{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T14:00:01Z","timestamp":1769090401289,"version":"3.49.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"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":[[2025,10,22]]},"DOI":"10.1109\/cbmi66578.2025.11339298","type":"proceedings-article","created":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T20:38:56Z","timestamp":1768941536000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Facilitating Interactive Image Labelling Using Fine-Tuned SAM2"],"prefix":"10.1109","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1762-902X","authenticated-orcid":false,"given":"Hermann","family":"F\u00fcrntratt","sequence":"first","affiliation":[{"name":"DIGITAL - Institute for Digital Technologies, JOANNEUM RESEARCH Forschungsgesellschaft mbH,Graz,Austria"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2442-4900","authenticated-orcid":false,"given":"Werner","family":"Bailer","sequence":"additional","affiliation":[{"name":"DIGITAL - Institute for Digital Technologies, JOANNEUM RESEARCH Forschungsgesellschaft mbH,Graz,Austria"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Labelme: Image Polygonal Annotation with Python","author":"Wada","year":"2025"},{"key":"ref2","article-title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","author":"Ren","year":"2024"},{"key":"ref3","volume-title":"Leading Image & Video Data Annotation Platform | CVAT","year":"2025"},{"key":"ref4","volume-title":"Open Source Data Labeling","author":"Signal","year":"2025"},{"key":"ref5","volume-title":"Labelbox | The data factory for AI teams","year":"2025"},{"key":"ref6","volume-title":"Roboflow: Computer vision tools for developers and enterprises","year":"2025"},{"key":"ref7","article-title":"BEit: BERT pre-training of image transformers","volume-title":"International Conference on Learning Representations","author":"Bao","year":"2022"},{"key":"ref8","first-page":"11966","article-title":"A ConvNet for the 2020s","volume-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Liu"},{"key":"ref9","first-page":"1280","article-title":"Masked-attention Mask Transformer for Universal Image Segmentation","volume-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Cheng"},{"key":"ref10","first-page":"2989","article-title":"OneFormer: One Transformer to Rule Universal Image Segmentation","volume-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Jain"},{"key":"ref11","first-page":"3041","article-title":"Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation","volume-title":"2023 IEEE\/CVF. Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Li"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV51070.2023.00371","volume-title":"Segment Anything","author":"Kirillov","year":"2023"},{"key":"ref13","first-page":"19769","article-title":"Segment everything everywhere all at once","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems, ser. NIPS \u201923","author":"Zou"},{"key":"ref14","first-page":"19358","article-title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","volume-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Fang"},{"key":"ref15","first-page":"14408","article-title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","volume-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Wang"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM58861.2023.10386032"},{"issue":"5","key":"ref17","doi-asserted-by":"crossref","DOI":"10.3390\/rs16050797","article-title":"Segment Anything Model Can Not Segment Anything: Assessing AI Foundation Model\u2019s Generalizability in Permafrost Mapping","volume":"16","author":"Li","year":"2024","journal-title":"Remote Sensing"},{"key":"ref18","first-page":"21 956","article-title":"Low-Resource Vision Challenges for Foundation Models","volume-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Zhang"},{"key":"ref19","volume-title":"Qt | Tools for Each Stage of Software Development Lifecycle","author":"Company","year":"2025"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/AIVR56993.2022.00023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"}],"event":{"name":"2025 International Conference on Content-Based Multimedia Indexing (CBMI)","location":"Dublin, Ireland","start":{"date-parts":[[2025,10,22]]},"end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 International Conference on Content-Based Multimedia Indexing (CBMI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11339229\/11339242\/11339298.pdf?arnumber=11339298","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T21:07:05Z","timestamp":1769029625000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11339298\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/cbmi66578.2025.11339298","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}