{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:23:37Z","timestamp":1763191417044,"version":"3.45.0"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11227195","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Towards Open-World Video Segmentation via Iterative Automatic Prompting"],"prefix":"10.1109","author":[{"given":"Liangzhi","family":"Li","sequence":"first","affiliation":[{"name":"Qufu Normal University,China"}]},{"given":"Xinru","family":"Li","sequence":"additional","affiliation":[{"name":"Qufu Normal University,China"}]},{"given":"Zhouqiang","family":"Jiang","sequence":"additional","affiliation":[{"name":"Osaka University,Japan"}]},{"given":"Xingfu","family":"Cheng","sequence":"additional","affiliation":[{"name":"Qufu Normal University,China"}]},{"given":"Zhaofeng","family":"Niu","sequence":"additional","affiliation":[{"name":"Qufu Normal University,China"}]},{"given":"Bowen","family":"Wang","sequence":"additional","affiliation":[{"name":"Osaka University,Japan"}]},{"given":"Guangshun","family":"Li","sequence":"additional","affiliation":[{"name":"Qufu Normal University,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00172"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.55"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540054"},{"key":"ref4","first-page":"25005","article-title":"Visual prompting via image inpainting","volume":"35","author":"Bar","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.565"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging10120305"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00127"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"article-title":"Sam2long: Enhancing sam 2 for long video segmentation with a training-free memory tree","year":"2024","author":"Ding","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11128804"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01240"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3611020\/mm1"},{"article-title":"Concatenated masked autoencoders as spatial-temporal learner","year":"2023","author":"Jiang","key":"ref13"},{"journal-title":"Ultralytics yolov8","year":"2023","author":"Jocher","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3146922"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00139"},{"article-title":"Am-sam: Automated prompting and mask calibration for segment anything model","year":"2024","author":"Li","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00142"},{"article-title":"Matcher: Segment anything with one shot using allpurpose feature matching","year":"2023","author":"Liu","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01846"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20870-7_35"},{"article-title":"Dinov2: Learning robust visual features without supervision","year":"2023","author":"Oquab","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.372"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"article-title":"The 2017 davis challenge on video object segmentation","year":"2017","author":"Pont-Tuset","key":"ref26"},{"key":"ref27","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"article-title":"Sam 2: Segment anything in images and videos","year":"2024","author":"Ravi","key":"ref28"},{"article-title":"Autosam: Adapting sam to medical images by overloading the prompt encoder","year":"2023","author":"Shaharabany","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02185-6"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02195-4"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_36"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.116"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2024.102463"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00438"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01060"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00660"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00110"},{"article-title":"Det-sam2: Technical report on the self-prompting segmentation framework based on segment anything model 2","year":"2024","author":"Wang","key":"ref39"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00125"},{"article-title":"Blo-sam: Bi-level optimization based overfitting-preventing finetuning of sam","year":"2024","author":"Zhang","key":"ref41"},{"article-title":"Personalize segment anything model with one shot","year":"2023","author":"Zhang","key":"ref42"},{"article-title":"Evaluation study on sam 2 for class-agnostic instance-level segmentation","year":"2024","author":"Zhang","key":"ref43"},{"article-title":"Evf-sam: Early vision-language fusion for text-prompted segment anything model","year":"2024","author":"Zhang","key":"ref44"},{"article-title":"Uvosam: A mask-free paradigm for unsupervised video object segmentation via segment anything model","year":"2023","author":"Zhang","key":"ref45"},{"key":"ref46","first-page":"36","article-title":"Segment everything everywhere all at once","author":"Zou","year":"2024","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11227195.pdf?arnumber=11227195","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:21:00Z","timestamp":1763191260000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11227195\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11227195","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}