{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T16:03:43Z","timestamp":1784131423224,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":26,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819235094","type":"print"},{"value":"9789819235100","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T00:00:00Z","timestamp":1784160000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T00:00:00Z","timestamp":1784160000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2027]]},"DOI":"10.1007\/978-981-92-3510-0_29","type":"book-chapter","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T15:04:55Z","timestamp":1784127895000},"page":"340-353","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Light-Weight Self-Prompting Foundation Model for Automatous Video Object Segmentation"],"prefix":"10.1007","author":[{"given":"Zhaoyuan","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Naiyang","family":"Guan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yinghui","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Longfei","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,16]]},"reference":[{"key":"29_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.128609","volume":"292","author":"Y Li","year":"2025","unstructured":"Li, Y., Hu, C., Ren, K., Xi, H., Fan, J.: UASeg: Uncertainty aware weakly supervised semantic segmentation for autonomous driving. Expert Syst. Appl. 292, 128609 (2025)","journal-title":"Expert Syst. Appl."},{"key":"29_CR2","volume-title":"Proceedings of the SIGGRAPH 2025","author":"Y Tu","year":"2025","unstructured":"Tu, Y., Luo, H., Chen, X., Ji, S., Bai, X., Zhao, H.: VideoAnydoor: high-fidelity video object insertion with precise motion control. In: Proceedings of the SIGGRAPH 2025. Association for Computing Machinery, New York, USA (2025)"},{"issue":"5","key":"29_CR3","doi-asserted-by":"publisher","first-page":"2182","DOI":"10.1109\/TMI.2025.3526955","volume":"44","author":"X Li","year":"2025","unstructured":"Li, X., Cui, C., Shi, S., Fei, H., Hu, Y.: Semi-supervised echocardiography video segmentation via adaptive spatio-temporal tensor semantic awareness and memory flow. IEEE Trans. Med. Imaging. 44(5), 2182\u20132193 (2025)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"29_CR4","first-page":"1","volume-title":"ICASSP 2025","author":"M Mansoori","year":"2025","unstructured":"Mansoori, M., Shahabodini, S., Abouei, J., Plataniotis, K.N., Mohammadi, A.: Self-prompting polyp segmentation in colonoscopy using hybrid YOLO-SAM2 model. In: ICASSP 2025, pp. 1\u20135 (2025)"},{"issue":"1","key":"29_CR5","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1007\/s10462-022-10176-7","volume":"56","author":"M Gao","year":"2023","unstructured":"Gao, M., Zheng, F., Yu, J.J.Q., Shan, C., Ding, G., Han, J.: Deep learning for video object segmentation: a review. Artif. Intell. Rev. 56(1), 457\u2013531 (2023)","journal-title":"Artif. Intell. Rev."},{"key":"29_CR6","first-page":"3992","volume-title":"ICCV 2023","author":"A Kirillov","year":"2023","unstructured":"Kirillov, A., et al.: Segment anything. In: ICCV 2023, pp. 3992\u20134003 (2023)"},{"key":"29_CR7","volume-title":"CoRR","author":"J Yang","year":"2023","unstructured":"Yang, J., Gao, M., Li, Z., Gao, S., Wang, F., Zheng, F.: Track anything: segment anything meets videos. In: CoRR, vol. abs\/2304.11968,  (2023)"},{"key":"29_CR8","volume-title":"CoRR","author":"Y Cheng","year":"2023","unstructured":"Cheng, Y., et al.: Segment and track anything. In: CoRR, vol. abs\/2305.06558,  (2023)"},{"key":"29_CR9","first-page":"640","volume-title":"ECCV 2022","author":"HK Cheng","year":"2022","unstructured":"Cheng, H.K., Schwing, A.G.: XMem: long-term video object segmentation with an Atkinson-Shiffrin memory model. In: ECCV 2022, pp. 640\u2013658. Springer Nature (2022)"},{"key":"29_CR10","first-page":"36324","volume-title":"Advances in Neural Information Processing Systems","author":"Z Yang","year":"2022","unstructured":"Yang, Z., Yang, Y.: Decoupling features in hierarchical propagation for video object segmentation. In: Advances in Neural Information Processing Systems, pp. 36324\u201336336. Curran Associates, Inc. (2022)"},{"key":"29_CR11","unstructured":"Ravi, N., et al.: SAM 2: segment anything in images and videos. In: ICLR 2025, Singapore (2025)"},{"key":"29_CR12","first-page":"9302","volume-title":"WACV 2025","author":"F Raji\u010d","year":"2025","unstructured":"Raji\u010d, F., Ke, L., Tai, Y., Tang, C., Danelljan, M., Yu, F.: Segment anything meets point tracking. In: WACV 