{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T16:56:20Z","timestamp":1783184180482,"version":"3.54.6"},"publisher-location":"Cham","reference-count":58,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726323","type":"print"},{"value":"9783031726330","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-72633-0_6","type":"book-chapter","created":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T07:55:51Z","timestamp":1732175751000},"page":"98-115","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":39,"title":["VISA: Reasoning Video Object Segmentation via\u00a0Large Language Models"],"prefix":"10.1007","author":[{"given":"Cilin","family":"Yan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haochen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shilin","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaolong","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yao","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guoliang","family":"Kang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weidi","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Efstratios","family":"Gavves","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,22]]},"reference":[{"key":"6_CR1","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. In: Advances in Neural Information Processing Systems, vol. 35, pp. 23716\u201323736 (2022)"},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Botach, A., Zheltonozhskii, E., Baskin, C.: End-to-end referring video object segmentation with multimodal transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4985\u20134995 (2022)","DOI":"10.1109\/CVPR52688.2022.00493"},{"key":"6_CR3","unstructured":"Cheng, B., Choudhuri, A., Misra, I., Kirillov, A., Girdhar, R., Schwing, A.G.: Mask2former for video instance segmentation. arXiv preprint arXiv:2112.10764 (2021)"},{"key":"6_CR4","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"640","DOI":"10.1007\/978-3-031-19815-1_37","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: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13688, pp. 640\u2013658. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_37"},{"key":"6_CR5","unstructured":"Cheng, H.K., Tai, Y.W., Tang, C.K.: Rethinking space-time networks with improved memory coverage for efficient video object segmentation. In: Advances in Neural Information Processing Systems, vol. 34, pp. 11781\u201311794 (2021)"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Cheng, J., Tsai, Y.H., Hung, W.C., Wang, S., Yang, M.H.: Fast and accurate online video object segmentation via tracking parts. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7415\u20137424 (2018)","DOI":"10.1109\/CVPR.2018.00774"},{"key":"6_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1007\/978-3-030-58558-7_26","volume-title":"Computer Vision \u2013 ECCV 2020","author":"A Dave","year":"2020","unstructured":"Dave, A., Khurana, T., Tokmakov, P., Schmid, C., Ramanan, D.: TAO: a large-scale benchmark for tracking any object. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12350, pp. 436\u2013454. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58558-7_26"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Ding, H., Liu, C., He, S., Jiang, X., Loy, C.C.: MeViS: a large-scale benchmark for video segmentation with motion expressions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2694\u20132703 (2023)","DOI":"10.1109\/ICCV51070.2023.00254"},{"key":"6_CR9","doi-asserted-by":"crossref","unstructured":"Ding, H., Liu, C., He, S., Jiang, X., Torr, P.H., Bai, S.: Mose: a new dataset for video object segmentation in complex scenes. arXiv preprint arXiv:2302.01872 (2023)","DOI":"10.1109\/ICCV51070.2023.01850"},{"key":"6_CR10","doi-asserted-by":"crossref","unstructured":"Ding, H., Liu, C., Wang, S., Jiang, X.: Vision-language transformer and query generation for referring segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 16321\u201316330 (2021)","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Ding, Z., Hui, T., Huang, J., Wei, X., Han, J., Liu, S.: Language-bridged spatial-temporal interaction for referring video object segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4964\u20134973 (2022)","DOI":"10.1109\/CVPR52688.2022.00491"},{"key":"6_CR12","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth $$16 \\times 16$$ words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Jin, P., Takanobu, R., Zhang, C., Cao, X., Yuan, L.: Chat-UniVi: unified visual representation empowers large language models with image and video understanding. arXiv preprint arXiv:2311.08046 (2023)","DOI":"10.1109\/CVPR52733.2024.01300"},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"Kazemzadeh, S., Ordonez, V., Matten, M., Berg, T.: ReferitGame: referring to objects in photographs of natural scenes. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 787\u2013798 (2014)","DOI":"10.3115\/v1\/D14-1086"},{"key":"6_CR15","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. arXiv preprint arXiv:2304.02643 (2023)"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Lai, X., et al.: Lisa: reasoning segmentation via large language model. arXiv preprint arXiv:2308.00692 (2023)","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"6_CR17","unstructured":"Li, B., Zhang, Y., Chen, L., Wang, J., Yang, J., Liu, Z.: Otter: a multi-modal model with in-context instruction tuning. arXiv preprint arXiv:2305.03726 (2023)"},{"key":"6_CR18","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)"},{"key":"6_CR19","unstructured":"Li, X., Wang, J., Xu, X., Li, X., Lu, Y., Raj, B.: R 2vos: robust referring video object segmentation via relational multimodal cycle consistency. arXiv preprint arXiv:2207.01203 (2022)"},{"key":"6_CR20","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, C., Jia, J.: Llama-vid: an image is worth 2 tokens in large language models. arXiv preprint arXiv:2311.17043 (2023)","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"6_CR21","doi-asserted-by":"publisher","unstructured":"Li, Z., Tao, R., Gavves, E., Snoek, C.G.M., Smeulders, A.W.M.: Tracking by natural language specification. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7350\u20137358 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.777","DOI":"10.1109\/CVPR.2017.777"},{"key":"6_CR22","doi-asserted-by":"crossref","unstructured":"Liu, C., Ding, H., Jiang, X.: GRES: generalized referring expression segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23592\u201323601 (2023)","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"6_CR23","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"6_CR24","doi-asserted-by":"crossref","unstructured":"Luo, G., et al.: Multi-task collaborative network for joint referring expression comprehension and segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10034\u201310043 (2020)","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"6_CR25","doi-asserted-by":"crossref","unstructured":"Maaz, M., Rasheed, H., Khan, S., Khan, F.S.: Video-chatGPT: towards detailed video understanding via large vision and language models. arXiv preprint arXiv:2306.05424 (2023)","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"6_CR26","doi-asserted-by":"crossref","unstructured":"Mao, J., Huang, J., Toshev, A., Camburu, O., Yuille, A.L., Murphy, K.: Generation and comprehension of unambiguous object descriptions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 11\u201320 (2016)","DOI":"10.1109\/CVPR.2016.9"},{"key":"6_CR27","doi-asserted-by":"crossref","unstructured":"Milletari, F., Navab, N., Ahmadi, S.A.: V-net: fully convolutional neural networks for volumetric medical image segmentation. In: 2016 Fourth International Conference on 3D Vision, pp. 565\u2013571. IEEE (2016)","DOI":"10.1109\/3DV.2016.79"},{"key":"6_CR28","doi-asserted-by":"crossref","unstructured":"Oh, S.W., Lee, J.Y., Xu, N., Kim, S.J.: Video object segmentation using space-time memory networks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9226\u20139235 (2019)","DOI":"10.1109\/ICCV.2019.00932"},{"key":"6_CR29","unstructured":"Peng, Z., et al.: KOSMOS-2: grounding multimodal large language models to the world. arXiv preprint arXiv:2306.14824 (2023)"},{"key":"6_CR30","doi-asserted-by":"crossref","unstructured":"Perazzi, F., Khoreva, A., Benenson, R., Schiele, B., Sorkine-Hornung, A.: Learning video object segmentation from static images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2663\u20132672 (2017)","DOI":"10.1109\/CVPR.2017.372"},{"key":"6_CR31","doi-asserted-by":"crossref","unstructured":"Pi, R., et al.: DetGPT: detect what you need via reasoning. arXiv preprint arXiv:2305.14167 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.876"},{"key":"6_CR32","unstructured":"Pont-Tuset, J., et al.: The 2017 DAVIS challenge on video object segmentation. arXiv preprint arXiv:1704.00675 (2017)"},{"key":"6_CR33","unstructured":"Qi, J., et al.: Occluded video instance segmentation: dataset and ICCV 2021 challenge. arXiv preprint arXiv:2111.07950 (2021)"},{"key":"6_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1007\/978-3-030-58555-6_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Seo","year":"2020","unstructured":"Seo, S., Lee, J.-Y., Han, B.: URVOS: unified referring video object segmentation network with a large-scale benchmark. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12360, pp. 208\u2013223. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58555-6_13"},{"key":"6_CR35","unstructured":"Stroh, N.: TrackGPT\u2013a generative pre-trained transformer for cross-domain entity trajectory forecasting. arXiv preprint arXiv:2402.00066 (2024)"},{"key":"6_CR36","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: OV-VIS: open-vocabulary video instance segmentation. Int. J. Comput. Vis. 1\u201318 (2024)","DOI":"10.1109\/TCSVT.2024.3474698"},{"key":"6_CR37","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: Towards open-vocabulary video instance segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4057\u20134066 (2023)","DOI":"10.1109\/ICCV51070.2023.00375"},{"key":"6_CR38","unstructured":"Wang, W., et\u00a0al.: CogVLM: visual expert for pretrained language models. arXiv preprint arXiv:2311.03079 (2023)"},{"key":"6_CR39","doi-asserted-by":"crossref","unstructured":"Wang, W., Feiszli, M., Wang, H., Tran, D.: Unidentified video objects: a benchmark for dense, open-world segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10776\u201310785 (2021)","DOI":"10.1109\/ICCV48922.2021.01060"},{"key":"6_CR40","unstructured":"Wang, W., et\u00a0al.: VisionLLM: large language model is also an open-ended decoder for vision-centric tasks. