{"id":"https://openalex.org/W4402352343","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650474","title":"Look and Review, Then Tell: Generate More Coherent Paragraphs from Images by Fusing Visual and Textual Information","display_name":"Look and Review, Then Tell: Generate More Coherent Paragraphs from Images by Fusing Visual and Textual Information","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402352343","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650474"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10650474","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10650474","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5115602239","display_name":"Zhen Yang","orcid":"https://orcid.org/0000-0002-6058-0217"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Yang","raw_affiliation_strings":["Beijing Institute of Technology,School of Computer Science and Technology,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047425057","display_name":"Hongxia Zhao","orcid":"https://orcid.org/0000-0003-3934-8082"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongxia Zhao","raw_affiliation_strings":["Institute of Automation Academy of Sciences,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101796595","display_name":"Ping Jian","orcid":"https://orcid.org/0000-0001-7236-2922"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ping Jian","raw_affiliation_strings":["Beijing Institute of Technology,School of Computer Science and Technology,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16704342,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"139","issue":null,"first_page":"1","last_page":"8"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9948999881744385,"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":0.9940999746322632,"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/computer-science","display_name":"Computer science","score":0.6903558969497681},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6341515779495239},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5985608696937561},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4216029942035675},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3540530502796173},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34967952966690063},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.06314864754676819}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6903558969497681},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6341515779495239},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5985608696937561},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4216029942035675},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3540530502796173},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34967952966690063},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.06314864754676819}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10650474","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10650474","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","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":47,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2105103432","https://openalex.org/W2549599535","https://openalex.org/W2560674852","https://openalex.org/W2600463316","https://openalex.org/W2605045867","https://openalex.org/W2745461083","https://openalex.org/W2747329762","https://openalex.org/W2890585349","https://openalex.org/W2890781596","https://openalex.org/W2897964062","https://openalex.org/W2930957955","https://openalex.org/W2953322005","https://openalex.org/W2962968835","https://openalex.org/W2963758027","https://openalex.org/W3014521650","https://openalex.org/W3018537643","https://openalex.org/W3090108315","https://openalex.org/W3105531629","https://openalex.org/W3115720040","https://openalex.org/W3162303990","https://openalex.org/W3174264667","https://openalex.org/W3174313486","https://openalex.org/W4283315784","https://openalex.org/W4293518031","https://openalex.org/W4312697499","https://openalex.org/W4385714406","https://openalex.org/W4389261383","https://openalex.org/W4390050357","https://openalex.org/W4392669905","https://openalex.org/W6620707391","https://openalex.org/W6631190155","https://openalex.org/W6678262379","https://openalex.org/W6752051073","https://openalex.org/W6754278344","https://openalex.org/W6776788304","https://openalex.org/W6791353385","https://openalex.org/W6811293548","https://openalex.org/W6852874933","https://openalex.org/W6855088408","https://openalex.org/W6858260899","https://openalex.org/W6859222214","https://openalex.org/W6860537150"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Image":[0],"paragraph":[1,136],"captioning":[2],"aims":[3],"to":[4,40,59,66,91,102,132],"describe":[5],"given":[6],"images":[7],"by":[8,16,119],"generating":[9],"natural":[10],"paragraphs.":[11],"Unfortunately,":[12],"the":[13,25,32,46,49,56,93,104,113,116,129,135,140,154,172,185],"paragraphs":[14],"generated":[15],"existing":[17,193],"methods":[18],"typically":[19],"suffer":[20],"from":[21],"poor":[22],"coherence":[23],"since":[24],"visual":[26,38,73,94,98,121,141],"information":[27,95,142,150],"is":[28,126,144,162],"inevitably":[29],"lost":[30],"after":[31],"pooling":[33],"operation,":[34],"which":[35,111],"maps":[36],"numerous":[37],"features":[39,99,118],"only":[41,163],"one":[42],"global":[43],"vector.":[44],"On":[45],"other":[47],"hand,":[48],"pooled":[50],"vectors":[51,122],"make":[52],"it":[53],"harder":[54],"for":[55],"language":[57,130],"models":[58],"interact":[60],"with":[61,123,192],"details":[62],"in":[63,97,160,168],"images,":[64],"leading":[65],"generic":[67],"or":[68],"even":[69],"wrong":[70],"descriptions":[71],"of":[72,115,166,174],"details.":[74],"In":[75,138],"this":[76],"paper,":[77],"we":[78],"propose":[79],"a":[80,107,148],"simple":[81],"yet":[82],"effective":[83],"module":[84],"called":[85],"Visual":[86],"Information":[87],"Enhancement":[88],"Module":[89],"(VIEM)":[90],"prevent":[92],"loss":[96,143,159],"pooling.":[100],"Meanwhile,":[101],"model":[103,131],"inter-sentence":[105],"dependency,":[106],"fusion":[108],"gate":[109],"mechanism,":[110],"makes":[112],"most":[114],"nonpooled":[117],"fusing":[120],"textual":[124],"information,":[125],"introduced":[127],"into":[128],"furthermore":[133],"improve":[134],"coherence.":[137],"experiments,":[139],"quantitatively":[145],"measured":[146],"through":[147],"mutual":[149],"based":[151],"method.":[152],"Surprisingly,":[153],"results":[155],"indicates":[156],"that":[157,167,184],"such":[158],"VIEM":[161],"approximately":[164],"50%":[165],"pooling,":[169],"effectively":[170],"demonstrating":[171],"efficacy":[173],"VIEM.":[175],"Moreover,":[176],"extensive":[177],"experiments":[178],"on":[179],"Stanford":[180],"image-paragraph":[181],"dataset":[182],"show":[183],"proposed":[186],"method":[187],"achieves":[188],"promising":[189],"performance":[190],"compared":[191],"methods1.":[194]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}