2025, pp. 9302\u20139311 (2025)"},{"key":"29_CR13","first-page":"291","volume-title":"ACCV 2024","author":"J Xie","year":"2025","unstructured":"Xie, J., Yang, C., Xie, W., Zisserman, A.: Moving object segmentation: all you need is SAM (and flow). In: ACCV 2024, pp. 291\u2013308. Springer Nature, Singapore (2025)"},{"key":"29_CR14","first-page":"18","volume-title":"ECCV 2024, Milan, Italy, September 29-October 4, 2024, Proceedings, Part LXII","author":"N Karaev","year":"2024","unstructured":"Karaev, N., Rocco, I., Graham, B., Neverova, N., Vedaldi, A., Rupprecht, C.: CoTracker: it is better to track together. In: ECCV 2024, Milan, Italy, September 29-October 4, 2024, Proceedings, Part LXII, pp. 18\u201335 (2024)"},{"key":"29_CR15","first-page":"59","volume-title":"ECCV 2022","author":"AW Harley","year":"2022","unstructured":"Harley, A.W., Fang, Z., Fragkiadaki, K.: Particle video revisited: tracking through occlusions using point trajectories. In: ECCV 2022, pp. 59\u201375. Springer Nature (2022)"},{"key":"29_CR16","doi-asserted-by":"crossref","unstructured":"Xie, J., Xie, W., Zisserman, A.: Appearance-based refinement for object-centric motion segmentation. In: ECCV 2024: Proceedings, Part XXXIX, vol. 2024, pp. 238\u2013256","DOI":"10.1007\/978-3-031-72933-1_14"},{"key":"29_CR17","first-page":"22139","volume-title":"CVPR 2023","author":"E Meunier","year":"2023","unstructured":"Meunier, E., Bouthemy, P.: Unsupervised space-time network for temporally-consistent segmentation of multiple motions. In: CVPR 2023, pp. 22139\u201322148 (2023)"},{"key":"29_CR18","first-page":"5314","volume-title":"CVPR 2023 Workshops","author":"H Mokayed","year":"2023","unstructured":"Mokayed, H., Nayebiastaneh, A., De, K., Sozos, S., Hagner, O., Backe, B.: Nordic Vehicle Dataset (NVD): performance of vehicle detectors using newly captured NVD from UAV in different snowy weather conditions. In: CVPR 2023 Workshops, pp. 5314\u20135322 (2023)"},{"key":"29_CR19","volume-title":"CoRR","author":"T Zhou","year":"2024","unstructured":"Zhou, T., Luo, W., Ye, Q., Shi, Z., Chen, J.: SAM-PD: how far can SAM take us in tracking and segmenting anything in videos by prompt denoising. In: CoRR, vol. abs\/2403.04194,  (2024)"},{"key":"29_CR20","unstructured":"Zhang, R., et al.: Personalize segment anything model with one shot. In: ICLR 2024, Vienna, Austria (2024)"},{"key":"29_CR21","first-page":"4222","volume-title":"Proceedings of Machine Learning Research","author":"Y Zhang","year":"2024","unstructured":"Zhang, Y., Ma, L., Pal, S., Zhang, Y., Coates, M.: Multi-resolution time-series transformer for long-term forecasting. In: Proceedings of Machine Learning Research, vol. 238, pp. 4222\u20134230. PMLR (2024)"},{"key":"29_CR22","unstructured":"Bolya, D., Ryali, C., Hoffman, J., Feichtenhofer, C.: Window attention is bugged: how not to interpolate position embeddings. In: ICLR 2024, Vienna, Austria (2024)"},{"key":"29_CR23","volume-title":"CoRR","author":"H Liu","year":"2025","unstructured":"Liu, H., Watanabe, H.: InterpIoU: rethinking bounding box regression with interpolation-based IoU optimization. In: CoRR, vol. abs\/2507.12420,  (2025)"},{"key":"29_CR24","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: ICCV 2017, pp. 2999\u20133007","DOI":"10.1109\/ICCV.2017.324"},{"key":"29_CR25","volume-title":"CoRR","author":"J Pont-Tuset","year":"2017","unstructured":"Pont-Tuset, J., Perazzi, F., Caelles, S., Arbel\u00e1ez, P., Sorkine-Hornung, A., Gool, L.V.: The 2017 DAVIS challenge on video object segmentation. In: CoRR, vol. abs\/1704.00675,  (2017)"},{"key":"29_CR26","first-page":"20167","volume-title":"ICCV 2023","author":"H Ding","year":"2023","unstructured":"Ding, H., Liu, C., He, S., Jiang, X., Torr, P.H.S., Bai, S.: MOSE: a new dataset for video object segmentation in complex scenes. In: ICCV 2023, pp. 20167\u201320177 (2023)"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-3510-0_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T15:04:59Z","timestamp":1784127899000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3510-0_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,16]]},"ISBN":["9789819235094","9789819235100"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3510-0_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,16]]},"assertion":[{"value":"16 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Toronto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2026a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2026\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}