{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T13:54:44Z","timestamp":1774965284209,"version":"3.50.1"},"publisher-location":"Cham","reference-count":80,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198298","type":"print"},{"value":"9783031198304","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\/978-3-031-19830-4_34","type":"book-chapter","created":{"date-parts":[[2022,10,21]],"date-time":"2022-10-21T16:21:10Z","timestamp":1666369270000},"page":"596-613","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":55,"title":["Hierarchical Feature Alignment Network for\u00a0Unsupervised Video Object Segmentation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7677-7487","authenticated-orcid":false,"given":"Gensheng","family":"Pei","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7303-3231","authenticated-orcid":false,"given":"Fumin","family":"Shen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0337-9410","authenticated-orcid":false,"given":"Yazhou","family":"Yao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5487-9845","authenticated-orcid":false,"given":"Guo-Sen","family":"Xie","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6708-2205","authenticated-orcid":false,"given":"Zhenmin","family":"Tang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9008-222X","authenticated-orcid":false,"given":"Jinhui","family":"Tang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,10,22]]},"reference":[{"key":"34_CR1","unstructured":"Akhter, I., Ali, M., Faisal, M., Hartley, R.: Epo-net: Exploiting geometric constraints on dense trajectories for motion saliency. In: WACV (2020)"},{"key":"34_CR2","doi-asserted-by":"crossref","unstructured":"Chen, C., Wang, G., Peng, C., Zhang, X., Qin, H.: Improved robust video saliency detection based on long-term spatial-temporal information. In: TIP (2019)","DOI":"10.1109\/TIP.2019.2934350"},{"key":"34_CR3","doi-asserted-by":"crossref","unstructured":"Chen, T., Yao, Y., Zhang, L., Wang, Q., Xie, G., Shen, F.: Saliency guided inter-and intra-class relation constraints for weakly supervised semantic segmentation. In: TMM (2022)","DOI":"10.1109\/TMM.2022.3157481"},{"key":"34_CR4","unstructured":"Chen, Y., Han, C., Wang, N., Zhang, Z.: Revisiting feature alignment for one-stage object detection. arXiv preprint arXiv:1908.01570 (2019)"},{"key":"34_CR5","doi-asserted-by":"crossref","unstructured":"Cheng, H.K., Tai, Y.W., Tang, C.K.: Modular interactive video object segmentation: Interaction-to-mask, propagation and difference-aware fusion. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00551"},{"key":"34_CR6","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: ICCV (2017)","DOI":"10.1109\/ICCV.2017.81"},{"key":"34_CR7","unstructured":"Contributors, M.: MMSegmentation: Openmmlab semantic segmentation toolbox and benchmark (2020). https:\/\/github.com\/open-mmlab\/mmsegmentation"},{"key":"34_CR8","doi-asserted-by":"crossref","unstructured":"Duke, B., Ahmed, A., Wolf, C., Aarabi, P., Taylor, G.W.: Sstvos: Sparse spatiotemporal transformers for video object segmentation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00585"},{"key":"34_CR9","doi-asserted-by":"crossref","unstructured":"Fan, D.P., Wang, W., Cheng, M.M., Shen, J.: Shifting more attention to video salient object detection. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00875"},{"key":"34_CR10","doi-asserted-by":"crossref","unstructured":"Giordano, D., Murabito, F., Palazzo, S., Spampinato, C.: Superpixel-based video object segmentation using perceptual organization and location prior. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299114"},{"key":"34_CR11","doi-asserted-by":"crossref","unstructured":"Gu, Y., Wang, L., Wang, Z., Liu, Y., Cheng, M.M., Lu, S.P.: Pyramid constrained self-attention network for fast video salient object detection. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i07.6718"},{"key":"34_CR12","unstructured":"Han, B., Davis, L.S.: Density-based multifeature background subtraction with support vector machine. In: TPAMI (2011)"},{"key":"34_CR13","doi-asserted-by":"crossref","unstructured":"Han, J., Ding, J., Li, J., Xia, G.S.: Align deep features for oriented object detection. In: TGRS (2021)","DOI":"10.1109\/TGRS.2021.3062048"},{"key":"34_CR14","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":"34_CR15","doi-asserted-by":"crossref","unstructured":"Heo, Y., Koh, Y.J., Kim, C.S.: Guided interactive video object segmentation using reliability-based attention maps. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00724"},{"key":"34_CR16","doi-asserted-by":"crossref","unstructured":"Huang, S., Lu, Z., Cheng, R., He, C.: Fapn: Feature-aligned pyramid network for dense image prediction. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00090"},{"key":"34_CR17","doi-asserted-by":"crossref","unstructured":"Huang, Z., Wei, Y., Wang, X., Shi, H., Liu, W., Huang, T.S.: Alignseg: Feature-aligned segmentation networks. In: TPAMI (2021)","DOI":"10.1109\/TPAMI.2021.3062772"},{"key":"34_CR18","doi-asserted-by":"crossref","unstructured":"Hui, T., et al.: Collaborative spatial-temporal modeling for language-queried video actor segmentation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00417"},{"key":"34_CR19","doi-asserted-by":"crossref","unstructured":"Ilg, E., Mayer, N., Saikia, T., Keuper, M., Dosovitskiy, A., Brox, T.: Flownet 2.0: Evolution of optical flow estimation with deep networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.179"},{"key":"34_CR20","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: ICML (2015)"},{"key":"34_CR21","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":"34_CR22","doi-asserted-by":"crossref","unstructured":"Ji, G.P., Fu, K., Wu, Z., Fan, D.P., Shen, J., Shao, L.: Full-duplex strategy for video object segmentation. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00488"},{"key":"34_CR23","doi-asserted-by":"crossref","unstructured":"Johnander, J., Danelljan, M., Brissman, E., Khan, F.S., Felsberg, M.: A generative appearance model for end-to-end video object segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00916"},{"key":"34_CR24","doi-asserted-by":"crossref","unstructured":"Khoreva, A., Rohrbach, A., Schiele, B.: Video object segmentation with language referring expressions. In: ACCV (2018)","DOI":"10.1007\/978-3-030-11018-5_2"},{"key":"34_CR25","unstructured":"Kr\u00e4henb\u00fchl, P., Koltun, V.: Efficient inference in fully connected crfs with gaussian edge potentials. In: NeurIPS (2011)"},{"key":"34_CR26","doi-asserted-by":"crossref","unstructured":"Lao, D., Zhu, P., Wonka, P., Sundaramoorthi, G.: Flow-guided video inpainting with scene templates. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01433"},{"key":"34_CR27","doi-asserted-by":"crossref","unstructured":"Li, G., Xie, Y., Wei, T., Wang, K., Lin, L.: Flow guided recurrent neural encoder for video salient object detection. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00342"},{"key":"34_CR28","doi-asserted-by":"crossref","unstructured":"Li, H., Chen, G., Li, G., Yu, Y.: Motion guided attention for video salient object detection. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00737"},{"key":"34_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1007\/978-3-030-01219-9_13","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Li","year":"2018","unstructured":"Li, S., Seybold, B., Vorobyov, A., Lei, X., Kuo, C.-C.J.: Unsupervised video object segmentation with motion-based bilateral networks. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 215\u2013231. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01219-9_13"},{"key":"34_CR30","doi-asserted-by":"crossref","unstructured":"Li, X., Wang, W., Hu, X., Yang, J.: Selective kernel networks. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00060"},{"key":"34_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"775","DOI":"10.1007\/978-3-030-58452-8_45","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Li","year":"2020","unstructured":"Li, X., et al.: Semantic flow for fast and accurate scene parsing. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 775\u2013793. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_45"},{"key":"34_CR32","unstructured":"Liang, Y., Li, X., Jafari, N., Chen, Q.: Video object segmentation with adaptive feature bank and uncertain-region refinement. In: NeurIPS (2020)"},{"key":"34_CR33","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"34_CR34","doi-asserted-by":"crossref","unstructured":"Liu, D., Yu, D., Wang, C., Zhou, P.: F2net: Learning to focus on the foreground for unsupervised video object segmentation. In: AAAI (2021)","DOI":"10.1609\/aaai.v35i3.16308"},{"key":"34_CR35","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: Hierarchical vision transformer using shifted windows. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"34_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1007\/978-3-030-58580-8_39","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Lu","year":"2020","unstructured":"Lu, X., Wang, W., Danelljan, M., Zhou, T., Shen, J., Van Gool, L.: Video object segmentation with episodic graph memory networks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 661\u2013679. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58580-8_39"},{"key":"34_CR37","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":"34_CR38","unstructured":"Mahadevan, S., Athar, A., O\u0161ep, A., Hennen, S., Leal-Taix\u00e9, L., Leibe, B.: Making a case for 3d convolutions for object segmentation in videos. In: BMVC (2020)"},{"key":"34_CR39","doi-asserted-by":"crossref","unstructured":"Mao, Y., Wang, N., Zhou, W., Li, H.: Joint inductive and transductive learning for video object segmentation. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00953"},{"key":"34_CR40","doi-asserted-by":"crossref","unstructured":"Miao, J., Wu, Y., Liu, P., Ding, Y., Yang, Y.: Pose-guided feature alignment for occluded person re-identification. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00063"},{"key":"34_CR41","unstructured":"Nair, V., Hinton, G.E.: Rectified linear units improve restricted boltzmann machines. In: ICML (2010)"},{"key":"34_CR42","doi-asserted-by":"crossref","unstructured":"Ochs, P., Malik, J., Brox, T.: Segmentation of moving objects by long term video analysis. In: TPAMI (2013)","DOI":"10.1109\/TPAMI.2013.242"},{"key":"34_CR43","doi-asserted-by":"crossref","unstructured":"Oh, S.W., Lee, J.Y., Xu, N., Kim, S.J.: Fast user-guided video object segmentation by interaction-and-propagation networks. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00539"},{"key":"34_CR44","doi-asserted-by":"crossref","unstructured":"Oh, S.W., Lee, J.Y., Xu, N., Kim, S.J.: Video object segmentation using space-time memory networks. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00932"},{"key":"34_CR45","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":"34_CR46","unstructured":"Paszke, A., et al.: Pytorch: An imperative style, high-performance deep learning library. In: NeurIPS (2019)"},{"key":"34_CR47","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":"34_CR48","doi-asserted-by":"crossref","unstructured":"Perazzi, F., Wang, O., Gross, M., Sorkine-Hornung, A.: Fully connected object proposals for video segmentation. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.369"},{"key":"34_CR49","doi-asserted-by":"crossref","unstructured":"Prest, A., Leistner, C., Civera, J., Schmid, C., Ferrari, V.: Learning object class detectors from weakly annotated video. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6248065"},{"key":"34_CR50","doi-asserted-by":"crossref","unstructured":"Ren, S., Liu, W., Liu, Y., Chen, H., Han, G., He, S.: Reciprocal transformations for unsupervised video object segmentation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01520"},{"key":"34_CR51","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1007\/978-3-030-58555-6_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Seo","year":"2020","unstructured":"Seo, S., Lee, J.-Y., Han, B.: Urvos: Unified referring video object segmentation network with a large-scale benchmark. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12360, pp. 208\u2013223. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58555-6_13"},{"key":"34_CR52","doi-asserted-by":"crossref","unstructured":"Seong, H., Oh, S.W., Lee, J.Y., Lee, S., Lee, S., Kim, E.: Hierarchical memory matching network for video object segmentation. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01265"},{"key":"34_CR53","doi-asserted-by":"crossref","unstructured":"Shrivastava, A., Gupta, A., Girshick, R.: Training region-based object detectors with online hard example mining. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.89"},{"key":"34_CR54","doi-asserted-by":"crossref","unstructured":"Siam, M., et al.: Video object segmentation using teacher-student adaptation in a human robot interaction (hri) setting. In: ICRA (2019)","DOI":"10.1109\/ICRA.2019.8794254"},{"key":"34_CR55","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"744","DOI":"10.1007\/978-3-030-01252-6_44","volume-title":"Computer Vision \u2013 ECCV 2018","author":"H Song","year":"2018","unstructured":"Song, H., Wang, W., Zhao, S., Shen, J., Lam, K.-M.: Pyramid dilated deeper convlstm for video salient object detection. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 744\u2013760. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01252-6_44"},{"key":"34_CR56","doi-asserted-by":"crossref","unstructured":"Sun, D., Yang, X., Liu, M.Y., Kautz, J.: Pwc-net: Cnns for optical flow using pyramid, warping, and cost volume. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00931"},{"key":"34_CR57","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1007\/978-3-030-58536-5_24","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Teed","year":"2020","unstructured":"Teed, Z., Deng, J.: Raft: Recurrent all-pairs field transforms for optical flow. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 402\u2013419. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58536-5_24"},{"key":"34_CR58","doi-asserted-by":"crossref","unstructured":"Tokmakov, P., Alahari, K., Schmid, C.: Learning video object segmentation with visual memory. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.480"},{"key":"34_CR59","doi-asserted-by":"crossref","unstructured":"Tokmakov, P., Schmid, C., Alahari, K.: Learning to segment moving objects. In: IJCV (2019)","DOI":"10.1007\/s11263-018-1122-2"},{"key":"34_CR60","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"34_CR61","doi-asserted-by":"crossref","unstructured":"Ventura, C., Bellver, M., Girbau, A., Salvador, A., Marques, F., Giro-i Nieto, X.: Rvos: End-to-end recurrent network for video object segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00542"},{"key":"34_CR62","doi-asserted-by":"crossref","unstructured":"Wang, G., Zhang, T., Cheng, J., Liu, S., Yang, Y., Hou, Z.: Rgb-infrared cross-modality person re-identification via joint pixel and feature alignment. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00372"},{"key":"34_CR63","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: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00933"},{"key":"34_CR64","unstructured":"Wang, W., Shen, J., Porikli, F.: Saliency-aware geodesic video object segmentation. In: CVPR (2015)"},{"key":"34_CR65","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":"34_CR66","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., Luo, P.: Segformer: Simple and efficient design for semantic segmentation with transformers. In: NeurIPS (2021)"},{"key":"34_CR67","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"603","DOI":"10.1007\/978-3-030-01228-1_36","volume-title":"Computer Vision \u2013 ECCV 2018","author":"N Xu","year":"2018","unstructured":"Xu, N., et al.: YouTube-VOS: Sequence-to-sequence video object segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 603\u2013619. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01228-1_36"},{"key":"34_CR68","doi-asserted-by":"crossref","unstructured":"Yan, P., et al.: Semi-supervised video salient object detection using pseudo-labels. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00738"},{"key":"34_CR69","doi-asserted-by":"crossref","unstructured":"Yang, S., Zhang, L., Qi, J., Lu, H., Wang, S., Zhang, X.: Learning motion-appearance co-attention for zero-shot video object segmentation. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00159"},{"key":"34_CR70","doi-asserted-by":"crossref","unstructured":"Yang, Z., Wang, Q., Bertinetto, L., Hu, W., Bai, S., Torr, P.H.: Anchor diffusion for unsupervised video object segmentation. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00102"},{"key":"34_CR71","doi-asserted-by":"crossref","unstructured":"Yao, Y., et al.: Non-salient region object mining for weakly supervised semantic segmentation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00265"},{"key":"34_CR72","doi-asserted-by":"crossref","unstructured":"Yao, Y., et al.: Jo-src: A contrastive approach for combating noisy labels. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00515"},{"key":"34_CR73","doi-asserted-by":"crossref","unstructured":"Yao, Y., Zhang, J., Shen, F., Hua, X., Xu, J., Tang, Z.: Exploiting web images for dataset construction: A domain robust approach. In: TMM (2017)","DOI":"10.1109\/TMM.2017.2684626"},{"key":"34_CR74","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Chen, X., Wang, J.: Object-contextual representations for semantic segmentation. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58539-6_11"},{"key":"34_CR75","doi-asserted-by":"crossref","unstructured":"Zhang, K., Zhao, Z., Liu, D., Liu, Q., Liu, B.: Deep transport network for unsupervised video object segmentation. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00866"},{"key":"34_CR76","doi-asserted-by":"crossref","unstructured":"Zhang, M., et al.: Dynamic context-sensitive filtering network for video salient object detection. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00158"},{"key":"34_CR77","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1007\/978-3-030-58583-9_27","volume-title":"Computer Vision \u2013 ECCV 2020","author":"M Zhen","year":"2020","unstructured":"Zhen, M., et al.: Learning discriminative feature with crf for unsupervised video object segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12372, pp. 445\u2013462. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58583-9_27"},{"key":"34_CR78","doi-asserted-by":"crossref","unstructured":"Zhou, T., Li, J., Li, X., Shao, L.: Target-aware object discovery and association for unsupervised video multi-object segmentation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00691"},{"key":"34_CR79","doi-asserted-by":"crossref","unstructured":"Zhou, T., Wang, S., Zhou, Y., Yao, Y., Li, J., Shao, L.: Motion-attentive transition for zero-shot video object segmentation. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i07.7008"},{"key":"34_CR80","doi-asserted-by":"crossref","unstructured":"Zhuo, T., Cheng, Z., Zhang, P., Wong, Y., Kankanhalli, M.: Unsupervised online video object segmentation with motion property understanding. In: TIP (2019)","DOI":"10.1109\/TIP.2019.2930152"}],"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\/978-3-031-19830-4_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,22]],"date-time":"2022-10-22T00:01:29Z","timestamp":1666396889000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19830-4_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198298","9783031198304"],"references-count":80,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19830-4_34","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":"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)"}}]}}