{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T17:26:14Z","timestamp":1783099574339,"version":"3.54.6"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3535404","type":"journal-article","created":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T18:44:24Z","timestamp":1738089864000},"page":"3501-3512","source":"Crossref","is-referenced-by-count":3,"title":["GEM: Boost Simple Network for Glass Surface Segmentation via Vision Foundation Models"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2305-1201","authenticated-orcid":false,"given":"Jing","family":"Hao","sequence":"first","affiliation":[{"name":"University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4530-2606","authenticated-orcid":false,"given":"Moyun","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinrong","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3971-3484","authenticated-orcid":false,"given":"Kuo Feng","family":"Hung","sequence":"additional","affiliation":[{"name":"University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"22490","article-title":"Exploiting semantic relations for glass surface detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lin","year":"2022"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3013604"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3272224"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3181439"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00374"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01321"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01556"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2013.6738606"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3323890"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3171400"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475240"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3035231"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.393"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00863"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01229"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3256762"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref19","article-title":"The dawn of LMMs: Preliminary explorations with GPT-4V(ision)","author":"Yang","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref21","article-title":"VFMM3D: Releasing the potential of image by vision foundation model for monocular 3D object detection","author":"Ding","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/tase.2025.3542418"},{"key":"ref23","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref24","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref26","article-title":"An image is worth 16 x 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"ref28","article-title":"Faster segment anything: Towards lightweight SAM for mobile applications","author":"Zhang","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00306"},{"key":"ref30","article-title":"Internal-external boundary attention fusion for glass surface segmentation","author":"Han","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/80"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02240"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"ref34","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00110"},{"key":"ref36","first-page":"868","article-title":"Segment everything everywhere all at once","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zou","year":"2024"},{"key":"ref37","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh","year":"2021"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3217384"},{"key":"ref39","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref41","article-title":"Accuracy of segment-anything model (SAM) in medical image segmentation tasks","author":"He","year":"2023"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2023.103540"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s41062-025-02073-z"},{"key":"ref44","article-title":"Segment anything model (SAM) meets glass: Mirror and transparent objects cannot be easily detected","author":"Han","year":"2023"},{"key":"ref45","article-title":"Is synthetic data from generative models ready for image recognition?","author":"He","year":"2022"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00774"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00334"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3232328"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"ref50","article-title":"DINO: DETR with improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2022"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref55","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xie","year":"2021"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01087"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01451"},{"key":"ref59","article-title":"An image is worth 16 x 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00412"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref62","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chu","year":"2021"},{"key":"ref63","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cheng","year":"2021"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01733"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00599"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106506"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10856403.pdf?arnumber=10856403","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,12]],"date-time":"2025-06-12T17:43:36Z","timestamp":1749750216000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10856403\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3535404","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}