{"id":"https://openalex.org/W7140121105","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.342","title":"AGIC: Attention-Guided Image Captioning to Improve Caption Relevance","display_name":"AGIC: Attention-Guided Image Captioning to Improve Caption Relevance","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140121105","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.342"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-eacl.342","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.342","pdf_url":"https://aclanthology.org/2026.findings-eacl.342.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-eacl.342.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130382847","display_name":"L. D. M. S. Sai Teja","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"L D M S Sai Teja","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088341794","display_name":"Ashok Urlana","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ashok Urlana","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5019439792","display_name":"Pruthwik Mishra","orcid":"https://orcid.org/0009-0000-3657-5250"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pruthwik Mishra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38708455,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6517","last_page":"6528"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9700999855995178,"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":0.9700999855995178,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.010400000028312206,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.004999999888241291,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8640000224113464},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.6437000036239624},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5357000231742859},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.27869999408721924},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.27059999108314514}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8640000224113464},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.6437000036239624},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6333000063896179},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5357000231742859},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4880000054836273},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4578999876976013},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.27869999408721924},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-eacl.342","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.342","pdf_url":"https://aclanthology.org/2026.findings-eacl.342.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-eacl.342","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.342","pdf_url":"https://aclanthology.org/2026.findings-eacl.342.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140121105.pdf","grobid_xml":"https://content.openalex.org/works/W7140121105.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Despite":[0],"significant":[1],"progress":[2],"in":[3,29],"image":[4,96],"captioning,":[5],"generating":[6],"accurate":[7],"and":[8,46,52,64,92],"descriptive":[9],"captions":[10],"remains":[11],"a":[12,39,90],"long-standing":[13],"challenge.In":[14],"this":[15],"study,":[16],"we":[17,56],"propose":[18],"Attention-Guided":[19],"Image":[20],"Captioning":[21],"(AGIC),":[22],"which":[23],"amplifies":[24],"salient":[25],"visual":[26],"regions":[27],"directly":[28],"the":[30,61],"feature":[31],"space":[32],"to":[33,49],"guide":[34],"caption":[35],"generation.We":[36],"further":[37],"introduce":[38],"hybrid":[40],"decoding":[41],"strategy":[42],"that":[43,69],"combines":[44],"deterministic":[45],"probabilistic":[47],"sampling":[48],"balance":[50],"fluency":[51],"diversity.To":[53],"evaluate":[54],"AGIC,":[55],"conduct":[57],"extensive":[58],"experiments":[59],"on":[60],"Flickr8k,":[62],"Flickr30k":[63],"MSCOCO":[65],"datasets.The":[66],"results":[67],"show":[68],"AGIC":[70,81],"matches":[71],"or":[72],"surpasses":[73],"several":[74],"state-of-the-art":[75],"models":[76],"while":[77],"achieving":[78],"faster":[79],"inference.Moreover,":[80],"demonstrates":[82],"strong":[83],"performance":[84],"across":[85],"multiple":[86],"evaluation":[87],"metrics,":[88],"offering":[89],"scalable":[91],"interpretable":[93],"solution":[94],"for":[95],"captioning.":[97]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-24T00:00:00"}