4228998522","display_name":null,"funder_award_id":"2017A030311029","funder_id":"https://openalex.org/F4320321921","funder_display_name":"Natural Science Foundation of Guangdong Province"},{"id":"https://openalex.org/G6618701442","display_name":null,"funder_award_id":"17lgzd08","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1969616664","https://openalex.org/W2133564696","https://openalex.org/W2176091656","https://openalex.org/W2183341477","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2220981600","https://openalex.org/W2250861254","https://openalex.org/W2277195237","https://openalex.org/W2296385829","https://openalex.org/W2302086703","https://openalex.org/W2468907370","https://openalex.org/W2552161745","https://openalex.org/W2564898401","https://openalex.org/W2575842049","https://openalex.org/W2745461083","https://openalex.org/W2752465200","https://openalex.org/W2798959609","https://openalex.org/W2895420168","https://openalex.org/W2914393402","https://openalex.org/W2941127321","https://openalex.org/W2963037989","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2963170456","https://openalex.org/W2965697393","https://openalex.org/W2972897806","https://openalex.org/W4206070039","https://openalex.org/W4247950230"],"related_works":["https://openalex.org/W3157643567","https://openalex.org/W2971688299","https://openalex.org/W3020826863","https://openalex.org/W2903179935","https://openalex.org/W159132833","https://openalex.org/W2971866238","https://openalex.org/W3209355071","https://openalex.org/W3216250699","https://openalex.org/W2889818188","https://openalex.org/W1492132281"],"abstract_inverted_index":{"Visual":[0,12],"structure":[1,4,13,25,90],"and":[2,9,20,71,91,113,144,173,182,193,208],"syntactic":[3,24,72],"are":[5,186],"essential":[6],"in":[7,17,26,68,110,117,147],"images":[8],"texts,":[10],"respectively.":[11],"depicts":[14],"both":[15,69,167],"entities":[16,58],"an":[18,118,148,159],"image":[19,119,160],"their":[21,63],"interactions,":[22],"whereas":[23],"texts":[27],"can":[28],"reflect":[29],"the":[30,46,54,84,105,122,140,163,168,205],"part-of-speech":[31,98],"constraints":[32],"between":[33,108],"adjacent":[34,60],"words.":[35,61,129],"Most":[36],"existing":[37],"methods":[38,103,207],"either":[39],"use":[40],"visual":[41,70,89,115,142,171],"global":[42],"representation":[43],"to":[44,87,136,162],"guide":[45],"language":[47,64,85],"model":[48,81,86],"or":[49,59,201],"generate":[50],"captions":[51],"without":[52],"considering":[53,166],"relationships":[55],"of":[56,124,154,158,170,178],"different":[57],"Thus,":[62],"models":[65],"lack":[66],"relevance":[67],"structure.":[73],"To":[74],"solve":[75],"this":[76],"problem,":[77],"we":[78],"propose":[79],"a":[80,96,111,132],"that":[82],"aligns":[83],"certain":[88],"also":[92],"constrains":[93],"it":[94],"with":[95,200],"specific":[97],"template.":[99],"In":[100],"addition,":[101],"most":[102],"exploit":[104],"latent":[106],"relationship":[107],"words":[109,165],"sentence":[112],"pre-extracted":[114,141],"regions":[116,126,146,157],"yet":[120],"ignore":[121],"effects":[123,169],"unextracted":[125,145,174],"on":[127,139,188,198,212],"predicted":[128,164],"We":[130],"develop":[131],"residual":[133],"attention":[134,151],"mechanism":[135],"simultaneously":[137],"focus":[138],"objects":[143,172],"image.":[149],"Residual":[150],"is":[152,197],"capable":[153],"capturing":[155],"precise":[156],"corresponding":[161],"regions.":[175],"The":[176],"effectiveness":[177],"our":[179],"entire":[180],"framework":[181,196],"each":[183],"proposed":[184],"module":[185],"verified":[187],"two":[189],"classical":[190],"datasets:":[191],"MSCOCO":[192],"Flickr30k.":[194],"Our":[195],"par":[199],"even":[202],"better":[203],"than":[204],"state-of-the-art":[206],"achieves":[209],"superior":[210],"performance":[211],"COCO":[213],"captioning":[214],"Leaderboard.":[215]},"counts_by_year":[{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}