{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T16:00:58Z","timestamp":1781366458400,"version":"3.54.1"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,9]],"date-time":"2023-10-09T00:00:00Z","timestamp":1696809600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,9]],"date-time":"2023-10-09T00:00:00Z","timestamp":1696809600000},"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":[[2023,10,9]]},"DOI":"10.1109\/dsaa60987.2023.10302637","type":"proceedings-article","created":{"date-parts":[[2023,11,6]],"date-time":"2023-11-06T19:07:21Z","timestamp":1699297641000},"page":"1-7","source":"Crossref","is-referenced-by-count":3,"title":["A CNN-Transformer Hybrid Network for Multi-scale object detection"],"prefix":"10.1109","author":[{"given":"Jianhong","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingdong","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","first-page":"9627","article-title":"Fcos: Fully convolutional onestage object detection","author":"tian","year":"2019","journal-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision"},{"key":"ref35","author":"carion","year":"2020","journal-title":"End-to-End Object Detection with Transformers"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"ref34","article-title":"ConTNet: Why not use convolution and transformer at the same time","author":"yan","year":"2021","journal-title":"CoRR abs\/2104 13497"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00359"},{"key":"ref14","article-title":"Attention-guided context feature pyramid network for object detection","author":"cao","year":"0","journal-title":"arXiv preprint arXiv 2005 13118 2020"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00615"},{"key":"ref30","first-page":"2961","article-title":"Mask r-cnn","author":"he","year":"2017","journal-title":"Proceedings of the IEEE International Conference on Computer Vision"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01261"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.10.098"},{"key":"ref32","article-title":"FreeAnchor: Learning to Match Anchors for Visual Object Detection","author":"zhang","year":"0","journal-title":"CoRR abs\/1909 02466 (2019)"},{"key":"ref2","article-title":"Escaping the big data paradigm with compact transformers","author":"hassani","year":"2021","journal-title":"ArXiv abs\/2104 05704"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref17","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"European Conference on Computer Vision (ECCV)"},{"key":"ref39","author":"zhu","year":"2020","journal-title":"Deformable detr Deformable transformers for end-to-end object detection"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref38","article-title":"Next-ViT: Next Generation Vision Transformer for Efficient Deployment in Realistic Industrial Scenarios","author":"li","year":"2022","journal-title":"CoRR abs\/2207 05501"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref24","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"ECCV"},{"key":"ref46","article-title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","author":"dosovitskiy","year":"2021","journal-title":"International Conference on Learning Representations"},{"key":"ref23","article-title":"YOLOv4: Optimal speed and accuracy of object detection","author":"bochkovskiy","year":"2020","journal-title":"arXiv 2004 10934"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00917"},{"key":"ref26","author":"song","year":"2021","journal-title":"ViDT An Efficient and Effective Fully Transformerbased Object Detector"},{"key":"ref25","author":"zhu","year":"2020","journal-title":"Deformable detr Deformable transformers for end-to-end object detection"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00916"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_20"},{"key":"ref22","article-title":"Yolov3: An incremental improvement","author":"redmon","year":"2018","journal-title":"arXiv preprint arXiv 1804 02767"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00919"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858826"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00298"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.207"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"ref8","first-page":"21","article-title":"Ssd: Single shot multibox detector","author":"liu","year":"2016","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref7","article-title":"Vitae: Vision transformer advanced byn exploring intrinsic inductive bias","author":"xu","year":"2106","journal-title":"ArXiv abs\/1701"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref4","article-title":"Pruning self-attentions into convolutional layers in single path","author":"he","year":"0","journal-title":"ArXiv abs\/2111 11802 (2021)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00062"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00042"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00089"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3164083"}],"event":{"name":"2023 IEEE 10th International Conference on Data Science and Advanced Analytics (DSAA)","location":"Thessaloniki, Greece","start":{"date-parts":[[2023,10,9]]},"end":{"date-parts":[[2023,10,13]]}},"container-title":["2023 IEEE 10th International Conference on Data Science and Advanced Analytics (DSAA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10302431\/10302461\/10302637.pdf?arnumber=10302637","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,13]],"date-time":"2024-06-13T17:33:03Z","timestamp":1718299983000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10302637\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,9]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/dsaa60987.2023.10302637","relation":{},"subject":[],"published":{"date-parts":[[2023,10,9]]}}}