{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T11:34:56Z","timestamp":1743075296457,"version":"3.40.3"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031198175"},{"type":"electronic","value":"9783031198182"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-19818-2_38","type":"book-chapter","created":{"date-parts":[[2022,10,21]],"date-time":"2022-10-21T16:21:10Z","timestamp":1666369270000},"page":"666-681","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Video Instance Segmentation via\u00a0Multi-Scale Spatio-Temporal Split Attention Transformer"],"prefix":"10.1007","author":[{"given":"Omkar","family":"Thawakar","sequence":"first","affiliation":[]},{"given":"Sanath","family":"Narayan","sequence":"additional","affiliation":[]},{"given":"Jiale","family":"Cao","sequence":"additional","affiliation":[]},{"given":"Hisham","family":"Cholakkal","sequence":"additional","affiliation":[]},{"given":"Rao Muhammad","family":"Anwer","sequence":"additional","affiliation":[]},{"given":"Muhammad Haris","family":"Khan","sequence":"additional","affiliation":[]},{"given":"Salman","family":"Khan","sequence":"additional","affiliation":[]},{"given":"Michael","family":"Felsberg","sequence":"additional","affiliation":[]},{"given":"Fahad Shahbaz","family":"Khan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,10,22]]},"reference":[{"key":"38_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1007\/978-3-030-58621-8_10","volume-title":"Computer Vision \u2013 ECCV 2020","author":"A Athar","year":"2020","unstructured":"Athar, A., Mahadevan, S., Os\u0306ep, A., Leal-Taix\u00e9, L., Leibe, B.: STEm-Seg: spatio-temporal embeddings for instance segmentation in videos. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 158\u2013177. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58621-8_10"},{"key":"38_CR2","doi-asserted-by":"crossref","unstructured":"Bertasius, G., Torresani, L.: Classifying, segmenting, and tracking object instances in video with mask propagation. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00976"},{"key":"38_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-030-58568-6_1","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Cao","year":"2020","unstructured":"Cao, J., Anwer, R.M., Cholakkal, H., Khan, F.S., Pang, Y., Shao, L.: SipMask: spatial information preservation for fast image and video instance segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 1\u201318. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_1"},{"key":"38_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"38_CR5","doi-asserted-by":"crossref","unstructured":"Fu, Y., Yang, L., Liu, D., Huang, T.S., Shi, H.: CompFeat: comprehensive feature aggregation for video instance segmentation. In: AAAI (2021)","DOI":"10.1609\/aaai.v35i2.16225"},{"key":"38_CR6","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"38_CR7","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":"38_CR8","unstructured":"Hwang, S., Heo, M., Oh, S.W., Kim, S.J.: Video instance segmentation using inter-frame communication transformers. In: NeurIPS (2021)"},{"key":"38_CR9","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"38_CR10","doi-asserted-by":"crossref","unstructured":"Johnander, J., Brissman, E., Danelljan, M., Felsberg, M.: Learning video instance segmentation with recurrent graph neural networks. In: GCPI (2021)","DOI":"10.1007\/978-3-030-92659-5_13"},{"key":"38_CR11","unstructured":"Ke, L., Li, X., Danelljan, M., Tai, Y.W., Tang, C.K., Yu, F.: Prototypical cross-attention networks for multiple object tracking and segmentation. In: NeurIPS (2021)"},{"key":"38_CR12","unstructured":"Kristan, M., et al.: The visual object tracking vot2015 challenge results. In: ICCV workshops (2015)"},{"key":"38_CR13","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":"38_CR14","doi-asserted-by":"crossref","unstructured":"Lin, C., Hung, Y., Feris, R., He, L.: Video instance segmentation tracking with a modified VAE architecture. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01316"},{"key":"38_CR15","doi-asserted-by":"crossref","unstructured":"Lin, H., Wu, R., Liu, S., Lu, J., Jia, J.: Video instance segmentation with a propose-reduce paradigm. In: arXiv preprint arXiv:2103.13746 (2021)","DOI":"10.1109\/ICCV48922.2021.00176"},{"key":"38_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"38_CR17","doi-asserted-by":"crossref","unstructured":"Liu, D., Cui, Y., Tan, W., Chen, Y.: SG-Net: spatial granularity network for one-stage video instance segmentation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00969"},{"key":"38_CR18","unstructured":"Paszke, A., et al.: An imperative style, high-performance deep learning library. In: NeurIPS (2019). https:\/\/papers.neurips.cc\/paper\/9015-pytorch-an-imperative-style-high-performance-deep-learning-library.pdf"},{"key":"38_CR19","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., He, T.: FCOS: fully convolutional one-stage object detection. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00972"},{"key":"38_CR20","unstructured":"Vaswani, A., et al.: Pattention is all you need. In: NeurIPS (2017)"},{"key":"38_CR21","doi-asserted-by":"crossref","unstructured":"Voigtlaender, P., Chai, Y., Schroff, F., Adam, H., Leibe, B., Chen, L.: FEELVOS: fast end-to-end embedding learning for video object segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00971"},{"key":"38_CR22","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: End-to-end video instance segmentation with transformers. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"38_CR23","doi-asserted-by":"crossref","unstructured":"Wojke, N., Bewley, A., Paulus, D.: Simple online and realtime tracking with a deep association metric. In: ICIP (2017)","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"38_CR24","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: arXiv preprint arXiv:2112.08275 (2021)","DOI":"10.1007\/978-3-031-19815-1_32"},{"key":"38_CR25","unstructured":"Xu, N., et al.: Youtube-vis dataset 2021 version. https:\/\/youtube-vos.org\/dataset\/vis (2021)"},{"key":"38_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":"38_CR27","doi-asserted-by":"crossref","unstructured":"Yang, L., Wang, Y., Xiong, X., Yang, J., Katsaggelos, A.K.: Efficient video object segmentation via network modulation. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00680"},{"key":"38_CR28","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":"38_CR29","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","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19818-2_38","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T14:39:52Z","timestamp":1710340792000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19818-2_38"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198175","9783031198182"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19818-2_38","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"22 October 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}