{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T17:49:36Z","timestamp":1743011376737,"version":"3.40.3"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030110178"},{"type":"electronic","value":"9783030110185"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"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":[[2019]]},"DOI":"10.1007\/978-3-030-11018-5_27","type":"book-chapter","created":{"date-parts":[[2019,1,24]],"date-time":"2019-01-24T05:50:50Z","timestamp":1548309050000},"page":"297-305","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Building A Size Constrained Predictive Models for Video Classification"],"prefix":"10.1007","author":[{"given":"Miha","family":"Skalic","sequence":"first","affiliation":[]},{"given":"David","family":"Austin","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,1,23]]},"reference":[{"key":"27_CR1","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"YA LeCun","year":"2015","unstructured":"LeCun, Y.A., Bengio, Y., Hinton, G.E.: Deep learning. Nature 521, 436\u2013444 (2015)","journal-title":"Nature"},{"key":"27_CR2","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems (2012)"},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Graves, A., Mohamed, A., Hinton, G.: Speech recognition with deep recurrent neural networks. In: Icassp, pp. 6645\u20136649 (2013)","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"27_CR4","unstructured":"Ng, J.Y.H., Hausknecht, M., Vijayanarasimhan, S., Vinyals, O., Monga, R., Toderici, G.: Beyond short snippets: deep networks for video classification. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (2015)"},{"key":"27_CR5","unstructured":"Abu-El-Haija, S., et al.: YouTube-8m: A large-scale video classification benchmark. CoRR abs\/1609.08675 (2016)"},{"key":"27_CR6","unstructured":"Miech, A., Laptev, I., Sivic, J.: Learnable pooling with context gating for video classification. CoRR abs\/1706.06905 (2017)"},{"key":"27_CR7","unstructured":"Wang, H., Zhang, T., Wu, J.: The monkeytyping solution to the Youtube-8m video understanding challenge. CoRR abs\/1706.05150 (2017)"},{"key":"27_CR8","unstructured":"Li, F., et al.: Temporal modeling approaches for large-scale youtube-8m video understanding. CoRR abs\/1707.04555 (2017)"},{"key":"27_CR9","unstructured":"Chen, S., Wang, X., Tang, Y., Chen, X., Wu, Z., Jiang, Y.: Aggregating frame-level features for large-scale video classification. CoRR abs\/1707.00803 (2017)"},{"key":"27_CR10","unstructured":"Skalic, M., Pekalski, M., Pan, X.E.: Deep learning methods for efficient large scale video labeling. CoRR abs\/1706.04572 (2017)"},{"key":"27_CR11","unstructured":"Abadi, M., et al.: TensorFlow: Large-scale machine learning on heterogeneous systems (2015). Software available from http:\/\/tensorflow.org"},{"key":"27_CR12","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016","DOI":"10.1109\/CVPR.2016.308"},{"issue":"8","key":"27_CR13","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"27_CR14","doi-asserted-by":"crossref","unstructured":"Cho, K., van Merrienboer, B., G\u00fcl\u00e7ehre, \u00c7., Bougares, F., Schwenk, H., Bengio, Y.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. CoRR abs\/1406.1078 (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"27_CR15","doi-asserted-by":"crossref","unstructured":"Laptev, I., Marsza\u0142ek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2008)","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"27_CR16","doi-asserted-by":"crossref","unstructured":"Wang, H., Schmid, C.: Action recognition with improved trajectories. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3551\u20133558 (2013)","DOI":"10.1109\/ICCV.2013.441"},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Wang, H., Ullah, M.M., Klaser, A., Laptev, I., Schmid, C.: Evaluation of local spatio-temporal features for action recognition. In: BMVC 2009 \u2013 British Machine Vision Conference (2009)","DOI":"10.5244\/C.23.124"},{"key":"27_CR18","doi-asserted-by":"crossref","unstructured":"J\u00e9gou, H., Douze, M., Schmid, C., P\u00e9rez, P.: Aggregating local descriptors into a compact image representation. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 3304\u20133311 (2010)","DOI":"10.1109\/CVPR.2010.5540039"},{"key":"27_CR19","doi-asserted-by":"crossref","unstructured":"Perronnin, F., Dance, C.: Fisher kernels on visual vocabularies for image categorization. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1\u20138 (2007)","DOI":"10.1109\/CVPR.2007.383266"},{"key":"27_CR20","doi-asserted-by":"crossref","unstructured":"Arandjelovic, R., Gronat, P., Torii, A., Pajdla, T., Sivic, J.: NetVLAD: CNN architecture for weakly supervised place recognition. In: IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 5297\u20135307 (2018)","DOI":"10.1109\/TPAMI.2017.2711011"},{"key":"27_CR21","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. In: NIPS Deep Learning and Representation Learning Workshop (2015)"},{"key":"27_CR22","unstructured":"Ruppert, D.: Efficient estimations from a slowly convergent robbins-monro process. Technical report, Cornell University Operations Research and Industrial Engineering (2018)"},{"key":"27_CR23","unstructured":"Han, S., Mao, H., Dally, W.J.: Deep compression: compressing deep neural network with pruning, trained quantization and huffman coding. CoRR abs\/1510.00149 (2015)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-11018-5_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,22]],"date-time":"2023-01-22T01:21:29Z","timestamp":1674350489000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-11018-5_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030110178","9783030110185"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-11018-5_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"23 January 2019","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"}]}}