{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T08:04:23Z","timestamp":1789459463476,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":57,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373236","type":"print"},{"value":"9783032373243","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-37324-3_28","type":"book-chapter","created":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T07:18:31Z","timestamp":1789456711000},"page":"514-532","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Segmenting, Fast and\u00a0Slow: Real-Time Open-Vocabulary Video Instance Segmentation with\u00a0Dual-Path Processing"],"prefix":"10.1007","author":[{"given":"Luca","family":"Barsellotti","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martin","family":"Sundermeyer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mattia","family":"Segu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nikita","family":"Araslanov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad Ferjad","family":"Naeem","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marcella","family":"Cornia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongqin","family":"Xian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maxim","family":"Berman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,16]]},"reference":[{"key":"28_CR1","doi-asserted-by":"crossref","unstructured":"Athar, A., et al.: BURST: a benchmark for unifying object recognition, segmentation and tracking in video. In: WACV (2023)","DOI":"10.1109\/WACV56688.2023.00172"},{"key":"28_CR2","doi-asserted-by":"crossref","unstructured":"Butler, D., Wulff, J., Stanley, G., Black, M.J.: A naturalistic open source movie for optical flow evaluation. In: ECCV (2012)","DOI":"10.1007\/978-3-642-33783-3_44"},{"key":"28_CR3","doi-asserted-by":"crossref","unstructured":"Cai, H., Li, J., Hu, M., Gan, C., Han, S.: EfficientViT: lightweight multi-scale attention for high-resolution dense prediction. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01587"},{"key":"28_CR4","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"28_CR5","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"28_CR6","unstructured":"Cheng, B., Schwing, A., Kirillov, A.: Per-pixel classification is not all you need for semantic segmentation. In: NeurIPS (2021)"},{"key":"28_CR7","doi-asserted-by":"crossref","unstructured":"Ding, J., Xue, N., Xia, G.S., Dai, D.: Decoupling zero-shot semantic segmentation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01129"},{"key":"28_CR8","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., et al.: FlowNet: learning optical flow with convolutional networks. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.316"},{"key":"28_CR9","doi-asserted-by":"crossref","unstructured":"Gupta, A., Dollar, P., Girshick, R.: LVIS: a dataset for large vocabulary instance segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00550"},{"key":"28_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"1\u20133","key":"28_CR11","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1016\/0004-3702(81)90024-2","volume":"17","author":"B Horn","year":"1981","unstructured":"Horn, B., Schunck, B.: Determining optical flow. Artif. Intell. 17(1\u20133), 185\u2013203 (1981)","journal-title":"Artif. Intell."},{"key":"28_CR12","doi-asserted-by":"crossref","unstructured":"Huang, D., Yu, Z., Anandkumar, A.: MinVIS: a minimal video instance segmentation framework without video-based training. In: NeurIPS (2022)","DOI":"10.52202\/068431-2267"},{"issue":"8","key":"28_CR13","doi-asserted-by":"publisher","first-page":"2555","DOI":"10.1109\/TPAMI.2020.2976928","volume":"43","author":"T Hui","year":"2020","unstructured":"Hui, T., Tang, X., Loy, C.C.: A lightweight optical flow CNN\u2013revisiting data fidelity and regularization. IEEE TPAMI 43(8), 2555\u20132569 (2020)","journal-title":"IEEE TPAMI"},{"key":"28_CR14","doi-asserted-by":"crossref","unstructured":"Ilg, E., Mayer, N., Saikia, T., Keuper, M., Dosovitskiy, A., Brox, T.: FlowNet 2.0: evolution of optical flow estimation with deep networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.179"},{"key":"28_CR15","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"28_CR16","unstructured":"Krylov, I., Nosov, S., Sovrasov, V.: Open Images V5 text annotation and yet another mask text spotter. In: ACML (2021)"},{"key":"28_CR17","doi-asserted-by":"crossref","unstructured":"Li, F., et al.: Mask DINO: towards a unified transformer-based framework for object detection and segmentation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"28_CR18","doi-asserted-by":"crossref","unstructured":"Liang, F., et al.: Open-vocabulary semantic segmentation with mask-adapted CLIP. