{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T20:29:18Z","timestamp":1769632158341,"version":"3.49.0"},"publisher-location":"Cham","reference-count":57,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585679","type":"print"},{"value":"9783030585686","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-58568-6_29","type":"book-chapter","created":{"date-parts":[[2020,11,12]],"date-time":"2020-11-12T14:03:09Z","timestamp":1605189789000},"page":"490-506","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":33,"title":["Unsupervised Video Object Segmentation with Joint Hotspot Tracking"],"prefix":"10.1007","author":[{"given":"Lu","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Jianming","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Zhe","family":"Lin","sequence":"additional","affiliation":[]},{"given":"Radom\u00edr","family":"M\u011bch","sequence":"additional","affiliation":[]},{"given":"Huchuan","family":"Lu","sequence":"additional","affiliation":[]},{"given":"You","family":"He","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,13]]},"reference":[{"key":"29_CR1","unstructured":"Bylinskii, Z., Judd, T., Oliva, A., Torralba, A., Durand, F.: What do different evaluation metrics tell us about saliency models? arXiv preprint arXiv:1604.03605 (2016)"},{"key":"29_CR2","doi-asserted-by":"crossref","unstructured":"Caelles, S., Maninis, K.K., Pont-Tuset, J., Leal-Taix\u00e9, L., Cremers, D., Van Gool, L.: One-shot video object segmentation. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.565"},{"key":"29_CR3","doi-asserted-by":"crossref","unstructured":"Chen, Y., Pont-Tuset, J., Montes, A., Van Gool, L.: Blazingly fast video object segmentation with pixel-wise metric learning. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00130"},{"key":"29_CR4","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: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00774"},{"key":"29_CR5","doi-asserted-by":"crossref","unstructured":"Cheng, J., Tsai, Y.H., Wang, S., Yang, M.H.: SegFlow: joint learning for video object segmentation and optical flow. In: CVPR (2017)","DOI":"10.1109\/ICCV.2017.81"},{"key":"29_CR6","doi-asserted-by":"crossref","unstructured":"Deng, Z., et al.: R$$^{3}$$Net: recurrent residual refinement network for saliency detection. In: IJCAI (2018)","DOI":"10.24963\/ijcai.2018\/95"},{"key":"29_CR7","doi-asserted-by":"crossref","unstructured":"Ding, H., Cohen, S., Price, B., Jiang, X.: PhraseClick: toward achieving flexible interactive segmentation by phrase and click. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58580-8_25"},{"key":"29_CR8","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":"29_CR9","doi-asserted-by":"crossref","unstructured":"Ding, H., Jiang, X., Shuai, B., Liu, A.Q., Wang, G.: Context contrasted feature and gated multi-scale aggregation for scene segmentation. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00254"},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"Ding, H., Jiang, X., Shuai, B., Liu, A.Q., Wang, G.: Semantic correlation promoted shape-variant context for segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00909"},{"key":"29_CR11","doi-asserted-by":"crossref","unstructured":"Faktor, A., Irani, M.: Video segmentation by non-local consensus voting. In: BMVC (2014)","DOI":"10.5244\/C.28.21"},{"key":"29_CR12","unstructured":"Ferrari, V., Schmid, C., Civera, J., Leistner, C., Prest, A.: Learning object class detectors from weakly annotated video. In: CVPR (2012)"},{"issue":"12","key":"29_CR13","doi-asserted-by":"publisher","first-page":"1333","DOI":"10.1177\/0301006616657097","volume":"45","author":"KR Gegenfurtner","year":"2016","unstructured":"Gegenfurtner, K.R.: The interaction between vision and eye movements. Perception 45(12), 1333\u20131357 (2016)","journal-title":"Perception"},{"key":"29_CR14","doi-asserted-by":"crossref","unstructured":"Hariharan, B., Arbel\u00e1ez, P., Bourdev, L., Maji, S., Malik, J.: Semantic contours from inverse detectors. In: CVPR (2011)","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"29_CR15","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":"29_CR16","doi-asserted-by":"crossref","unstructured":"Hu, P., Caba, F., Wang, O., Lin, Z., Sclaroff, S., Perazzi, F.: Temporally distributed networks for fast video semantic segmentation. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00884"},{"key":"29_CR17","unstructured":"Hu, Y.T., Huang, J.B., Schwing, A.: MaskRNN: instance level video object segmentation. In: Advances in Neural Information Processing Systems (2017)"},{"key":"29_CR18","doi-asserted-by":"crossref","unstructured":"Hu, Y.T., Huang, J.B., Schwing, A.G.: Unsupervised video object segmentation using motion saliency-guided spatio-temporal propagation. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01246-5_48"},{"key":"29_CR19","doi-asserted-by":"crossref","unstructured":"Huang, X., Shen, C., Boix, X., Zhao, Q.: SALICON: reducing the semantic gap in saliency prediction by adapting deep neural networks. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.38"},{"key":"29_CR20","doi-asserted-by":"crossref","unstructured":"Jain, S.D., Xiong, B., Grauman, K.: FusionSeg: learning to combine motion and appearance for fully automatic segmentation of generic objects in videos. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.228"},{"key":"29_CR21","doi-asserted-by":"crossref","unstructured":"Jang, W.D., Lee, C., Kim, C.S.: Primary object segmentation in videos via alternate convex optimization of foreground and background distributions. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.82"},{"key":"29_CR22","doi-asserted-by":"crossref","unstructured":"Jiang, L., Xu, M., Liu, T., Qiao, M., Wang, Z.: DeepVS: a deep learning based video saliency prediction approach. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01264-9_37"},{"key":"29_CR23","doi-asserted-by":"crossref","unstructured":"Keuper, M., Andres, B., Brox, T.: Motion trajectory segmentation via minimum cost multicuts. In: CVPR (2015)","DOI":"10.1109\/ICCV.2015.374"},{"key":"29_CR24","doi-asserted-by":"crossref","unstructured":"Koh, Y.J., Kim, C.S.: Primary object segmentation in videos based on region augmentation and reduction. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.784"},{"key":"29_CR25","unstructured":"Kr\u00e4henb\u00fchl, P., Koltun, V.: Efficient inference in fully connected CRFs with Gaussian edge potentials. In: Advances in Neural Information Processing Systems, pp. 109\u2013117 (2011)"},{"key":"29_CR26","doi-asserted-by":"crossref","unstructured":"Lee, Y.J., Kim, J., Grauman, K.: Key-segments for video object segmentation. In: ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126471"},{"key":"29_CR27","doi-asserted-by":"crossref","unstructured":"Li, B., Wu, W., Wang, Q., Zhang, F., Xing, J., Yan, J.: SiamRPN++: evolution of Siamese visual tracking with very deep networks. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00441"},{"key":"29_CR28","doi-asserted-by":"crossref","unstructured":"Li, B., Yan, J., Wu, W., Zhu, Z., Hu, X.: High performance visual tracking with Siamese region proposal network. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00935"},{"key":"29_CR29","doi-asserted-by":"crossref","unstructured":"Li, F., Kim, T., Humayun, A., Tsai, D., Rehg, J.M.: Video segmentation by tracking many figure-ground segments. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.273"},{"key":"29_CR30","doi-asserted-by":"crossref","unstructured":"Li, S., Seybold, B., Vorobyov, A., Fathi, A., Huang, Q., Jay Kuo, C.C.: Instance embedding transfer to unsupervised video object segmentation. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00683"},{"key":"29_CR31","doi-asserted-by":"crossref","unstructured":"Li, S., Seybold, B., Vorobyov, A., Lei, X., Jay Kuo, C.C.: Unsupervised video object segmentation with motion-based bilateral networks. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01219-9_13"},{"key":"29_CR32","doi-asserted-by":"crossref","unstructured":"Lu, X., Wang, W., Ma, C., Shen, J., Shao, L., Porikli, F.: See more, know more: unsupervised video object segmentation with co-attention Siamese networks. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00374"},{"key":"29_CR33","doi-asserted-by":"crossref","unstructured":"Papazoglou, A., Ferrari, V.: Fast object segmentation in unconstrained video. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.223"},{"key":"29_CR34","doi-asserted-by":"crossref","unstructured":"Perazzi, F., Pont-Tuset, J., McWilliams, B., Van Gool, L., Gross, M., Sorkine-Hornung, A.: A benchmark dataset and evaluation methodology for video object segmentation. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.85"},{"key":"29_CR35","unstructured":"Pont-Tuset, J., Perazzi, F., Caelles, S., Arbel\u00e1ez, P., Sorkine-Hornung, A., Van Gool, L.: The 2017 DAVIS challenge on video object segmentation. arXiv:1704.00675 (2017)"},{"issue":"3","key":"29_CR36","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1016\/j.bandc.2008.08.025","volume":"68","author":"NN Rommelse","year":"2008","unstructured":"Rommelse, N.N., Van der Stigchel, S., Sergeant, J.A.: A review on eye movement studies in childhood and adolescent psychiatry. Brain Cogn. 68(3), 391\u2013414 (2008)","journal-title":"Brain Cogn."},{"key":"29_CR37","doi-asserted-by":"crossref","unstructured":"Shin Yoon, J., Rameau, F., Kim, J., Lee, S., Shin, S., So Kweon, I.: Pixel-level matching for video object segmentation using convolutional neural networks. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.238"},{"key":"29_CR38","doi-asserted-by":"crossref","unstructured":"Siam, M., et al.: Video object segmentation using teacher-student adaptation in a human robot interaction (HRI) setting. In: 2019 International Conference on Robotics and Automation (2019)","DOI":"10.1109\/ICRA.2019.8794254"},{"key":"29_CR39","doi-asserted-by":"crossref","unstructured":"Song, H., Wang, W., Zhao, S., Shen, J., Lam, K.M.: Pyramid dilated deeper ConvLSTM for video salient object detection. