{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:03:47Z","timestamp":1772906627201,"version":"3.50.1"},"publisher-location":"Cham","reference-count":60,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030586201","type":"print"},{"value":"9783030586218","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\/978-3-030-58621-8_2","type":"book-chapter","created":{"date-parts":[[2020,11,26]],"date-time":"2020-11-26T19:03:23Z","timestamp":1606417403000},"page":"17-34","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":50,"title":["A Unified Framework for Shot Type Classification Based on Subject Centric Lens"],"prefix":"10.1007","author":[{"given":"Anyi","family":"Rao","sequence":"first","affiliation":[]},{"given":"Jiaze","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Linning","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Xuekun","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Qingqiu","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Bolei","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Dahua","family":"Lin","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,27]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Bagheri-Khaligh, A., Raziperchikolaei, R., Moghaddam, M.E.: A new method for shot classification in soccer sports video based on SVM classifier. In: 2012 IEEE Southwest Symposium on Image Analysis and Interpretation, pp. 109\u2013112. IEEE (2012)","DOI":"10.1109\/SSIAI.2012.6202465"},{"key":"2_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1007\/978-3-030-11018-5_37","volume-title":"Computer Vision \u2013 ECCV 2018 Workshops","author":"V Belagiannis","year":"2019","unstructured":"Belagiannis, V., Farshad, A., Galasso, F.: Adversarial network compression. In: Leal-Taix\u00e9, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11132, pp. 431\u2013449. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-11018-5_37"},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Benini, S., Canini, L., Leonardi, R.: Estimating cinematographic scene depth in movie shots. In: 2010 IEEE International Conference on Multimedia and Expo, pp. 855\u2013860. IEEE (2010)","DOI":"10.1109\/ICME.2010.5582611"},{"issue":"3","key":"2_CR4","doi-asserted-by":"publisher","first-page":"686","DOI":"10.1109\/TMM.2014.2300833","volume":"16","author":"S Bhattacharya","year":"2014","unstructured":"Bhattacharya, S., Mehran, R., Sukthankar, R., Shah, M.: Classification of cinematographic shots using lie algebra and its application to complex event recognition. IEEE Trans. Multimed. 16(3), 686\u2013696 (2014)","journal-title":"IEEE Trans. Multimed."},{"key":"2_CR5","unstructured":"Caelles, S., Pont-Tuset, J., Perazzi, F., Montes, A., Maninis, K.K., Van Gool, L.: The 2019 DAVIS challenge on VOS: unsupervised multi-object segmentation. arXiv:1905.00737 (2019)"},{"issue":"1","key":"2_CR6","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1007\/s11042-011-0916-9","volume":"62","author":"L Canini","year":"2013","unstructured":"Canini, L., Benini, S., Leonardi, R.: Classifying cinematographic shot types. Multimed. Tools Appl. 62(1), 51\u201373 (2013)","journal-title":"Multimed. Tools Appl."},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? a new model and the kinetics dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Chao, Y.W., Vijayanarasimhan, S., Seybold, B., Ross, D.A., Deng, J., Sukthankar, R.: Rethinking the faster R-CNN architecture for temporal action localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1130\u20131139 (2018)","DOI":"10.1109\/CVPR.2018.00124"},{"issue":"3","key":"2_CR9","doi-asserted-by":"publisher","first-page":"569","DOI":"10.1109\/TPAMI.2014.2345401","volume":"37","author":"MM Cheng","year":"2014","unstructured":"Cheng, M.M., Mitra, N.J., Huang, X., Torr, P.H., Hu, S.M.: Global contrast based salient region detection. IEEE Trans. Pattern Anal. Mach. Intell. 37(3), 569\u2013582 (2014)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2_CR10","unstructured":"Cheng, Y., Wang, D., Zhou, P., Zhang, T.: A survey of model compression and acceleration for deep neural networks. arXiv preprint arXiv:1710.09282 (2017)"},{"key":"2_CR11","unstructured":"Christoph, R., Pinz, F.A.: Spatiotemporal residual networks for video action recognition. In: Advances in Neural Information Processing Systems, pp. 3468\u20133476 (2016)"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Deng, J., Pan, Y., Yao, T., Zhou, W., Li, H., Mei, T.: Relation distillation networks for video object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 7023\u20137032 (2019)","DOI":"10.1109\/ICCV.2019.00712"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Deng, Z., et al.: R3Net: recurrent residual refinement network for saliency detection. In: Proceedings of the 27th International Joint Conference on Artificial Intelligence, pp. 684\u2013690. AAAI Press (2018)","DOI":"10.24963\/ijcai.2018\/95"},{"issue":"6","key":"2_CR14","doi-asserted-by":"publisher","first-page":"1066","DOI":"10.1109\/TMM.2005.858395","volume":"7","author":"LY Duan","year":"2005","unstructured":"Duan, L.Y., Xu, M., Tian, Q., Xu, C.S., Jin, J.S.: A unified framework for semantic shot classification in sports video. IEEE Trans. Multimed. 