{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:06:00Z","timestamp":1775228760358,"version":"3.50.1"},"reference-count":50,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,20]],"date-time":"2024-12-20T00:00:00Z","timestamp":1734652800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,20]],"date-time":"2024-12-20T00:00:00Z","timestamp":1734652800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61973294"],"award-info":[{"award-number":["61973294"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,20]]},"DOI":"10.1109\/acai63924.2024.10899669","type":"proceedings-article","created":{"date-parts":[[2025,3,3]],"date-time":"2025-03-03T18:27:20Z","timestamp":1741026440000},"page":"1-8","source":"Crossref","is-referenced-by-count":1,"title":["CLIP-ViT Detector: Side Adapter with Prompt for Vision Transformer Object Detection"],"prefix":"10.1109","author":[{"given":"Han","family":"Yang","sequence":"first","affiliation":[{"name":"Institute of Intelligent Machines,HFIPS Chinese Academy of Sciences,Hefei,China"}]},{"given":"Minxia","family":"Xu","sequence":"additional","affiliation":[{"name":"Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences,Hangzhou,China"}]},{"given":"Zhiyong","family":"Sun","sequence":"additional","affiliation":[{"name":"Institute of Intelligent Machines,HFIPS Chinese Academy of Sciences,Hefei,China"}]},{"given":"Bo","family":"Song","sequence":"additional","affiliation":[{"name":"Institute of Intelligent Machines,HFIPS Chinese Academy of Sciences,Hefei,China"}]},{"given":"Erkang","family":"Cheng","sequence":"additional","affiliation":[{"name":"Institute of Intelligent Machines,HFIPS Chinese Academy of Sciences,Hefei,China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref2","volume-title":"Yolov3: An incremental improvement","author":"Redmon","year":"2018"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref4","volume-title":"Deformable detr: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020"},{"key":"ref5","volume-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref6","volume-title":"Toward transformer-based object detection","author":"Beal","year":"2020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01172"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_5"},{"key":"ref12","first-page":"26183","article-title":"You only look at one sequence: Rethinking transformer in vision through object detection","volume":"34","author":"Fang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref13","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00679"},{"key":"ref15","volume-title":"F-vlm: Open-vocabulary object detection upon frozen vision and language models","author":"Kuo","year":"2022"},{"key":"ref16","volume-title":"Open-vocabulary object detection via vision and language knowledge distillation","author":"Gu","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref20","first-page":"5682","article-title":"S-prompts learning with pre-trained transformers: An occam\u2019s razor for domain incremental learning","volume":"35","author":"Wang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","volume-title":"Exploring visual prompts for adapting large-scale models","author":"Bahng","year":"2022"},{"key":"ref22","first-page":"16664","article-title":"Adaptformer: Adapting vision transformers for scalable visual recognition","volume":"35","author":"Chen","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01393"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_41"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00775"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01075"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref31","volume-title":"Prompt generation networks for input-based adaptation of frozen vision transformers","author":"Loedeman","year":"2022"},{"key":"ref32","first-page":"6575","article-title":"Feature-proxy transformer for few-shot segmentation","volume":"35","author":"Zhang","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref33","volume-title":"Neural prompt search","author":"Zhang","year":"2022"},{"key":"ref34","first-page":"2790","article-title":"Parameter-efficient transfer learning for nlp","volume-title":"International conference on machine learning","author":"Houlsby","year":"2019"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00516"},{"key":"ref36","first-page":"12991","article-title":"Lst: Ladder side-tuning for parameter and memory efficient transfer learning","volume":"35","author":"Sung","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref37","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"International conference on machine learning","author":"Touvron","year":"2021"},{"key":"ref38","volume-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref40","volume-title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2022"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"ref42","volume-title":"MMDetection: Open mmlab detection toolbox and benchmark","author":"Chen","year":"2019"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref44","first-page":"13937","article-title":"Dynam-icvit: Efficient vision transformers with dynamic token sparsification","volume":"34","author":"Rao","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00078"},{"key":"ref46","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"ref48","volume-title":"Dab-detr: Dynamic anchor boxes are better queries for detr","author":"Liu","year":"2022"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"}],"event":{"name":"2024 7th International Conference on Algorithms, Computing and Artificial Intelligence (ACAI)","location":"Guangzhou, China","start":{"date-parts":[[2024,12,20]]},"end":{"date-parts":[[2024,12,22]]}},"container-title":["2024 7th International Conference on Algorithms, Computing and Artificial Intelligence (ACAI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10899099\/10899447\/10899669.pdf?arnumber=10899669","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,4]],"date-time":"2025-03-04T05:55:51Z","timestamp":1741067751000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10899669\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,20]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/acai63924.2024.10899669","relation":{},"subject":[],"published":{"date-parts":[[2024,12,20]]}}}