{"id":"https://openalex.org/W2871882974","doi":"https://doi.org/10.1109/icip.2018.8451083","title":"Topic-Guided Attention for Image Captioning","display_name":"Topic-Guided Attention for Image Captioning","publication_year":2018,"publication_date":"2018-09-07","ids":{"openalex":"https://openalex.org/W2871882974","doi":"https://doi.org/10.1109/icip.2018.8451083","mag":"2871882974"},"language":"en","primary_location":{"id":"doi:10.1109/icip.2018.8451083","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2018.8451083","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 25th IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},"type":"preprint","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/A5056984944","display_name":"Zhihao Zhu","orcid":"https://orcid.org/0000-0002-4063-6009"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhihao Zhu","raw_affiliation_strings":["Institute of Artificial Intelligence and Robotics, Xian Jiaotong University, P. R. China"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence and Robotics, Xian Jiaotong University, P. R. China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101590799","display_name":"Xue Zhan","orcid":"https://orcid.org/0000-0003-0529-0417"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhan Xue","raw_affiliation_strings":["Institute of Artificial Intelligence and Robotics, Xian Jiaotong University, P. R. China"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence and Robotics, Xian Jiaotong University, P. R. China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005376529","display_name":"Zejian Yuan","orcid":"https://orcid.org/0000-0001-5548-3634"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zejian Yuan","raw_affiliation_strings":["Institute of Artificial Intelligence and Robotics, Xian Jiaotong University, P. R. China"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence and Robotics, Xian Jiaotong University, P. R. China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5056984944"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":2.02135555,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.86836192,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2615","last_page":"2619"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.996399998664856,"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"}},{"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"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.9669896364212036},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8299105167388916},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.7512990236282349},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.7342328429222107},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7064912915229797},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5567999482154846},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.42676016688346863},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3754546344280243},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3254985809326172},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.1315707564353943}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9669896364212036},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8299105167388916},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.7512990236282349},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.7342328429222107},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7064912915229797},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5567999482154846},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.42676016688346863},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3754546344280243},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3254985809326172},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.1315707564353943},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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:10.1109/icip.2018.8451083","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2018.8451083","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 25th IEEE International Conference on Image Processing (ICIP)","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":27,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1686810756","https://openalex.org/W1931639407","https://openalex.org/W2064675550","https://openalex.org/W2133564696","https://openalex.org/W2302086703","https://openalex.org/W2404394533","https://openalex.org/W2463955103","https://openalex.org/W2481240925","https://openalex.org/W2550553598","https://openalex.org/W2558533273","https://openalex.org/W2564898401","https://openalex.org/W2591644541","https://openalex.org/W2962835968","https://openalex.org/W2963954913","https://openalex.org/W2964018924","https://openalex.org/W2964121744","https://openalex.org/W2964308564","https://openalex.org/W3098232790","https://openalex.org/W6630875275","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6679434410","https://openalex.org/W6730719754","https://openalex.org/W6785355775","https://openalex.org/W6891831295"],"related_works":["https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W3217388757","https://openalex.org/W1938708284","https://openalex.org/W4380190185","https://openalex.org/W2788191623","https://openalex.org/W3151908889"],"abstract_inverted_index":{"Attention":[0],"mechanisms":[1],"have":[2],"attracted":[3],"considerable":[4],"interest":[5],"in":[6,69,85,117],"image":[7,31,55,66,83,99,104,107],"captioning":[8],"because":[9],"of":[10,29,40],"its":[11],"powerful":[12],"performance.":[13],"Existing":[14],"attention-based":[15],"models":[16],"use":[17],"feedback":[18],"information":[19,52,92],"from":[20,53],"the":[21,30,54,63,86,96,127],"caption":[22],"generator":[23],"as":[24,89],"guidance":[25],"to":[26,93],"determine":[27],"which":[28,57,81,112],"features":[32,105],"should":[33],"be":[34,114],"attended":[35],"to.":[36],"A":[37],"common":[38],"defect":[39],"these":[41],"attention":[42,76,87],"generation":[43],"methods":[44],"is":[45],"that":[46,133],"they":[47],"lack":[48],"a":[49,59,74,90],"higher-level":[50],"guiding":[51,91],"itself,":[56],"sets":[58],"limit":[60],"on":[61,126,139],"selecting":[62],"most":[64,97],"informative":[65],"features.":[67,100],"Therefore,":[68],"this":[70],"paper,":[71],"we":[72,102],"propose":[73],"novel":[75],"mechanism,":[77],"called":[78],"topic-guided":[79],"attention,":[80],"integrates":[82],"topics":[84,108],"model":[88],"help":[94],"select":[95],"important":[98],"Moreover,":[101],"extract":[103],"and":[106],"with":[109],"separate":[110],"networks,":[111],"can":[113],"fine-tuned":[115],"jointly":[116],"an":[118],"end-to-end":[119],"manner":[120],"during":[121],"training.":[122],"The":[123],"experimental":[124],"results":[125],"benchmark":[128],"Microsoft":[129],"COCO":[130],"dataset":[131],"show":[132],"our":[134],"method":[135],"yields":[136],"state-of-art":[137],"performance":[138],"various":[140],"quantitative":[141],"metrics.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":2}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}