{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T02:03:58Z","timestamp":1772935438442,"version":"3.50.1"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"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":[[2025,12,8]]},"DOI":"10.1109\/bigdata66926.2025.11401600","type":"proceedings-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T20:57:57Z","timestamp":1772830677000},"page":"4576-4585","source":"Crossref","is-referenced-by-count":0,"title":["Hybrid CNN-Transformer Architecture for Object Detection and Multimodal Captioning in Educational Contexts"],"prefix":"10.1109","author":[{"given":"Leila","family":"Habibi","sequence":"first","affiliation":[{"name":"University Paris 8,LIASD Laboratory,Saint-Denis,France"}]},{"given":"Madjid","family":"Maidi","sequence":"additional","affiliation":[{"name":"University Paris 8,LIASD Laboratory,Saint-Denis,France"}]},{"given":"Larbi","family":"Boubchir","sequence":"additional","affiliation":[{"name":"University Paris 8,LIASD Laboratory,Saint-Denis,France"}]},{"given":"Boubaker","family":"Daachi","sequence":"additional","affiliation":[{"name":"University Paris 8,LIASD Laboratory,Saint-Denis,France"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref3","article-title":"YOLOv3: An Incremental Improvement","author":"Redmon","year":"2018","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","author":"Bochkovskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"YOLOv5","volume-title":"GitHub repository","author":"Jocher","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"ref7","article-title":"YOLOv8","volume-title":"GitHub repository","author":"Jocher","year":"2023"},{"key":"ref8","article-title":"YOLOv9: Learning What You Want with Conditional Computational Block","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"YOLOv10: Real-Time End-to-End Object Detection","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"YOLOv11: Advancing Real-Time Object Detection","year":"2024","journal-title":"GitHub repository"},{"key":"ref11","article-title":"An Image is Worth $16 \\times 16$ Words: Transformers for Image Recognition at Scale","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Dosovitskiy","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref13","article-title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Zhu","year":"2021"},{"key":"ref14","article-title":"RT-DETR: Real-Time Detection Transformer","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Li","year":"2022"},{"key":"ref16","article-title":"Scaling Instruction-Finetuned Language Models","author":"Chung","year":"2022","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref20","article-title":"Attention is All You Need","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Vaswani","year":"2017"}],"event":{"name":"2025 IEEE International Conference on Big Data (BigData)","location":"Macau, China","start":{"date-parts":[[2025,12,8]]},"end":{"date-parts":[[2025,12,11]]}},"container-title":["2025 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11400704\/11400712\/11401600.pdf?arnumber=11401600","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T07:32:31Z","timestamp":1772868751000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11401600\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/bigdata66926.2025.11401600","relation":{},"subject":[],"published":{"date-parts":[[2025,12,8]]}}}