{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T17:22:45Z","timestamp":1771953765668,"version":"3.50.1"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031784439","type":"print"},{"value":"9783031784446","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"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\/978-3-031-78444-6_18","type":"book-chapter","created":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T10:43:04Z","timestamp":1733222584000},"page":"268-282","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["GRAtt-VIS: Gated Residual Attention for\u00a0Video Instance Segmentation"],"prefix":"10.1007","author":[{"given":"Tanveer","family":"Hannan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rajat","family":"Koner","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maximilian","family":"Bernhard","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Suprosanna","family":"Shit","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bjoern","family":"Menze","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Volker","family":"Tresp","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthias","family":"Schubert","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Seidl","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,4]]},"reference":[{"key":"18_CR1","doi-asserted-by":"crossref","unstructured":"Bertasius, G., et\u00a0al.: Classifying, segmenting, and tracking object instances in video with mask propagation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9739\u20139748 (2020)","DOI":"10.1109\/CVPR42600.2020.00976"},{"key":"18_CR2","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":"18_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":"18_CR4","doi-asserted-by":"crossref","unstructured":"Han, S.H., et al.: Visolo: grid-based space-time aggregation for efficient online video instance segmentation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00291"},{"key":"18_CR5","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"},{"key":"18_CR6","unstructured":"Heo, M., et al.: A generalized framework for video instance segmentation. arXiv preprint arXiv:2211.08834 (2022)"},{"key":"18_CR7","unstructured":"Heo, M., Hwang, S., Oh, S.W., Lee, J.Y., Kim, S.J.: Vita: video instance segmentation via object token association. In: NeurIPS (2022)"},{"key":"18_CR8","unstructured":"Huang, D.A., Yu, Z., Anandkumar, A.: Minvis: a minimal video instance segmentation framework without video-based training. In: NeurIPS (2022)"},{"key":"18_CR9","unstructured":"Hwang, S., Heo, M., Oh, S.W., Kim, S.J.: Video instance segmentation using inter-frame communication transformers. In: NeurIPS (2021)"},{"key":"18_CR10","unstructured":"Jang, E., Gu, S., Poole, B.: Categorical reparameterization with gumbel-softmax. arXiv preprint arXiv:1611.01144 (2016)"},{"key":"18_CR11","unstructured":"Koner, R., et al.: Instanceformer: an online video instance segmentation framework. arXiv preprint arXiv:2208.10547 (2022)"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Li, M., Li, S., Li, L., Zhang, L.: Spatial feature calibration and temporal fusion for effective one-stage video instance segmentation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01106"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Lin, H., Wu, R., Liu, S., Lu, J., Jia, J.: Video instance segmentation with a propose-reduce paradigm. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1739\u20131748 (2021)","DOI":"10.1109\/ICCV48922.2021.00176"},{"key":"18_CR14","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2019)"},{"key":"18_CR15","unstructured":"Maddison, C.J., Mnih, A., Teh, Y.W.: The concrete distribution: a continuous relaxation of discrete random variables. CoRR abs\/1611.00712 (2016). http:\/\/arxiv.org\/abs\/1611.00712"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Meinhardt, T., Kirillov, A., Leal-Taixe, L., Feichtenhofer, C.: Trackformer: multi-object tracking with transformers. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"18_CR17","unstructured":"Qi, J., et al.: Occluded video instance segmentation. arXiv preprint arXiv:2102.01558 (2021)"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Thawakar, O., et al.: Video instance segmentation via multi-scale spatio-temporal split attention transformer (2022)","DOI":"10.1007\/978-3-031-19818-2_38"},{"key":"18_CR19","unstructured":"Voigtlaender, P., et al.: MOTS: multi-object tracking and segmentation. CoRR abs\/1902.03604 (2019). http:\/\/arxiv.org\/abs\/1902.03604"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: End-to-end video instance segmentation with transformers. In: CVPR (2020)","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Wu, J., et al.: Efficient video instance segmentation via tracklet query and proposal. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00103"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Wu, J., Jiang, Y., Zhang, W., Bai, X., Bai, S.: Seqformer: a frustratingly simple model for video instance segmentation. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19815-1_32"},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Wu, J., Liu, Q., Jiang, Y., Bai, S., Yuille, A., Bai, X.: In defense of online models for video instance segmentation. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19815-1_34"},{"key":"18_CR24","unstructured":"Xu, N., et al.: Youtube-vis dataset 2021 version (2021). https:\/\/youtube-vos.org\/dataset\/vi. Accessed 01 Jan 2022"},{"key":"18_CR25","unstructured":"Xu, N., et al.: The 4th large-scale video object segmentation challenge - youtube-vos (2022). https:\/\/youtube-vos.org\/challenge\/2022\/. Accessed 18 Aug 2022"},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"Yang, L., Fan, Y., Xu, N.: Video instance segmentation. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00529"},{"key":"18_CR27","doi-asserted-by":"crossref","unstructured":"Yang, S., et al.: Crossover learning for fast online video instance segmentation. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00794"},{"key":"18_CR28","unstructured":"Yang, S., et al.: Tracking instances as queries. arXiv preprint arXiv:2106.11963 (2021)"},{"key":"18_CR29","doi-asserted-by":"crossref","unstructured":"Yang, S., et al.: Temporally efficient vision transformer for video instance segmentation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00290"},{"key":"18_CR30","unstructured":"Zhan, Z., McKee, D., Lazebnik, S.: Robust online video instance segmentation with track queries. arXiv preprint arXiv:2211.09108 (2022)"},{"key":"18_CR31","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)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78444-6_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T11:36:21Z","timestamp":1733225781000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78444-6_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,4]]},"ISBN":["9783031784439","9783031784446"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78444-6_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,4]]},"assertion":[{"value":"4 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}