{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:48:54Z","timestamp":1777654134666,"version":"3.51.4"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198144","type":"print"},{"value":"9783031198151","type":"electronic"}],"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\/978-3-031-19815-1_42","type":"book-chapter","created":{"date-parts":[[2022,10,19]],"date-time":"2022-10-19T23:11:54Z","timestamp":1666221114000},"page":"731-747","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Video Mask Transfiner for\u00a0High-Quality Video Instance Segmentation"],"prefix":"10.1007","author":[{"given":"Lei","family":"Ke","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Henghui","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martin","family":"Danelljan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-Wing","family":"Tai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chi-Keung","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fisher","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,20]]},"reference":[{"key":"42_CR1","doi-asserted-by":"crossref","unstructured":"Alldieck, T., Magnor, M., Xu, W., Theobalt, C., Pons-Moll, G.: Video based reconstruction of 3D people models. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00875"},{"key":"42_CR2","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":"42_CR3","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":"42_CR4","doi-asserted-by":"crossref","unstructured":"Bolya, D., Zhou, C., Xiao, F., Lee, Y.J.: Yolact: real-time instance segmentation. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00925"},{"key":"42_CR5","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":"42_CR6","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":"42_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"695","DOI":"10.1007\/978-3-030-58545-7_40","volume-title":"Computer Vision \u2013 ECCV 2020","author":"L-C Chen","year":"2020","unstructured":"Chen, L.-C., et al.: Naive-Student: leveraging semi-supervised learning in video sequences for urban scene segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 695\u2013714. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58545-7_40"},{"key":"42_CR8","doi-asserted-by":"crossref","unstructured":"Cheng, B., Girshick, R., Doll\u00e1r, P., Berg, A.C., Kirillov, A.: Boundary iou: improving object-centric image segmentation evaluation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01508"},{"key":"42_CR9","doi-asserted-by":"crossref","unstructured":"Cheng, H.K., Chung, J., Tai, Y.W., Tang, C.K.: Cascadepsp: toward class-agnostic and very high-resolution segmentation via global and local refinement. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00891"},{"key":"42_CR10","doi-asserted-by":"crossref","unstructured":"Ding, H., Jiang, X., Liu, A.Q., Thalmann, N.M., Wang, G.: Boundary-aware feature propagation for scene segmentation. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00692"},{"key":"42_CR11","doi-asserted-by":"crossref","unstructured":"Fang, Y., et al.: Instances as queries. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00683"},{"key":"42_CR12","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":"42_CR13","doi-asserted-by":"crossref","unstructured":"Huang, Z., Huang, L., Gong, Y., Huang, C., Wang, X.: Mask scoring r-cnn. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00657"},{"key":"42_CR14","unstructured":"Hwang, S., Heo, M., Oh, S.W., Kim, S.J.: Video instance segmentation using inter-frame communication transformers. In: NeurIPS (2021)"},{"key":"42_CR15","doi-asserted-by":"crossref","unstructured":"Ke, L., Danelljan, M., Li, X., Tai, Y.W., Tang, C.K., Yu, F.: Mask transfiner for high-quality instance segmentation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00437"},{"key":"42_CR16","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":"42_CR17","doi-asserted-by":"crossref","unstructured":"Ke, L., Tai, Y.W., Tang, C.K.: Deep occlusion-aware instance segmentation with overlapping bilayers. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00401"},{"key":"42_CR18","doi-asserted-by":"crossref","unstructured":"Ke, L., Tai, Y.W., Tang, C.K.: Occlusion-aware video object inpainting. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01420"},{"key":"42_CR19","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Wu, Y., He, K., Girshick, R.: Pointrend: image segmentation as rendering. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00982"},{"key":"42_CR20","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":"42_CR21","doi-asserted-by":"crossref","unstructured":"Lin, C.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":"42_CR22","doi-asserted-by":"crossref","unstructured":"Lin, H., Wu, R., Liu, S., Lu, J., Jia, J.: Video instance segmentation with a propose-reduce paradigm. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00176"},{"key":"42_CR23","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":"42_CR24","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2019)"},{"key":"42_CR25","doi-asserted-by":"crossref","unstructured":"Meinhardt, T., Kirillov, A., Leal-Taixe, L., Feichtenhofer, C.: Trackformer: multi-object tracking with transformers. arXiv preprint arXiv:2101.02702 (2021)","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"42_CR26","doi-asserted-by":"crossref","unstructured":"Milan, A., Leal-Taix\u00e9, L., Schindler, K., Reid, I.: Joint tracking and segmentation of multiple targets. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299178"},{"key":"42_CR27","doi-asserted-by":"crossref","unstructured":"Pang, J., et al.: Quasi-dense similarity learning for multiple object tracking. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00023"},{"key":"42_CR28","unstructured":"Qi, J., et al.: Occluded video instance segmentation. arXiv preprint arXiv:2102.01558 (2021)"},{"key":"42_CR29","doi-asserted-by":"crossref","unstructured":"Takikawa, T., Acuna, D., Jampani, V., Fidler, S.: Gated-scnn: gated shape cnns for semantic segmentation. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00533"},{"key":"42_CR30","doi-asserted-by":"crossref","unstructured":"Tang, C., Chen, H., Li, X., Li, J., Zhang, Z., Hu, X.: Look closer to segment better: Boundary patch refinement for instance segmentation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01371"},{"key":"42_CR31","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":"42_CR32","doi-asserted-by":"crossref","unstructured":"Voigtlaender, P., Chai, Y., Schroff, F., Adam, H., Leibe, B., Chen, L.C.: Feelvos: fast end-to-end embedding learning for video object segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00971"},{"key":"42_CR33","doi-asserted-by":"crossref","unstructured":"Voigtlaender, P., et al.: Mots: multi-object tracking and segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00813"},{"key":"42_CR34","doi-asserted-by":"publisher","first-page":"3349","DOI":"10.1109\/TPAMI.2020.2983686","volume":"43","author":"J Wang","year":"2020","unstructured":"Wang, J., et al.: Deep high-resolution representation learning for visual recognition. TPAMI 43, 3349\u20133364 (2020)","journal-title":"TPAMI"},{"key":"42_CR35","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":"42_CR36","doi-asserted-by":"crossref","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 (2021)","DOI":"10.1007\/978-3-031-19815-1_32"},{"key":"42_CR37","doi-asserted-by":"crossref","unstructured":"Yang, L., Fan, Y., Xu, N.: Video instance segmentation. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00529"},{"key":"42_CR38","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":"42_CR39","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":"42_CR40","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1007\/978-3-030-58610-2_29","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Yuan","year":"2020","unstructured":"Yuan, Y., Xie, J., Chen, X., Wang, J.: SegFix: model-agnostic boundary refinement for segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12357, pp. 489\u2013506. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58610-2_29"},{"key":"42_CR41","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable detr: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"},{"key":"42_CR42","unstructured":"Zhu, Y., et al.: Improving semantic segmentation via self-training. arXiv preprint arXiv:2004.14960 (2020)"},{"key":"42_CR43","unstructured":"Zou, Y., et al.: Pseudoseg: designing pseudo labels for semantic segmentation. In: International Conference on Learning Representations (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\/978-3-031-19815-1_42","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,21]],"date-time":"2022-10-21T23:31:49Z","timestamp":1666395109000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19815-1_42"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198144","9783031198151"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19815-1_42","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"20 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)"}}]}}