{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T22:39:23Z","timestamp":1769035163114,"version":"3.49.0"},"reference-count":11,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"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":[[2025,10,22]]},"DOI":"10.1109\/cbmi66578.2025.11339312","type":"proceedings-article","created":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T20:38:56Z","timestamp":1768941536000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Beyond CNNs: Efficient Fine-Tuning of Multi-Modal LLMs for Object Detection on Low-Data Regimes"],"prefix":"10.1109","author":[{"given":"Nirmal","family":"Elamon","sequence":"first","affiliation":[{"name":"Artificial Creative intelligence (ACI) Expedia Group,Seattle,USA"}]},{"given":"Rouzbeh","family":"Davoudi","sequence":"additional","affiliation":[{"name":"Artificial Creative intelligence (ACI) Expedia Group,Seattle,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref3","article-title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal","author":"Ren","journal-title":"2015"},{"key":"ref4","volume-title":"Text recognition on images using pre-trained CNN","author":"Rizky","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IVCNZ48456.2019.8961031"},{"key":"ref6","article-title":"Learning Transferable Visual Models From Natural Language Supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Radford"},{"key":"ref7","article-title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","author":"Abdin","year":"2024","journal-title":"C"},{"key":"ref8","volume-title":"The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)","author":"Yang","year":"2023"},{"key":"ref9","volume-title":"Lumos: Empowering Multimodal LLMs with Scene Text Recognition","author":"Shenoy","year":"2024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"}],"event":{"name":"2025 International Conference on Content-Based Multimedia Indexing (CBMI)","location":"Dublin, Ireland","start":{"date-parts":[[2025,10,22]]},"end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 International Conference on Content-Based Multimedia Indexing (CBMI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11339229\/11339242\/11339312.pdf?arnumber=11339312","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T08:02:45Z","timestamp":1768982565000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11339312\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":11,"URL":"https:\/\/doi.org\/10.1109\/cbmi66578.2025.11339312","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}