{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T19:10:52Z","timestamp":1775243452904,"version":"3.50.1"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012458","type":"print"},{"value":"9783030012465","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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":[[2018]]},"DOI":"10.1007\/978-3-030-01246-5_22","type":"book-chapter","created":{"date-parts":[[2018,10,5]],"date-time":"2018-10-05T16:14:56Z","timestamp":1538756096000},"page":"364-380","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":156,"title":["Multi-fiber Networks for Video Recognition"],"prefix":"10.1007","author":[{"given":"Yunpeng","family":"Chen","sequence":"first","affiliation":[]},{"given":"Yannis","family":"Kalantidis","sequence":"additional","affiliation":[]},{"given":"Jianshu","family":"Li","sequence":"additional","affiliation":[]},{"given":"Shuicheng","family":"Yan","sequence":"additional","affiliation":[]},{"given":"Jiashi","family":"Feng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"key":"22_CR1","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4724\u20134733. IEEE (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"22_CR2","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A closer look at spatiotemporal convolutions for action recognition (2017). arXiv preprint: arXiv:1711.11248","DOI":"10.1109\/CVPR.2018.00675"},{"key":"22_CR3","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":"22_CR4","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN (2015). arXiv preprint: arXiv:1504.08083","DOI":"10.1109\/ICCV.2015.169"},{"key":"22_CR5","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs (2016). arXiv preprint: arXiv:1606.00915"},{"key":"22_CR6","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp. 1725\u20131732 (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"22_CR7","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 4489\u20134497. IEEE (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"22_CR8","unstructured":"Xie, S., Sun, C., Huang, J., Tu, Z., Murphy, K.: Rethinking spatiotemporal feature learning for video understanding (2017). arXiv preprint: arXiv:1712.04851"},{"key":"22_CR9","doi-asserted-by":"crossref","unstructured":"Hara, K., Kataoka, H., Satoh, Y.: Can spatiotemporal 3D CNNs retrace the history of 2D CNNs and imagenet. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, pp. 18\u201322 (2018)","DOI":"10.1109\/CVPR.2018.00685"},{"key":"22_CR10","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition (2014). arXiv preprint: arXiv:1409.1556"},{"key":"22_CR11","doi-asserted-by":"crossref","unstructured":"Shou, Z., Wang, D., Chang, S.F.: Temporal action localization in untrimmed videos via multi-stage CNNs. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.119"},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"Shou, Z., Chan, J., Zareian, A., Miyazawa, K., Chang, S.F.: CDC: convolutional-de-convolutional networks for precise temporal action localization in untrimmed videos. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.155"},{"key":"22_CR13","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Advances in Neural Information Processing Systems, pp. 568\u2013576 (2014)"},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Zisserman, A.: Convolutional two-stream network fusion for video action recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.213"},{"key":"22_CR15","doi-asserted-by":"crossref","unstructured":"Ng, J.Y.H., Hausknecht, M., Vijayanarasimhan, S., Vinyals, O., Monga, R., Toderici, G.: Beyond short snippets: deep networks for video classification. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4694\u20134702. IEEE (2015)","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"22_CR16","doi-asserted-by":"crossref","unstructured":"Wang, L., Li, W., Li, W., Van Gool, L.: Appearance-and-relation networks for video classification (2017). arXiv preprint: arXiv:1711.09125","DOI":"10.1109\/CVPR.2018.00155"},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"Tran, A., Cheong, L.F.: Two-stream flow-guided convolutional attention networks for action recognition. In: International Conference on Computer Vision (2017)","DOI":"10.1109\/ICCVW.2017.368"},{"key":"22_CR18","doi-asserted-by":"crossref","unstructured":"Wu, C.Y., Zaheer, M., Hu, H., Manmatha, R., Smola, A.J., Kr\u00e4henb\u00fchl, P.: Compressed video action recognition (2017). arXiv preprint: arXiv:1712.00636","DOI":"10.1109\/CVPR.2018.00631"},{"key":"22_CR19","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"22_CR20","unstructured":"Kay, W., et al.: The kinetics human action video dataset (2017). arXiv preprint: arXiv:1705.06950"},{"key":"22_CR21","series-title":"LNCS","first-page":"162","volume-title":"ECCV 2018, Part XVI","author":"Z Shou","year":"2018","unstructured":"Shou, Z., Gao, H., Zhang, L., Miyazawa, K., Chang, S.F.: Autoloc: weakly-supervised temporal action localization in untrimmed videos. In: Ferrari, V. (ed.) ECCV 2018, Part XVI. LNCS, vol. 11220, pp. 162\u2013179. Springer, AG (2018)"},{"key":"22_CR22","doi-asserted-by":"crossref","unstructured":"Shou, Z.: Online detection of action start in untrimmed, streaming videos. In: Ferrari, V. et al. (eds.) ECCV 2018, Part III. LNCS, vol. 11207, pp. 551\u2013568. Springer, AG (2018)","DOI":"10.1007\/978-3-030-01219-9_33"},{"key":"22_CR23","unstructured":"Tran, D., Ray, J., Shou, Z., Chang, S.F., Paluri, M.: Convnet architecture search for spatiotemporal feature learning (2017). arXiv preprint: arXiv:1708.05038"},{"key":"22_CR24","unstructured":"Szegedy, C., et al.: Going deeper with convolutions"},{"key":"22_CR25","unstructured":"Howard, A.G., et al.: Mobilenets: efficient convolutional neural networks for mobile vision applications (2017). arXiv preprint: arXiv:1704.04861"},{"key":"22_CR26","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: Inverted residuals and linear bottlenecks: Mobile networks for classification, detection and segmentation (2018). arXiv preprint: arXiv:1801.04381","DOI":"10.1109\/CVPR.2018.00474"},{"key":"22_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhou, X., Lin, M., Sun, J.: Shufflenet: an extremely efficient convolutional neural network for mobile devices (2017). arXiv preprint: arXiv:1707.01083","DOI":"10.1109\/CVPR.2018.00716"},{"key":"22_CR28","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5987\u20135995. IEEE (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"22_CR29","doi-asserted-by":"crossref","unstructured":"Ahmed, K., Torresani, L.: Maskconnect: Connectivity learning by gradient descent. In: Ferrari, V., et al. (eds.) ECCV 2018, Part V. LNCS, vol. 11209, pp. 362\u2013378. Springer, AG (2018)","DOI":"10.1007\/978-3-030-01228-1_22"},{"key":"22_CR30","doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: deep learning with depthwise separable convolutions (2017). arXiv preprint: arXiv:1610.02357","DOI":"10.1109\/CVPR.2017.195"},{"key":"22_CR31","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"key":"22_CR32","unstructured":"Chen, Y., Li, J., Xiao, H., Jin, X., Yan, S., Feng, J.: Dual path networks. In: Advances in Neural Information Processing Systems, pp. 4470\u20134478 (2017)"},{"key":"22_CR33","unstructured":"Chen, T., et al.: Mxnet: a flexible and efficient machine learning library for heterogeneous distributed systems (2015). arXiv preprint: arXiv:1512.01274"},{"key":"22_CR34","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: Ucf101: a dataset of 101 human actions classes from videos in the wild (2012). arXiv preprint: arXiv:1212.0402"},{"key":"22_CR35","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: HMDB: a large video database for human motion recognition. In: 2011 IEEE International Conference on Computer Vision (ICCV), pp. 2556\u20132563. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"22_CR36","unstructured":"Paszke, A., Gross, S., Chintala, S., Chanan, G.: Pytorch (2017)"},{"key":"22_CR37","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Wildes, R.P.: Spatiotemporal multiplier networks for video action recognition. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7445\u20137454. IEEE (2017)","DOI":"10.1109\/CVPR.2017.787"},{"key":"22_CR38","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, Part VIII. LNCS, vol. 9912, pp. 20\u201336. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_2"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01246-5_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T18:36:40Z","timestamp":1775241400000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01246-5_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012458","9783030012465"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01246-5_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"6 October 2018","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":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}