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"6_CR41","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: End-to-end video instance segmentation with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8741\u20138750 (2021)","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"6_CR42","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: CRIS: clip-driven referring image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11686\u201311695 (2022)","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"6_CR43","doi-asserted-by":"crossref","unstructured":"Wu, D., Wang, T., Zhang, Y., Zhang, X., Shen, J.: OnlineRefer: a simple online baseline for referring video object segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2761\u20132770 (2023)","DOI":"10.1109\/ICCV51070.2023.00259"},{"key":"6_CR44","doi-asserted-by":"crossref","unstructured":"Wu, J., Jiang, Y., Sun, P., Yuan, Z., Luo, P.: Language as queries for referring video object segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4974\u20134984 (2022)","DOI":"10.1109\/CVPR52688.2022.00492"},{"key":"6_CR45","unstructured":"Wu, J., Jiang, Y., Zhang, W., Bai, X., Bai, S.: SeqFormer: a frustratingly simple model for video instance segmentation. arXiv preprint arXiv:2112.08275, 1(2), 6 (2021)"},{"key":"6_CR46","doi-asserted-by":"crossref","unstructured":"Yang, Z., Wang, J., Tang, Y., Chen, K., Zhao, H., Torr, P.H.: LAVT: language-aware vision transformer for referring image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18155\u201318165 (2022)","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"6_CR47","unstructured":"Yang, Z., Wei, Y., Yang, Y.: Associating objects with transformers for video object segmentation. In: Advances in Neural Information Processing Systems, vol. 34, pp. 2491\u20132502 (2021)"},{"key":"6_CR48","unstructured":"Ye, Q., et\u00a0al.: mPLUG-Owl: modularization empowers large language models with multimodality. arXiv preprint arXiv:2304.14178 (2023)"},{"key":"6_CR49","doi-asserted-by":"crossref","unstructured":"Zhang, H., Li, X., Bing, L.: Video-llama: an instruction-tuned audio-visual language model for video understanding. arXiv preprint arXiv:2306.02858 (2023)","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"6_CR50","unstructured":"Zhang, S., et al.: GPT4RoI: instruction tuning large language model on region-of-interest. arXiv preprint arXiv:2307.03601 (2023)"},{"key":"6_CR51","unstructured":"Zhang, T., et al.: OMG-LLaVA: bridging image-level, object-level, pixel-level reasoning and understanding. arXiv preprint arXiv:2406.19389 (2024)"},{"key":"6_CR52","doi-asserted-by":"crossref","unstructured":"Zhang, T., et al.: DVIS: decoupled video instance segmentation framework. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1282\u20131291 (2023)","DOI":"10.1109\/ICCV51070.2023.00124"},{"key":"6_CR53","unstructured":"Zhang, T., et al.: DVIS++: improved decoupled framework for universal video segmentation. arXiv preprint arXiv:2312.13305 (2023)"},{"key":"6_CR54","unstructured":"Zhang, T., et al.: 1st place solution for the 5th LSVOS challenge: video instance segmentation. arXiv preprint arXiv:2308.14392 (2023)"},{"key":"6_CR55","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Zhang, T., Ji, S., Yan, S., Li, X.: DVIS-DAQ: improving video segmentation via dynamic anchor queries. arXiv preprint arXiv:2404.00086 (2024)","DOI":"10.1007\/978-3-031-72973-7_26"},{"key":"6_CR56","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: MiniGPT-4: enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)"},{"key":"6_CR57","doi-asserted-by":"crossref","unstructured":"Zou, X., et\u00a0al.: Generalized decoding for pixel, image, and language. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15116\u201315127 (2023)","DOI":"10.1109\/CVPR52729.2023.01451"},{"key":"6_CR58","unstructured":"Zou, X., et al.: Segment everything everywhere all at once. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72633-0_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T08:09:09Z","timestamp":1732176549000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72633-0_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,22]]},"ISBN":["9783031726323","9783031726330"],"references-count":58,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72633-0_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,22]]},"assertion":[{"value":"22 November 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}