7(6), 1066\u20131083 (2005)","journal-title":"IEEE Trans. Multimed."},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Ekin, A., Tekalp, A.M.: Shot type classification by dominant color for sports video segmentation and summarization. In: Proceedings of the 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003, ICASSP 2003, vol. 3, pp. III-173. IEEE (2003)","DOI":"10.1109\/ICASSP.2003.1199135"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Heilbron, F.C., Escorcia, V., Ghanem, B., Niebles, J.C.: ActivityNet: a large-scale video benchmark for human activity understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 961\u2013970 (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. arXiv preprint arXiv:1812.03982 (2018)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"2_CR18","volume-title":"Understanding Movies","author":"LD Giannetti","year":"1999","unstructured":"Giannetti, L.D., Leach, J.: Understanding Movies, vol. 1. Prentice Hall, Upper Saddle River (1999)"},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Goldblum, M., Fowl, L., Feizi, S., Goldstein, T.: Adversarially robust distillation. In: Thirty-Fourth AAAI Conference on Artificial Intelligence (2020)","DOI":"10.1609\/aaai.v34i04.5816"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Guo, C., et al.: Progressive sparse local attention for video object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3909\u20133918 (2019)","DOI":"10.1109\/ICCV.2019.00401"},{"issue":"10","key":"2_CR21","doi-asserted-by":"publisher","first-page":"1682","DOI":"10.1109\/TCSVT.2014.2345933","volume":"24","author":"MA Hasan","year":"2014","unstructured":"Hasan, M.A., Xu, M., He, X., Xu, C.: CAMHID: camera motion histogram descriptor and its application to cinematographic shot classification. IEEE Trans. Circuits Syst. Video Technol. 24(10), 1682\u20131695 (2014)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"2_CR23","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. In: NIPS Deep Learning and Representation Learning Workshop (2015)"},{"issue":"4","key":"2_CR24","doi-asserted-by":"publisher","first-page":"815","DOI":"10.1109\/TPAMI.2018.2815688","volume":"41","author":"Q Hou","year":"2019","unstructured":"Hou, Q., Cheng, M.M., Hu, X., Borji, A., Tu, Z., Torr, P.: Deeply supervised salient object detection with short connections. IEEE TPAMI 41(4), 815\u2013828 (2019)","journal-title":"IEEE TPAMI"},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"Huang, Q., Xiong, Y., Rao, A., Wang, J., Lin, D.: Movienet: a holistic dataset for movie understanding. In: The European Conference on Computer Vision (ECCV). Springer, Cham (2020)","DOI":"10.1007\/978-3-030-58548-8_41"},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Jiang, H., Zhang, M.: Tennis video shot classification based on support vector machine. In: 2011 IEEE International Conference on Computer Science and Automation Engineering, vol. 2, pp. 757\u2013761. IEEE (2011)","DOI":"10.1109\/CSAE.2011.5952612"},{"key":"2_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"272","DOI":"10.1007\/978-3-642-33712-3_20","volume-title":"Computer Vision \u2013 ECCV 2012","author":"A Kowdle","year":"2012","unstructured":"Kowdle, A., Chen, T.: Learning to segment a video to clips based on scene and camera motion. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7574, pp. 272\u2013286. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33712-3_20"},{"key":"2_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"923","DOI":"10.1007\/978-3-642-10467-1_83","volume-title":"Advances in Multimedia Information Processing - PCM 2009","author":"L Li","year":"2009","unstructured":"Li, L., Zhang, X., Hu, W., Li, W., Zhu, P.: Soccer video shot classification based on color characterization using dominant sets clustering. In: Muneesawang, P., Wu, F., Kumazawa, I., Roeksabutr, A., Liao, M., Tang, X. (eds.) PCM 2009. LNCS, vol. 5879, pp. 923\u2013929. Springer, Heidelberg (2009). https:\/\/doi.org\/10.1007\/978-3-642-10467-1_83"},{"key":"2_CR29","doi-asserted-by":"crossref","unstructured":"Li, S., He, F., Du, B., Zhang, L., Xu, Y., Tao, D.: Fast spatio-temporal residual network for video super-resolution. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.01077"},{"issue":"8","key":"2_CR30","doi-asserted-by":"publisher","first-page":"3919","DOI":"10.1109\/TIP.2016.2579306","volume":"25","author":"X Li","year":"2016","unstructured":"Li, X., et al.: DeepSaliency: multi-task deep neural network model for salient object detection. IEEE Trans. Image Process. 25(8), 3919\u20133930 (2016)","journal-title":"IEEE Trans. Image Process."},{"key":"2_CR31","doi-asserted-by":"publisher","first-page":"502","DOI":"10.1109\/TPAMI.2019.2901464","volume":"42","author":"M Monfort","year":"2019","unstructured":"Monfort, M., et al.: Moments in time dataset: one million videos for event understanding. IEEE Trans. Pattern Anal. Mach. Intell. 42, 502\u2013508 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2_CR32","doi-asserted-by":"crossref","unstructured":"Prasertsakul, P., Kondo, T., Iida, H.: Video shot classification using 2D motion histogram. In: 2017 14th International Conference on Electrical Engineering\/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON), pp. 202\u2013205. IEEE (2017)","DOI":"10.1109\/ECTICon.2017.8096208"},{"key":"2_CR33","doi-asserted-by":"crossref","unstructured":"Rao, A., et al.: A local-to-global approach to multi-modal movie scene segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10146\u201310155 (2020)","DOI":"10.1109\/CVPR42600.2020.01016"},{"key":"2_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1007\/978-3-030-01240-3_4","volume-title":"Computer Vision \u2013 ECCV 2018","author":"A Recasens","year":"2018","unstructured":"Recasens, A., Kellnhofer, P., Stent, S., Matusik, W., Torralba, A.: Learning to zoom: a saliency-based sampling layer for neural networks. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 52\u201367. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01240-3_4"},{"key":"2_CR35","doi-asserted-by":"crossref","unstructured":"Roth, J., et al.: AVA-ActiveSpeaker: an audio-visual dataset for active speaker detection. arXiv preprint arXiv:1901.01342 (2019)","DOI":"10.1109\/ICCVW.2019.00460"},{"issue":"3","key":"2_CR36","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vis."},{"key":"2_CR37","doi-asserted-by":"crossref","unstructured":"Savardi, M., Signoroni, A., Migliorati, P., Benini, S.: Shot scale analysis in movies by convolutional neural networks. In: 2018 25th IEEE International Conference on Image Processing (ICIP), pp. 2620\u20132624. IEEE (2018)","DOI":"10.1109\/ICIP.2018.8451474"},{"key":"2_CR38","doi-asserted-by":"crossref","unstructured":"Shou, Z., et al.: DMC-Net: generating discriminative motion cues for fast compressed video action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1268\u20131277 (2019)","DOI":"10.1109\/CVPR.2019.00136"},{"issue":"8","key":"2_CR39","doi-asserted-by":"publisher","first-page":"1163","DOI":"10.1109\/TCSVT.2011.2138830","volume":"21","author":"P Sidiropoulos","year":"2011","unstructured":"Sidiropoulos, P., Mezaris, V., Kompatsiaris, I., Meinedo, H., Bugalho, M., Trancoso, I.: Temporal video segmentation to scenes using high-level audiovisual features. IEEE Trans. Circuits Syst. Video Technol. 21(8), 1163\u20131177 (2011)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"10","key":"2_CR40","doi-asserted-by":"publisher","first-page":"1529","DOI":"10.1109\/TCSVT.2009.2022705","volume":"19","author":"HL Wang","year":"2009","unstructured":"Wang, H.L., Cheong, L.F.: Taxonomy of directing semantics for film shot classification. IEEE Trans. Circuits Syst. Video Technol. 19(10), 1529\u20131542 (2009)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"2_CR41","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1007\/978-3-319-46484-8_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"L Wang","year":"2016","unstructured":"Wang, L., et al.: Temporal segment networks: towards good practices for deep action recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 20\u201336. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_2"},{"key":"2_CR42","unstructured":"Wang, X., Zhang, R., Sun, Y., Qi, J.: KDGAN: knowledge distillation with generative adversarial networks. In: Bengio, S., Wallach, H., Larochelle, H., Grauman, K., Cesa-Bianchi, N., Garnett, R. (eds.) Advances in Neural Information Processing Systems 31, pp. 775\u2013786. Curran Associates, Inc. (2018)"},{"key":"2_CR43","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"2_CR44","doi-asserted-by":"crossref","unstructured":"Wang, Y., Xu, C., Xu, C., Tao, D.: Adversarial learning of portable student networks. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.11667"},{"key":"2_CR45","unstructured":"Wikipedia: As seen through a telescope. https:\/\/en.wikipedia.org\/. Accessed 18 Feb 2020"},{"key":"2_CR46","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1007\/978-3-030-58610-2_11","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Xia","year":"2020","unstructured":"Xia, J., Rao, A., Huang, Q., Xu, L., Wen, J., Lin, D.: Online multi-modal person search in videos. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12357, pp. 174\u2013190. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58610-2_11"},{"key":"2_CR47","doi-asserted-by":"crossref","unstructured":"Tong, X.-F., Liu, Q.-S., Lu, H.-Q., Jin, H.-L.: Shot classification in sports video. In: Proceedings 7th International Conference on Signal Processing, ICSP 2004, vol. 2, pp. 1364\u20131367 (2004)","DOI":"10.1109\/ICOSP.2004.1441579"},{"key":"2_CR48","doi-asserted-by":"crossref","unstructured":"Xiong, Y., Huang, Q., Guo, L., Zhou, H., Zhou, B., Lin, D.: A graph-based framework to bridge movies and synopses. In: The IEEE International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00469"},{"key":"2_CR49","doi-asserted-by":"crossref","unstructured":"Xu, G., Liu, Z., Li, X., Loy, C.C.: Knowledge distillation meets self-supervision. In: European Conference on Computer Vision (ECCV). Springer, Cham (2020)","DOI":"10.1007\/978-3-030-58545-7_34"},{"key":"2_CR50","doi-asserted-by":"crossref","unstructured":"Xu, H., Das, A., Saenko, K.: R-C3D: region convolutional 3D network for temporal activity detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5783\u20135792 (2017)","DOI":"10.1109\/ICCV.2017.617"},{"key":"2_CR51","doi-asserted-by":"crossref","unstructured":"Xu, K., Wen, L., Li, G., Bo, L., Huang, Q.: Spatiotemporal CNN for video object segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1379\u20131388 (2019)","DOI":"10.1109\/CVPR.2019.00147"},{"key":"2_CR52","doi-asserted-by":"crossref","unstructured":"Xu, M., et al.: Using context saliency for movie shot classification. In: 2011 18th IEEE International Conference on Image Processing, pp. 3653\u20133656. IEEE (2011)","DOI":"10.1109\/ICIP.2011.6116510"},{"key":"2_CR53","doi-asserted-by":"crossref","unstructured":"Xu, R., Li, X., Zhou, B., Loy, C.C.: Deep flow-guided video inpainting. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00384"},{"key":"2_CR54","doi-asserted-by":"crossref","unstructured":"Yang, J., Zheng, W.S., Yang, Q., Chen, Y.C., Tian, Q.: Spatial-temporal graph convolutional network for video-based person re-identification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3289\u20133299 (2020)","DOI":"10.1109\/CVPR42600.2020.00335"},{"key":"2_CR55","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"560","DOI":"10.1007\/978-3-030-01216-8_34","volume-title":"Computer Vision \u2013 ECCV 2018","author":"IH Laradji","year":"2018","unstructured":"Laradji, I.H., Rostamzadeh, N., Pinheiro, P.O., Vazquez, D., Schmidt, M.: Where are the blobs: counting by localization with point supervision. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 560\u2013576. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01216-8_34"},{"key":"2_CR56","doi-asserted-by":"crossref","unstructured":"Yuan, L., et al.: Central similarity quantization for efficient image and video retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3083\u20133092 (2020)","DOI":"10.1109\/CVPR42600.2020.00315"},{"key":"2_CR57","doi-asserted-by":"crossref","unstructured":"Zeng, X., Liao, R., Gu, L., Xiong, Y., Fidler, S., Urtasun, R.: DMM-Net: differentiable mask-matching network for video object segmentation. arXiv preprint arXiv:1909.12471 (2019)","DOI":"10.1109\/ICCV.2019.00403"},{"key":"2_CR58","unstructured":"Zhang, H., Liu, D., Xiong, Z.: Two-stream oriented video super-resolution for action recognition. arXiv preprint arXiv:1903.05577 (2019)"},{"key":"2_CR59","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Xiong, Y., Wang, L., Wu, Z., Tang, X., Lin, D.: Temporal action detection with structured segment networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2914\u20132923 (2017)","DOI":"10.1109\/ICCV.2017.317"},{"key":"2_CR60","doi-asserted-by":"crossref","unstructured":"Zhu, W., Liang, S., Wei, Y., Sun, J.: Saliency optimization from robust background detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2814\u20132821 (2014)","DOI":"10.1109\/CVPR.2014.360"}],"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\/978-3-030-58621-8_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T00:03:43Z","timestamp":1732579423000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58621-8_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030586201","9783030586218"],"references-count":60,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58621-8_2","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":"27 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)"}}]}}