{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:59:36Z","timestamp":1777658376645,"version":"3.51.4"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,3,14]],"date-time":"2025-03-14T00:00:00Z","timestamp":1741910400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,14]],"date-time":"2025-03-14T00:00:00Z","timestamp":1741910400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,3,14]]},"DOI":"10.1109\/icict64582.2025.00081","type":"proceedings-article","created":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T17:27:23Z","timestamp":1751563643000},"page":"479-485","source":"Crossref","is-referenced-by-count":1,"title":["MEKA: Multimodal External Knowledge Augmentation for Social Media Image Captioning"],"prefix":"10.1109","author":[{"given":"Madhumita","family":"Dash","sequence":"first","affiliation":[{"name":"Accrete AI,Mumbai,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tejas","family":"Pant","sequence":"additional","affiliation":[{"name":"Accrete AI,Mumbai,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Himanshu","family":"Parganiha","sequence":"additional","affiliation":[{"name":"Accrete AI,Mumbai,India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"The claude 3 model family: Opus, sonnet, haiku","volume":"1","year":"2024","journal-title":"Claude-3 Model Card"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01275"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00188"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-9440-9_25"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/BESC64747.2024.10780559"},{"key":"ref7","volume-title":"SerpAPI"},{"key":"ref8","volume-title":"SerpAPI organic results"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.89"},{"key":"ref10","article-title":"Visual question answering instruction: Unlocking multimodal large language model to domain-specific visual multitasks","author":"Lee","year":"2024","journal-title":"arXiv preprint"},{"key":"ref11","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning. PMLR","author":"Li","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599873"},{"key":"ref13","first-page":"22820","article-title":"Fine-grained late-interaction multi-modal retrieval for retrieval augmented visual question answering","volume":"36","author":"Lin","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3661377"},{"key":"ref15","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref16","article-title":"Rar: Retrieving and ranking augmented mllms for visual recognition","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.242"},{"key":"ref18","volume-title":"Hello GPT-4o"},{"key":"ref19","volume-title":"Models"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01240"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00278"},{"key":"ref22","volume-title":"Amazon Rekognition"},{"key":"ref23","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01305"},{"key":"ref25","article-title":"Freshllms: Refreshing large language models with search engine augmentation","author":"Vu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Mmidr: Teaching large language model to interpret multimodal misinformation via knowledge distillation","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02408"},{"key":"ref28","volume-title":"X. X API endpoint map"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681453"}],"event":{"name":"2025 8th International Conference on Information and Computer Technologies (ICICT)","location":"Hawaii-Hilo, HI, USA","start":{"date-parts":[[2025,3,14]]},"end":{"date-parts":[[2025,3,16]]}},"container-title":["2025 8th International Conference on Information and Computer Technologies (ICICT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11058461\/11058401\/11058541.pdf?arnumber=11058541","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T05:13:07Z","timestamp":1751605987000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11058541\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,14]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icict64582.2025.00081","relation":{},"subject":[],"published":{"date-parts":[[2025,3,14]]}}}