{"id":"https://openalex.org/W4411996346","doi":"https://doi.org/10.1109/icict64582.2025.00081","title":"MEKA: Multimodal External Knowledge Augmentation for Social Media Image Captioning","display_name":"MEKA: Multimodal External Knowledge Augmentation for Social Media Image Captioning","publication_year":2025,"publication_date":"2025-03-14","ids":{"openalex":"https://openalex.org/W4411996346","doi":"https://doi.org/10.1109/icict64582.2025.00081"},"language":"en","primary_location":{"id":"doi:10.1109/icict64582.2025.00081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icict64582.2025.00081","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 8th International Conference on Information and Computer Technologies (ICICT)","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":null,"display_name":"Madhumita Dash","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Madhumita Dash","raw_affiliation_strings":["Accrete AI,Mumbai,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Accrete AI,Mumbai,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tejas Pant","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tejas Pant","raw_affiliation_strings":["Accrete AI,Mumbai,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Accrete AI,Mumbai,India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5118808244","display_name":"Himanshu Parganiha","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Himanshu Parganiha","raw_affiliation_strings":["Accrete AI,Mumbai,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Accrete AI,Mumbai,India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"479","last_page":"485"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9912999868392944,"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":0.9900000095367432,"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":0.9572104215621948},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7540003657341003},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.6290850043296814},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5553014874458313},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3962874412536621},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3776755928993225},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3671705722808838},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3574630320072174},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34485703706741333},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2937996983528137}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9572104215621948},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7540003657341003},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.6290850043296814},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5553014874458313},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3962874412536621},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3776755928993225},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3671705722808838},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3574630320072174},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34485703706741333},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2937996983528137}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icict64582.2025.00081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icict64582.2025.00081","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 8th International Conference on Information and Computer Technologies (ICICT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2982573303","https://openalex.org/W3034689697","https://openalex.org/W4284670349","https://openalex.org/W4382131058","https://openalex.org/W4386076004","https://openalex.org/W4389518609","https://openalex.org/W4389518901","https://openalex.org/W4400529431","https://openalex.org/W4402704606","https://openalex.org/W4402727075","https://openalex.org/W4402916777","https://openalex.org/W4403780601","https://openalex.org/W4403938643","https://openalex.org/W4405304393","https://openalex.org/W6849177959","https://openalex.org/W6851592950","https://openalex.org/W6856883136","https://openalex.org/W6857301099","https://openalex.org/W6861107346","https://openalex.org/W6862183416","https://openalex.org/W6862322214","https://openalex.org/W6862366005"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W4210416330","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W1938708284","https://openalex.org/W4380190185"],"abstract_inverted_index":{"Multimodal":[0],"Large":[1],"Language":[2],"Models":[3],"(MLLMs)":[4],"have":[5],"shown":[6],"promising":[7],"results":[8,90],"in":[9,106,130],"image":[10,52,69],"captioning":[11,53],"tasks.":[12],"However,":[13],"their":[14,37],"effectiveness":[15],"for":[16,33,54,147],"social":[17,55,148],"media":[18,56,149],"content":[19,150],"is":[20,128],"limited":[21],"by":[22,58],"static":[23],"training":[24],"data":[25],"and":[26,71,137,156],"inability":[27],"to":[28,74,120,139],"capture":[29],"real-time":[30,141],"context,":[31,154],"especially":[32],"events":[34,158],"that":[35,49,92,114],"postdate":[36],"training.":[38],"We":[39],"present":[40],"MEKA":[41,64,93],"(Multimodal":[42],"External":[43],"Knowledge":[44],"Augmentation),":[45],"a":[46,102],"novel":[47],"framework":[48],"enhances":[50],"MLLM-based":[51],"posts":[57],"dynamically":[59],"integrating":[60],"external":[61],"knowledge":[62,84],"sources.":[63],"combines":[65],"web":[66],"search,":[67,70],"reverse":[68],"entity":[72,116],"recognition":[73,117],"provide":[75],"rich":[76],"contextual":[77],"information":[78,142],"without":[79],"relying":[80],"on":[81],"the":[82,86,123,131],"internal":[83],"of":[85,125],"MLLMs.":[87],"Our":[88],"experimental":[89],"demonstrate":[91],"significantly":[94,118],"outperforms":[95],"state-of-the-art":[96],"models":[97],"such":[98],"as":[99],"GPT-4-turbo,":[100],"achieving":[101],"97%":[103],"win":[104],"rate":[105],"human":[107],"evaluations.":[108],"Through":[109],"ablation":[110],"studies,":[111],"we":[112],"show":[113],"while":[115],"contributes":[119],"caption":[121],"quality,":[122],"impact":[124],"query":[126],"generation":[127],"minimal":[129],"current":[132,157],"implementation.":[133],"MEKA's":[134],"scalable":[135],"architecture":[136],"ability":[138],"incorporate":[140],"make":[143],"it":[144],"particularly":[145],"effective":[146],"where":[151],"understanding":[152],"cultural":[153],"humor,":[155],"are":[159],"crucial.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}