{"id":"https://openalex.org/W2892135935","doi":"https://doi.org/10.1109/icip.2018.8451558","title":"Image Captioning with Word Level Attention","display_name":"Image Captioning with Word Level Attention","publication_year":2018,"publication_date":"2018-09-07","ids":{"openalex":"https://openalex.org/W2892135935","doi":"https://doi.org/10.1109/icip.2018.8451558","mag":"2892135935"},"language":"en","primary_location":{"id":"doi:10.1109/icip.2018.8451558","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2018.8451558","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":"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/A5100386889","display_name":"Fang Fang","orcid":"https://orcid.org/0009-0007-0113-9134"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fang Fang","raw_affiliation_strings":["Ministry of Education, Tongji University, Shanghai, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ministry of Education, Tongji University, Shanghai, P. R. China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058982350","display_name":"Hanli Wang","orcid":"https://orcid.org/0000-0002-9999-4871"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanli Wang","raw_affiliation_strings":["Ministry of Education, Tongji University, Shanghai, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ministry of Education, Tongji University, Shanghai, P. R. China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102827532","display_name":"Pengjie Tang","orcid":"https://orcid.org/0000-0001-7523-0175"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengjie Tang","raw_affiliation_strings":["Ministry of Education, Tongji University, Shanghai, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ministry of Education, Tongji University, Shanghai, P. R. China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1278","last_page":"1282"},"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":0.9914000034332275,"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":0.9821000099182129,"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":0.8636624813079834},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8555693030357361},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.8021234273910522},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6951979994773865},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.6893466711044312},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6768543720245361},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6170881986618042},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6046668291091919},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5762832760810852},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5747579336166382},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.5128183960914612},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5109869241714478},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5011816024780273},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4592139720916748},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44215211272239685},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4145280122756958},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.3669188618659973},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06020215153694153}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8636624813079834},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8555693030357361},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.8021234273910522},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6951979994773865},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.6893466711044312},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6768543720245361},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6170881986618042},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6046668291091919},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5762832760810852},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5747579336166382},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.5128183960914612},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5109869241714478},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5011816024780273},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4592139720916748},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44215211272239685},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4145280122756958},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.3669188618659973},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06020215153694153},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip.2018.8451558","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2018.8451558","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W92662927","https://openalex.org/W1514535095","https://openalex.org/W1811254738","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1897761818","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2064675550","https://openalex.org/W2097117768","https://openalex.org/W2101105183","https://openalex.org/W2108325777","https://openalex.org/W2123301721","https://openalex.org/W2194775991","https://openalex.org/W2220981600","https://openalex.org/W2302086703","https://openalex.org/W2550553598","https://openalex.org/W2552161745","https://openalex.org/W2575842049","https://openalex.org/W2732016772","https://openalex.org/W2962706528","https://openalex.org/W2964018924","https://openalex.org/W2964168617","https://openalex.org/W6630875275","https://openalex.org/W6638742206","https://openalex.org/W6639102338","https://openalex.org/W6639694449","https://openalex.org/W6678262379","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W3217195652","https://openalex.org/W947140380","https://openalex.org/W4286432911","https://openalex.org/W4230884544","https://openalex.org/W4245453790","https://openalex.org/W3194985222","https://openalex.org/W3216571906","https://openalex.org/W4214830338","https://openalex.org/W2518587255","https://openalex.org/W4287599800"],"abstract_inverted_index":{"Image":[0],"captioning":[1],"is":[2,54,74,89],"an":[3],"attractive":[4],"and":[5,13,34,139],"challenging":[6],"task":[7],"to":[8,43,76,95,106],"perform":[9],"automatic":[10],"image":[11,78],"description":[12],"a":[14,68,90],"number":[15],"of":[16,24],"works":[17],"are":[18,27],"designed":[19,75],"for":[20,46,83],"this":[21,66],"task.":[22],"Most":[23],"these":[25],"researches":[26],"based":[28],"on":[29,121,137,141],"convolutional":[30],"neural":[31,36],"network":[32,37],"(CNN)":[33],"recurrent":[35],"(RNN),":[38],"where":[39],"the":[40,50,56,61,100,122,128,132],"primary":[41],"input":[42],"language":[44,116],"model":[45,130],"word":[47,58,70,85,108],"prediction":[48],"at":[49,60],"current":[51],"time":[52,63],"step":[53],"usually":[55],"linguistic":[57],"generated":[59],"previous":[62],"step.":[64],"In":[65],"work,":[67],"novel":[69],"level":[71,109],"attention":[72,104,110],"layer":[73],"process":[77],"features":[79],"with":[80,135],"two":[81],"modules":[82],"accurate":[84],"prediction.":[86],"The":[87,118],"first":[88],"bidirectional":[91],"spatial":[92],"embedding":[93],"module":[94,102],"handle":[96],"feature":[97],"maps,":[98],"then":[99],"second":[101],"employs":[103],"mechanism":[105],"extract":[107],"which":[111],"will":[112],"be":[113],"fed":[114],"into":[115],"model.":[117],"experimental":[119],"results":[120],"benchmark":[123],"MSCOCO":[124],"dataset":[125],"demonstrate":[126],"that":[127],"proposed":[129],"achieves":[131],"state-of-the-art":[133],"performances":[134],"106.0":[136],"CIDEr":[138],"34.0":[140],"B-4,":[142],"respectively.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}