{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T16:11:09Z","timestamp":1772554269753,"version":"3.50.1"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,27]],"date-time":"2024-10-27T00:00:00Z","timestamp":1729987200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,27]],"date-time":"2024-10-27T00:00:00Z","timestamp":1729987200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100020950","name":"National Science and Technology Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020950","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006785","name":"Google","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006785","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,27]]},"DOI":"10.1109\/icip51287.2024.10647459","type":"proceedings-article","created":{"date-parts":[[2024,9,27]],"date-time":"2024-09-27T18:34:45Z","timestamp":1727462085000},"page":"2494-2500","source":"Crossref","is-referenced-by-count":1,"title":["Open-Vocabulary Panoptic Segmentation Using Bert Pre-Training of Vision-Language Multiway Transformer Model"],"prefix":"10.1109","author":[{"given":"Yi-Chia","family":"Chen","sequence":"first","affiliation":[{"name":"National Taiwan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei-Hua","family":"Li","sequence":"additional","affiliation":[{"name":"National Taiwan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chu-Song","family":"Chen","sequence":"additional","affiliation":[{"name":"National Taiwan University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096379"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10222905"},{"key":"ref3","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref4","article-title":"Open-vocabulary universal image segmentation with maskclip","author":"Ding","year":"2023","journal-title":"ICML"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"ref7","article-title":"VLMo: Unified vision-language pre-training with mixture-of-modality-experts","author":"Bao","year":"2022","journal-title":"NeurIPS"},{"key":"ref8","article-title":"Segformer: Simple and efficient design for semantic segmentation with transformers","author":"Xie","year":"2021","journal-title":"NeurIPS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref10","article-title":"Per-pixel classification is not all you need for semantic segmentation","author":"Cheng","year":"2021","journal-title":"NeurIPS"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref12","article-title":"Vinvl: Making visual representations matter in vision-language models","author":"Zhang","year":"2021","journal-title":"CVPR"},{"key":"ref13","article-title":"Blip-2: Bootstrapping language-image pretraining with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"ICML"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref16","article-title":"Convolutions die hard: Open-vocabulary segmentation with single frozen convolutional clip","author":"Yu","year":"2023","journal-title":"NeurIPS"},{"key":"ref17","article-title":"Vision transformer adapter for dense predictions","author":"Chen","year":"2023","journal-title":"ICLR"},{"key":"ref18","article-title":"Zero-shot semantic segmentation","author":"Bucher","year":"2019","journal-title":"NeurIPS"},{"key":"ref19","article-title":"Language-driven semantic segmentation","author":"Li","year":"2022","journal-title":"ICLR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00683"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01129"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01863"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"}],"event":{"name":"2024 IEEE International Conference on Image Processing (ICIP)","location":"Abu Dhabi, United Arab Emirates","start":{"date-parts":[[2024,10,27]]},"end":{"date-parts":[[2024,10,30]]}},"container-title":["2024 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10647221\/10647122\/10647459.pdf?arnumber=10647459","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,28]],"date-time":"2024-09-28T05:51:54Z","timestamp":1727502714000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10647459\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,27]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icip51287.2024.10647459","relation":{},"subject":[],"published":{"date-parts":[[2024,10,27]]}}}