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"28_CR19","doi-asserted-by":"crossref","unstructured":"Liang, T., Lin, K.Y., Tan, C., Zhang, J., Zheng, W., Hu, J.F.: ReferDINO: referring video object segmentation with visual grounding foundations. In: ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.01861"},{"key":"28_CR20","doi-asserted-by":"publisher","unstructured":"Lin, T., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds) Computer Vision \u2013 ECCV 2014. ECCV 2014. Lecture Notes in Computer Science, vol 8693. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"28_CR21","doi-asserted-by":"publisher","unstructured":"Liu, S., et\u00a0al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds) Computer Vision \u2013 ECCV 2024. ECCV 2024. Lecture Notes in Computer Science, vol. 15105. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72970-6_3","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"28_CR22","unstructured":"Lucas, B., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: IJCAI, pp. 674\u2013679 (1981)"},{"key":"28_CR23","unstructured":"Lv, W., Zhao, Y., Chang, Q., Huang, K., Wang, G., Liu, Y.: RT-DETRv2: improved baseline with bag-of-freebies for real-time detection transformer. arXiv:2407.17140 [cs.CV] (2024)"},{"key":"28_CR24","doi-asserted-by":"crossref","unstructured":"Mayer, N., et al.: A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.438"},{"key":"28_CR25","doi-asserted-by":"crossref","unstructured":"Nagaraja, V., Morariu, V., Davis, L.: Modeling context between objects for referring expression understanding. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"28_CR26","doi-asserted-by":"crossref","unstructured":"Nilsson, D., Sminchisescu, C.: Semantic video segmentation by gated recurrent flow propagation. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00713"},{"issue":"8","key":"28_CR27","doi-asserted-by":"publisher","first-page":"2022","DOI":"10.1007\/s11263-022-01629-1","volume":"130","author":"J Qi","year":"2022","unstructured":"Qi, J., et al.: Occluded video instance segmentation: a benchmark. IJCV 130(8), 2022\u20132039 (2022)","journal-title":"IJCV"},{"key":"28_CR28","doi-asserted-by":"publisher","unstructured":"Qin, D., et al.: MobileNetV4: universal models for the mobile ecosystem. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds) Computer Vision \u2013 ECCV 2024. ECCV 2024. Lecture Notes in Computer Science, vol. 15098. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-73661-2_5","DOI":"10.1007\/978-3-031-73661-2_5"},{"key":"28_CR29","unstructured":"Ravi, N., et\u00a0al.: SAM 2: segment anything in images and videos. In: ICLR (2024)"},{"key":"28_CR30","unstructured":"Roh, B., Shin, J., Shin, W., Kim, S.: Sparse DETR: efficient end-to-end object detection with learnable sparsity. In: ICLR (2022)"},{"key":"28_CR31","doi-asserted-by":"crossref","unstructured":"Segu, M., Gazulla, M.T., Xian, Y., Van Gool, L., Tombari, F.: MOBIUS: Big-to-mobile universal instance segmentation via multi-modal bottleneck fusion and calibrated decoder pruning. In: ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.01927"},{"key":"28_CR32","doi-asserted-by":"crossref","unstructured":"Seo, S., Lee, J.Y., Han, B.: URVOS: unified referring video object segmentation network with a large-scale benchmark. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58555-6_13"},{"key":"28_CR33","doi-asserted-by":"crossref","unstructured":"Sevilla-Lara, L., Sun, D., Jampani, V., Black, M.J.: Optical flow with semantic segmentation and localized layers. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.422"},{"key":"28_CR34","doi-asserted-by":"crossref","unstructured":"Shao, S., et al.: Objects365: a large-scale, high-quality dataset for object detection. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00852"},{"key":"28_CR35","doi-asserted-by":"crossref","unstructured":"Teed, Z., Deng, J.: RAFT: recurrent all-pairs field transforms for optical flow. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"28_CR36","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: Towards open-vocabulary video instance segmentation. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00375"},{"key":"28_CR37","doi-asserted-by":"crossref","unstructured":"Wang, W., Feiszli, M., Wang, H., Tran, D.: Unidentified video objects: a benchmark for dense, open-world segmentation. