{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T20:57:05Z","timestamp":1742936225485,"version":"3.40.3"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031442360"},{"type":"electronic","value":"9783031442377"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-44237-7_25","type":"book-chapter","created":{"date-parts":[[2023,9,19]],"date-time":"2023-09-19T22:01:45Z","timestamp":1695160905000},"page":"262-272","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Fast Video Instance Segmentation via\u00a0Recurrent Encoder-Based Transformers"],"prefix":"10.1007","author":[{"given":"Omkar","family":"Thawakar","sequence":"first","affiliation":[]},{"given":"Alexandre","family":"Rivkind","sequence":"additional","affiliation":[]},{"given":"Ehud","family":"Ahissar","sequence":"additional","affiliation":[]},{"given":"Fahad Shahbaz","family":"Khan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,9,20]]},"reference":[{"key":"25_CR1","doi-asserted-by":"crossref","unstructured":"Athar, A., Mahadevan, S., Osep, A., Leal-Taix\u00e9, L., Leibe, B.: Stem-seg: spatio-temporal embeddings for instance segmentation in videos. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58621-8_10"},{"key":"25_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":"25_CR3","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":"25_CR4","doi-asserted-by":"crossref","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: ECCV (2020)","DOI":"10.1007\/978-3-030-58568-6_1"},{"key":"25_CR5","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":"25_CR6","unstructured":"Chen, G., Choi, W., Yu, X., Han, T., Chandraker, M.: Learning efficient object detection models with knowledge distillation. In: NeurIPS, vol. 30 (2017)"},{"key":"25_CR7","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"25_CR8","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":"25_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.B.: Mask r-cnn. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"25_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"},{"key":"25_CR11","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":"25_CR12","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. In: arXiv preprint arXiv:1503.02531 (2015)"},{"key":"25_CR13","first-page":"13352","volume":"34","author":"S Hwang","year":"2021","unstructured":"Hwang, S., Heo, M., Oh, S.W., Kim, S.J.: Video instance segmentation using inter-frame communication transformers. NeurIPS 34, 13352\u201313363 (2021)","journal-title":"NeurIPS"},{"key":"25_CR14","unstructured":"Kang, Z., Zhang, P., Zhang, X., Sun, J., Zheng, N.: Instance-conditional knowledge distillation for object detection. In: NeurIPS, vol. 34, pp. 16468\u201316480 (2021)"},{"key":"25_CR15","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":"25_CR16","unstructured":"Koner, R., et al.: Instanceformer: an online video instance segmentation framework. In: ECCV (2022)"},{"key":"25_CR17","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":"25_CR18","doi-asserted-by":"crossref","unstructured":"Lin, T., et al.: Microsoft coco: Common objects in context. In: ECCV (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"25_CR19","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":"25_CR20","doi-asserted-by":"crossref","unstructured":"Liu, Y., Chen, K., Liu, C., Qin, Z., Luo, Z., Wang, J.: Structured knowledge distillation for semantic segmentation. In: CVPR, pp. 2604\u20132613 (2019)","DOI":"10.1109\/CVPR.2019.00271"},{"key":"25_CR21","doi-asserted-by":"crossref","unstructured":"Papernot, N., McDaniel, P., Wu, X., Jha, S., Swami, A.: Distillation as a defense to adversarial perturbations against deep neural networks. In: 2016 IEEE Symposium on Security and Privacy (SP), pp. 582\u2013597. IEEE (2016)","DOI":"10.1109\/SP.2016.41"},{"key":"25_CR22","unstructured":"Rivkind, A., Ram, O., Assa, E., Kreiserman, M., Ahissar, E.: Visual hyperacuity with moving sensor and recurrent neural computations. In: ICLR (2021)"},{"key":"25_CR23","unstructured":"Romero, A., Ballas, N., Kahou, S.E., Chassang, A., Gatta, C., Bengio, Y.: Fitnets: hints for thin deep nets. In: arXiv preprint arXiv:1412.6550 (2014)"},{"key":"25_CR24","doi-asserted-by":"crossref","unstructured":"Thawakar, O., et al.: Video instance segmentation via multi-scale spatio-temporal split attention transformer. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19818-2_38"},{"key":"25_CR25","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":"25_CR26","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":"25_CR27","doi-asserted-by":"publisher","unstructured":"Wu, J., Jiang, Y., Bai, S., Zhang, W., Bai, X.: Seqformer: sequential transformer for video instance segmentation. In: ECCV, pp. 553\u2013569. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_32","DOI":"10.1007\/978-3-031-19815-1_32"},{"key":"25_CR28","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":"25_CR29","doi-asserted-by":"crossref","unstructured":"Yang, C., Zhou, H., An, Z., Jiang, X., Xu, Y., Zhang, Q.: Cross-image relational knowledge distillation for semantic segmentation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01200"},{"key":"25_CR30","doi-asserted-by":"crossref","unstructured":"Yang, L., Fan, Y., Xu, N.: Video instance segmentation. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00529"},{"key":"25_CR31","doi-asserted-by":"crossref","unstructured":"Yang, S., Fang, Y., Wang, X., Li, Y., Fang, C., Shan, Y., Feng, B., Liu, W.: Crossover learning for fast online video instance segmentation. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00794"},{"key":"25_CR32","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":"25_CR33","unstructured":"Zagoruyko, S., Komodakis, N.: Paying more attention to attention: improving the performance of convolutional neural networks via attention transfer. arXiv preprint arXiv:1612.03928 (2016)"},{"key":"25_CR34","unstructured":"Zhang, L., Ma, K.: Improve object detection with feature-based knowledge distillation: towards accurate and efficient detectors. In: ICLR (2021)"},{"key":"25_CR35","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 Analysis of Images and Patterns"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-44237-7_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,19]],"date-time":"2023-09-19T22:13:28Z","timestamp":1695161608000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-44237-7_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031442360","9783031442377"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-44237-7_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"20 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CAIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computer Analysis of Images and Patterns","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Limassol","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Cyprus","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"caip2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/cyprusconferences.org\/caip2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"https:\/\/www.easyacademia.org","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"67","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":"54","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":"81% - 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":"2.06","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":"2.09","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}