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01252-6_44"},{"key":"29_CR40","unstructured":"Tan, M., Le, Q.V.: EfficientNet: rethinking model scaling for convolutional neural networks. arXiv preprint arXiv:1905.11946 (2019)"},{"key":"29_CR41","doi-asserted-by":"crossref","unstructured":"Tokmakov, P., Alahari, K., Schmid, C.: Learning motion patterns in videos. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.64"},{"key":"29_CR42","doi-asserted-by":"crossref","unstructured":"Tokmakov, P., Alahari, K., Schmid, C.: Learning video object segmentation with visual memory. In: CVPR (2017)","DOI":"10.1109\/ICCV.2017.480"},{"key":"29_CR43","doi-asserted-by":"crossref","unstructured":"Wang, L., Lu, H., Wang, Y., Feng, M., Ruan, X.: Learning to detect salient objects with image-level supervision. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.404"},{"key":"29_CR44","doi-asserted-by":"crossref","unstructured":"Wang, Q., Zhang, L., Bertinetto, L., Hu, W., Torr, P.H.: Fast online object tracking and segmentation: a unifying approach. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00142"},{"key":"29_CR45","doi-asserted-by":"crossref","unstructured":"Wang, W., Lu, X., Shen, J., Crandall, D.J., Shao, L.: Zero-shot video object segmentation via attentive graph neural networks. In: CVPR (2019)","DOI":"10.1109\/ICCV.2019.00933"},{"key":"29_CR46","doi-asserted-by":"crossref","unstructured":"Wang, W., Shen, J., Guo, F., Cheng, M.M., Borji, A.: Revisiting video saliency: a large-scale benchmark and a new model. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00514"},{"key":"29_CR47","unstructured":"Wang, W., Shen, J., Porikli, F.: Saliency-aware geodesic video object segmentation. In: CVPR (2015)"},{"key":"29_CR48","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Learning unsupervised video object segmentation through visual attention. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00318"},{"key":"29_CR49","unstructured":"Wei, Z., et al.: Sequence-to-segments networks for detecting segments in videos. IEEE Trans. Pattern Anal. Mach. Intell. (2019)"},{"key":"29_CR50","unstructured":"Wei, Z., et al.: Sequence-to-segment networks for segment detection. In: Advances in Neural Information Processing Systems, pp. 3507\u20133516 (2018)"},{"key":"29_CR51","doi-asserted-by":"crossref","unstructured":"Wug Oh, S., Lee, J.Y., Sunkavalli, K., Joo Kim, S.: Fast video object segmentation by reference-guided mask propagation. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00770"},{"key":"29_CR52","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":"29_CR53","doi-asserted-by":"crossref","unstructured":"Yang, Z., Wang, Q., Bertinetto, L., Hu, W., Bai, S., Torr, P.H.S.: Anchor diffusion for unsupervised video object segmentation. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00102"},{"key":"29_CR54","doi-asserted-by":"crossref","unstructured":"Yang, Z., et al.: Predicting goal-directed human attention using inverse reinforcement learning. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00027"},{"key":"29_CR55","doi-asserted-by":"crossref","unstructured":"Zhang, L., Dai, J., Lu, H., He, Y.: A bi-directional message passing model for salient object detection. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00187"},{"key":"29_CR56","doi-asserted-by":"crossref","unstructured":"Zhang, L., Lin, Z., Zhang, J., Lu, H., He, Y.: Fast video object segmentation via dynamic targeting network. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00568"},{"key":"29_CR57","doi-asserted-by":"crossref","unstructured":"Zhang, L., Zhang, J., Lin, Z., Lu, H., He, Y.: CapSal: leveraging captioning to boost semantics for salient object detection. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00618"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58568-6_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T00:23:48Z","timestamp":1731371028000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58568-6_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585679","9783030585686"],"references-count":57,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58568-6_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"13 November 2020","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":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","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":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","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":"1360","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":"27% - 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","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":"7","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)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic. From the ECCV Workshops 249 full papers, 18 short papers, and 21 further contributions were published out of a total of 467 submissions.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}