{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T12:03:30Z","timestamp":1742990610240,"version":"3.40.3"},"publisher-location":"Cham","reference-count":20,"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_21","type":"book-chapter","created":{"date-parts":[[2019,1,24]],"date-time":"2019-01-24T05:50:50Z","timestamp":1548309050000},"page":"229-238","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Learnable Pooling Methods for Video Classification"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3116-5302","authenticated-orcid":false,"given":"Sebastian","family":"Kmiec","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7600-9560","authenticated-orcid":false,"given":"Juhan","family":"Bae","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2102-0209","authenticated-orcid":false,"given":"Ruijian","family":"An","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,1,23]]},"reference":[{"key":"21_CR1","unstructured":"Abu-El-Haija, S., et al.: Youtube-8m: a large-scale video classification benchmark. arXiv:1609.08675 (2016). https:\/\/arxiv.org\/pdf\/1609.08675v1.pdf"},{"issue":"6","key":"21_CR2","doi-asserted-by":"publisher","first-page":"1437","DOI":"10.1109\/TPAMI.2017.2711011","volume":"40","author":"R Arandjelovi\u0107","year":"2018","unstructured":"Arandjelovi\u0107, R., Gronat, P., Torii, A., Pajdla, T., Sivic, J.: Netvlad: CNN architecture for weakly supervised place recognition. IEEE Trans. Pattern Anal. Mach. Intell. 40(6), 1437\u20131451 (2018). https:\/\/doi.org\/10.1109\/TPAMI.2017.2711011","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"21_CR3","unstructured":"Bian, Y., et al.: Revisiting the effectiveness of off-the-shelf temporal modeling approaches for large-scale video classification. arXiv preprint arXiv:1708.03805 (2017)"},{"key":"21_CR4","unstructured":"Brock, A., Lim, T., Ritchie, J.M., Weston, N.: Neural photo editing with introspective adversarial networks. CoRR abs\/1609.07093 (2016). http:\/\/arxiv.org\/abs\/1609.07093"},{"key":"21_CR5","doi-asserted-by":"publisher","unstructured":"Do, T., Tran, Q.D., Cheung, N.: Faemb: a function approximation-based embedding method for image retrieval. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, MA, USA, 7\u201312 June 2015, pp. 3556\u20133564 (2015). https:\/\/doi.org\/10.1109\/CVPR.2015.7298978","DOI":"10.1109\/CVPR.2015.7298978"},{"key":"21_CR6","unstructured":"Girdhar, R., Ramanan, D., Gupta, A., Sivic, J., Russell, B.: Actionvlad: Learning spatio-temporal aggregation for action classification"},{"key":"21_CR7","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. CoRR abs\/1512.03385 (2015). http:\/\/arxiv.org\/abs\/1512.03385"},{"issue":"9","key":"21_CR8","doi-asserted-by":"publisher","first-page":"1704","DOI":"10.1109\/TPAMI.2011.235","volume":"34","author":"H J\u00e9gou","year":"2012","unstructured":"J\u00e9gou, H., Perronnin, F., Douze, M., S\u00e1nchez, J., P\u00e9rez, P., Schmid, C.: Aggregating local image descriptors into compact codes. IEEE Trans. Pattern Anal. Mach. Intell. 34(9), 1704\u20131716 (2012). https:\/\/doi.org\/10.1109\/TPAMI.2011.235","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"21_CR9","doi-asserted-by":"publisher","unstructured":"J\u00e9gou, H., Zisserman, A.: Triangulation embedding and democratic aggregation for image search. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014, Columbus, OH, USA, 23\u201328 June 2014, pp. 3310\u20133317 (2014). https:\/\/doi.org\/10.1109\/CVPR.2014.417","DOI":"10.1109\/CVPR.2014.417"},{"key":"21_CR10","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. CoRR abs\/1412.6980 (2014). http:\/\/arxiv.org\/abs\/1412.6980"},{"key":"21_CR11","unstructured":"Long, X., Gan, C., de Melo, G., Wu, J., Liu, X., Wen, S.: Attention clusters: purely attention based local feature integration for video classification. CoRR abs\/1711.09550 (2017). http:\/\/arxiv.org\/abs\/1711.09550"},{"key":"21_CR12","unstructured":"Miech, A., Laptev, I., Sivic, J.: Learnable pooling with context gating for video classification. CoRR abs\/1706.06905 (2017). http:\/\/arxiv.org\/abs\/1706.06905"},{"issue":"2","key":"21_CR13","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1162\/neco.1994.6.2.181","volume":"6","author":"MI Jordan","year":"1994","unstructured":"Jordan, M.I., Jacobs, R.A.: Hierarchical mixtures of experts and the EM algorithm. Neural Comput. 6(2), 181\u2013214 (1994). https:\/\/doi.org\/10.1162\/neco.1994.6.2.181","journal-title":"Neural Comput."},{"key":"21_CR14","doi-asserted-by":"crossref","unstructured":"Radenovic, F., Iscen, A., Tolias, G., Avrithis, Y., Chum, O.: Revisiting oxford and paris: large-scale image retrieval benchmarking. In: IEEE Computer Vision and Pattern Recognition Conference (2018)","DOI":"10.1109\/CVPR.2018.00598"},{"key":"21_CR15","doi-asserted-by":"crossref","unstructured":"Radenovic, F., Iscen, A., Tolias, G., Avrithis, Y.S., Chum, O.: Revisiting oxford and paris: large-scale image retrieval benchmarking. CoRR abs\/1803.11285 (2018). http:\/\/arxiv.org\/abs\/1803.11285","DOI":"10.1109\/CVPR.2018.00598"},{"issue":"3","key":"21_CR16","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1007\/s11263-015-0810-4","volume":"116","author":"G Tolias","year":"2016","unstructured":"Tolias, G., Avrithis, Y., J\u00e9gou, H.: Image search with selective match kernels: aggregation across single and multiple images. Int. J. Comput. Vis. 116(3), 247\u2013261 (2016)","journal-title":"Int. J. Comput. Vis."},{"key":"21_CR17","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, Long Beach, CA, USA, 4\u20139 December 2017, pp. 6000\u20136010 (2017). http:\/\/papers.nips.cc\/paper\/7181-attention-is-all-you-need"},{"key":"21_CR18","unstructured":"Xie, S., Sun, C., Huang, J., Tu, Z., Murphy, K.: Rethinking spatiotemporal feature learning for video understanding. arXiv preprint arXiv:1712.04851 (2017)"},{"key":"21_CR19","unstructured":"Yu, K., Zhang, T.: Improved local coordinate coding using local tangents. In: Proceedings of the 27th International Conference on Machine Learning (ICML 2010), Haifa, Israel, 21\u201324 June 2010, pp. 1215\u20131222 (2010). http:\/\/www.icml2010.org\/papers\/454.pdf"},{"key":"21_CR20","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Wang, J., Xie, L., Zheng, L.: Attention-based pyramid aggregation network for visual place recognition. arXiv preprint arXiv:1808.00288 (2018)","DOI":"10.1145\/3240508.3240525"}],"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_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,22]],"date-time":"2023-01-22T01:20:36Z","timestamp":1674350436000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-11018-5_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030110178","9783030110185"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-11018-5_21","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"}]}}