{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:38:25Z","timestamp":1767339505344,"version":"3.28.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447589","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"6115-6119","source":"Crossref","is-referenced-by-count":1,"title":["Exploration of Visual Prompt in Grounded Pre-Trained Open-Set Detection"],"prefix":"10.1109","author":[{"given":"Qibo","family":"Chen","sequence":"first","affiliation":[{"name":"China Mobile(Zhejiang) Research &#x0026; Innovation Institute"}]},{"given":"Weizhong","family":"Jin","sequence":"additional","affiliation":[{"name":"China Mobile(Zhejiang) Research &#x0026; Innovation Institute"}]},{"given":"Shuchang","family":"Li","sequence":"additional","affiliation":[{"name":"China Mobile(Zhejiang) Research &#x0026; Innovation Institute"}]},{"given":"Mengdi","family":"Liu","sequence":"additional","affiliation":[{"name":"China Mobile(Zhejiang) Research &#x0026; Innovation Institute"}]},{"given":"Li","family":"Yu","sequence":"additional","affiliation":[{"name":"China Mobile(Zhejiang) Research &#x0026; Innovation Institute"}]},{"given":"Jian","family":"Jiang","sequence":"additional","affiliation":[{"name":"China Mobile(Zhejiang) Research &#x0026; Innovation Institute"}]},{"given":"Xiaozheng","family":"Wang","sequence":"additional","affiliation":[{"name":"China Mobile(Zhejiang) Research &#x0026; Innovation Institute"}]}],"member":"263","reference":[{"key":"ref1","first-page":"9287","article-title":"Elevater: A benchmark and toolkit for evaluating language-augmented visual models","volume":"35","author":"Li","year":"2022","journal-title":"NeurIPS"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref4","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"NeurIPS"},{"journal-title":"Deformable detr: Deformable transformers for end-to-end object detection","year":"2020","author":"Zhu","key":"ref5"},{"journal-title":"Open-vocabulary object detection via vision and language knowledge distillation","year":"2021","author":"Gu","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00100"},{"journal-title":"Grounding dino: Marrying dino with grounded pre-training for open-set object detection","year":"2023","author":"Liu","key":"ref10"},{"journal-title":"Omdet: Language-aware object detection with large-scale vision-language multi-dataset pre-training","year":"2022","author":"Zhao","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_41"},{"journal-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref13"},{"issue":"1","key":"ref14","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"The Journal of Machine Learning Research"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref18","first-page":"9125","article-title":"Detclip: Dictionary-enriched visual-concept paralleled pre-training for open-world detection","volume":"35","author":"Yao","year":"2022","journal-title":"NeurIPS"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"journal-title":"Gpt understands, too","year":"2021","author":"Liu","key":"ref20"},{"key":"ref21","first-page":"1931","article-title":"Unifying vision-and-language tasks via text generation","volume-title":"ICML","author":"Cho"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref23","first-page":"200","article-title":"Multimodal few-shot learning with frozen language models","volume":"34","author":"Tsimpoukelli","year":"2021","journal-title":"NeurIPS"},{"key":"ref24","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2006.479"},{"journal-title":"Categorical reparameterization with gumbel-softmax","year":"2016","author":"Jang","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447589.pdf?arnumber=10447589","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:32:00Z","timestamp":1722573120000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447589\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447589","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}