{"id":"https://openalex.org/W4402352496","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650884","title":"Enhance Training Objectives for Image Captioning with Decomposed Sequence-level Metric","display_name":"Enhance Training Objectives for Image Captioning with Decomposed Sequence-level Metric","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402352496","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650884"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10650884","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10650884","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":"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/A5018809119","display_name":"Yehuan Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yehuan Wang","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,Department of Computer Science and Technology,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,Department of Computer Science and Technology,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113963020","display_name":"Jiefeng Long","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiefeng Long","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,Department of Computer Science and Technology,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,Department of Computer Science and Technology,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030470805","display_name":"Jian Hu","orcid":"https://orcid.org/0000-0003-2625-8950"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Hu","raw_affiliation_strings":["Nanjing University of Science and Technology,School of Mechanical Engineering,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology,School of Mechanical Engineering,Nanjing,China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100579415","display_name":"Lin Shang","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Shang","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,Department of Computer Science and Technology,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,Department of Computer Science and Technology,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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":0.13256358,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"37","issue":null,"first_page":"1","last_page":"7"},"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":0.9970999956130981,"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":0.994700014591217,"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":0.9670531153678894},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7035243511199951},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.682927131652832},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6792694926261902},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5575279593467712},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5438003540039062},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5422024130821228},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.39947208762168884},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3974618911743164},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.365318238735199},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33882153034210205},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09091073274612427}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9670531153678894},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7035243511199951},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.682927131652832},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6792694926261902},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5575279593467712},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5438003540039062},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5422024130821228},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39947208762168884},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3974618911743164},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.365318238735199},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33882153034210205},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09091073274612427},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/ijcnn60899.2024.10650884","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10650884","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":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1514535095","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1956340063","https://openalex.org/W2024932032","https://openalex.org/W2133459682","https://openalex.org/W2176263492","https://openalex.org/W2194775991","https://openalex.org/W2481240925","https://openalex.org/W2506483933","https://openalex.org/W2575842049","https://openalex.org/W2745461083","https://openalex.org/W2795151422","https://openalex.org/W2901988662","https://openalex.org/W2903928149","https://openalex.org/W2963084599","https://openalex.org/W2963351448","https://openalex.org/W2964896648","https://openalex.org/W2979747405","https://openalex.org/W2986670728","https://openalex.org/W3034655362","https://openalex.org/W3177012523","https://openalex.org/W3203247740","https://openalex.org/W4221147537","https://openalex.org/W4281633595","https://openalex.org/W4292199884","https://openalex.org/W4318718936","https://openalex.org/W4385245566","https://openalex.org/W6620707391","https://openalex.org/W6630875275","https://openalex.org/W6682631176","https://openalex.org/W6685322675","https://openalex.org/W6839015040","https://openalex.org/W6842296751","https://openalex.org/W6849177959","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W4388002133"],"abstract_inverted_index":{"Image":[0],"captioning":[1],"aims":[2],"to":[3,41,70,87,96,114],"generate":[4],"fluent":[5],"and":[6,64,77,92,134,164],"accurate":[7],"descriptions":[8],"for":[9],"images.":[10],"To":[11],"evaluate":[12],"the":[13,32,61,94,116,123,136,153,160],"quality":[14],"of":[15,118,145],"captions,":[16],"various":[17],"metrics":[18,24],"have":[19],"been":[20],"proposed.":[21],"However,":[22],"current":[23],"only":[25],"assess":[26],"captions":[27],"at":[28],"sequence-level,":[29],"which":[30,157],"overwhelms":[31],"distinctions":[33,137],"between":[34,138,162],"each":[35,43,90,119,146],"token.":[36],"Thus,":[37,140],"existing":[38],"objectives":[39],"tend":[40],"treat":[42],"token":[44,147],"equally,":[45],"assigning":[46],"them":[47],"with":[48,132],"identical":[49],"weights":[50,151],"in":[51,57,102,152],"loss":[52,155],"functions.":[53],"Intuitively,":[54],"key":[55,100],"words":[56,69,101],"a":[58,111],"caption":[59],"carry":[60],"primary":[62],"information":[63],"contribute":[65],"more":[66,79,98],"than":[67],"other":[68],"sequence-level":[71,124],"metrics.":[72],"They":[73],"should":[74],"be":[75],"distinguished":[76],"weighted":[78],"during":[80],"training.":[81],"In":[82],"this":[83],"work,":[84],"we":[85,105,141],"propose":[86],"explicitly":[88],"measure":[89],"word":[91],"guide":[93],"model":[95],"focus":[97],"on":[99],"captions.":[103],"Firstly,":[104],"devise":[106],"token-level":[107,127],"CIDEr":[108,125,133],"(CIDEr-T)":[109],"as":[110,148],"new":[112],"metric":[113],"quantify":[115],"importance":[117],"word,":[120],"by":[121],"decomposing":[122],"into":[126],"granularity.":[128],"CIDEr-T":[129,143],"maintains":[130],"consistency":[131],"shows":[135],"tokens.":[139],"engage":[142],"scores":[144],"their":[149],"unique":[150],"raw":[154],"functions,":[156],"can":[158],"bridge":[159],"gap":[161],"training":[163],"evaluation.":[165]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}