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01060"},{"key":"28_CR38","doi-asserted-by":"crossref","unstructured":"Weng, Y., et al.: Mask propagation for efficient video semantic segmentation. In: NeurIPS (2023)","DOI":"10.52202\/075280-0314"},{"key":"28_CR39","doi-asserted-by":"crossref","unstructured":"Wu, J., Jiang, Y., Liu, Q., Yuan, Z., Bai, X., Bai, S.: General object foundation model for images and videos at scale. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00363"},{"key":"28_CR40","doi-asserted-by":"crossref","unstructured":"Wulff, J., Butler, D., Stanley, G., Black, M.J.: Lessons and insights from creating a synthetic optical flow benchmark. In: ECCV (2012)","DOI":"10.1007\/978-3-642-33868-7_17"},{"key":"28_CR41","doi-asserted-by":"crossref","unstructured":"Xiao, H., Feng, J., Lin, G., Liu, Y., Zhang, M.: MoNet: deep motion exploitation for video object segmentation. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00125"},{"key":"28_CR42","doi-asserted-by":"crossref","unstructured":"Xu, M., et al.: A simple baseline for open-vocabulary semantic segmentation with pre-trained vision-language model. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19818-2_42"},{"key":"28_CR43","doi-asserted-by":"crossref","unstructured":"Yan, B., et al.: Universal instance perception as object discovery and retrieval. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01471"},{"key":"28_CR44","doi-asserted-by":"crossref","unstructured":"Yan, B., Sundermeyer, M., Tan, D.J., Lu, H., Tombari, F.: Towards real-time open-vocabulary video instance segmentation. In: WACV (2025)","DOI":"10.1109\/WACV61041.2025.00188"},{"key":"28_CR45","doi-asserted-by":"crossref","unstructured":"Yang, L., Fan, Y., Xu, N.: Video instance segmentation. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00529"},{"key":"28_CR46","unstructured":"Yao, Z., Ai, J., Li, B., Zhang, C.: Efficient DETR: improving end-to-end object detector with dense prior. arXiv:2104.01318 [cs.CV] (2021)"},{"key":"28_CR47","doi-asserted-by":"crossref","unstructured":"Yu, F., et al.: BDD100K: a diverse driving dataset for heterogeneous multitask learning. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"28_CR48","doi-asserted-by":"crossref","unstructured":"Zang, Y., Li, W., Zhou, K., Huang, C., Loy, C.C.: Open-vocabulary DETR with conditional matching. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20077-9_7"},{"key":"28_CR49","unstructured":"Zhang, C., Han, D., Zheng, S., Choi, J., Kim, T., Hong, C.S.: MobileSAMv2: faster segment anything to everything. arXiv:2312.09579 [cs.CV] (2023)"},{"key":"28_CR50","doi-asserted-by":"crossref","unstructured":"Zhang, H., Li, F., Zou, X., Liu, S., Li, C., Yang, J., Zhang, L.: A simple framework for open-vocabulary segmentation and detection. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00100"},{"key":"28_CR51","doi-asserted-by":"crossref","unstructured":"Zhang, R., et al.: MobileInst: video instance segmentation on the mobile. In: AAAI (2024)","DOI":"10.1609\/aaai.v38i7.28555"},{"key":"28_CR52","unstructured":"Zhao, X., et al.: Fast segment anything. arXiv:2306.12156 [cs.CV] (2023)"},{"key":"28_CR53","doi-asserted-by":"crossref","unstructured":"Zhao, Y., et al.: DETRs beat YOLOs on real-time object detection. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"28_CR54","doi-asserted-by":"crossref","unstructured":"Zheng, D., Dong, W., Hu, H., Chen, X., Wang, Y.: Less is more: focus attention for efficient DETR. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00614"},{"key":"28_CR55","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. In: ICLR (2021)"},{"key":"28_CR56","doi-asserted-by":"crossref","unstructured":"Zou, X., et\u00a0al.: Generalized decoding for pixel, image, and language. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01451"},{"key":"28_CR57","doi-asserted-by":"crossref","unstructured":"Zou, X., et al.: Segment everything everywhere all at once. In: NeurIPS (2023)","DOI":"10.52202\/075280-0868"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37324-3_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T07:18:56Z","timestamp":1789456736000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37324-3_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373236","9783032373243"],"references-count":57,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37324-3_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"16 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","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":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}