{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T07:31:49Z","timestamp":1751355109320,"version":"3.40.3"},"publisher-location":"Cham","reference-count":26,"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_18","type":"book-chapter","created":{"date-parts":[[2019,1,24]],"date-time":"2019-01-24T05:50:50Z","timestamp":1548309050000},"page":"193-205","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["The 2nd YouTube-8M Large-Scale Video Understanding Challenge"],"prefix":"10.1007","author":[{"given":"Joonseok","family":"Lee","sequence":"first","affiliation":[]},{"given":"Apostol","family":"Natsev","sequence":"additional","affiliation":[]},{"given":"Walter","family":"Reade","sequence":"additional","affiliation":[]},{"given":"Rahul","family":"Sukthankar","sequence":"additional","affiliation":[]},{"given":"George","family":"Toderici","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,1,23]]},"reference":[{"key":"18_CR1","unstructured":"Abu-El-Haija, S., et al.: Youtube-8M: A large-scale video classification benchmark (2016). arXiv preprint: arXiv:1609.08675"},{"key":"18_CR2","unstructured":"Aliev, V., et al.: Label denoising with large ensembles of heterogeneous neural networks. In: Proceedings of the 2nd Workshop on YouTube-8M Large-Scale Video Understanding (2018)"},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Arandjelovic, R., Gronat, P., Torii, A., Pajdla, T., Sivic, J.: Netvlad: CNN architecture for weakly supervised place recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.572"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Araujo, A., Negrevergne, B., Chevaleyre, Y., Atif, J.: Training compact deep learning models for video classification using circulant matrices. In: Proceedings of the 2nd Workshop on YouTube-8M Large-Scale Video Understanding (2018)","DOI":"10.1007\/978-3-030-11018-5_25"},{"key":"18_CR5","unstructured":"Bober-Irizar, M., Husain, S., Ong, E.J., Bober, M.: Cultivating DNN diversity for large scale video labelling. In: Proceedings of the CVPR Workshop on YouTube-8M Large-Scale Video Understanding (2017)"},{"key":"18_CR6","unstructured":"Chen, S., Wang, X., Tang, Y., Chen, X., Wu, Z., Jiang, Y.G.: Aggregating frame-level features for large-scale video classification. In: Proceedings of the CVPR Workshop on YouTube-8M Large-Scale Video Understanding (2017)"},{"key":"18_CR7","unstructured":"Cho, C., et al.: Axon AI\u2019s solution to the 2nd Youtube-8M video understanding challenge. In: Proceedings of the 2nd Workshop on YouTube-8M Large-Scale Video Understanding (2018)"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"18_CR9","unstructured":"Garg, S.: Learning video features for multi-label classification. In: Proceedings of the 2nd Workshop on YouTube-8M Large-Scale Video Understanding (2018)"},{"key":"18_CR10","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network (2015). arXiv preprint: arXiv:1503.02531"},{"key":"18_CR11","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 international conference on Computer Vision and Pattern Recognition (CVPR) (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"18_CR12","unstructured":"Kim, E.S., et al.: Temporal attention mechanism with conditional inference for large-scale multi-label video classification. In: Proceedings of the 2nd Workshop on YouTube-8M Large-Scale Video Understanding (2018)"},{"key":"18_CR13","unstructured":"Kmiec, S., Bae, J.: Learnable pooling methods for video classification. In: Proceedings of the 2nd Workshop on YouTube-8M Large-Scale Video Understanding (2018)"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Lee, J., Abu-El-Haija, S., Varadarajan, B., Natsev, A.: Collaborative deep metric learning for video understanding. In: Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2018)","DOI":"10.1145\/3219819.3219856"},{"key":"18_CR15","unstructured":"Li, F., et al.: Temporal modeling approaches for large-scale Youtube-8M video understanding. In: Proceedings of the CVPR Workshop on YouTube-8M Large-Scale Video Understanding (2017)"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Lin, R., Xiao, J., Fan, J.: NeXtVLAD: an efficient neural network to aggregate frame-level features for large-scale video classification. In: Proceedings of the 2nd Workshop on YouTube-8M Large-Scale Video Understanding (2018)","DOI":"10.1007\/978-3-030-11018-5_19"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Liu, T., Liu, B.: Constrained-size tensorflow models for Youtube-8M video understanding challenge. In: Proceedings of the 2nd Workshop on YouTube-8M Large-Scale Video Understanding (2018)","DOI":"10.1007\/978-3-030-11018-5_22"},{"key":"18_CR18","unstructured":"Miech, A., Laptev, I., Sivic, J.: Learnable pooling with context gating for video classification. In: Proceedings of the CVPR Workshop on YouTube-8M Large-Scale Video Understanding (2017)"},{"key":"18_CR19","unstructured":"Na, S., Yu, Y., Lee, S., Kim, J., Kim, G.: Encoding video and label priors for multi-label video classification on Youtube-8M dataset. In: Proceedings of the CVPR Workshop on YouTube-8M Large-Scale Video Understanding (2017)"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Shin, K., Jeon, J., Lee, S.: Approach for video classification with multi-label on Youtube-8M dataset. In: Proceedings of the 2nd Workshop on YouTube-8M Large-Scale Video Understanding (2018)","DOI":"10.1007\/978-3-030-11018-5_29"},{"key":"18_CR21","unstructured":"Skalic, M., Austin, D.: Building a size constrained predictive model for video classification. In: Proceedings of the 2nd Workshop on YouTube-8M Large-Scale Video Understanding (2018)"},{"key":"18_CR22","unstructured":"Skalic, M., Pekalski, M., Pan, X.E.: Deep learning methods for efficient large scale video labeling. In: Proceedings of the CVPR Workshop on YouTube-8M Large-Scale Video Understanding (2017)"},{"key":"18_CR23","unstructured":"Tang, Y., Zhang, X., Wang, J., Chen, S., Ma, L., Jiang, Y.G.: Non-local netVLAD encoding for video classification. In: Proceedings of the 2nd Workshop on YouTube-8M Large-Scale Video Understanding (2018)"},{"key":"18_CR24","unstructured":"Wang, H.D., Zhang, T., Wu, J.: The monkeytyping solution to the Youtube-8M video understanding challenge. In: Proceedings of the CVPR Workshop on YouTube-8M Large-Scale Video Understanding (2017)"},{"key":"18_CR25","unstructured":"Zhu, L., Liu, Y., Yang, Y.: UTS submission to Google Youtube-8M challenge 2017. In: Proceedings of the CVPR Workshop on YouTube-8M Large-Scale Video Understanding (2017)"},{"key":"18_CR26","unstructured":"Zou, H., Xu, K., Li, J., Zhu, J.: The Youtube-8M kaggle competition: challenges and methods. In: Proceedings of the CVPR Workshop on YouTube-8M Large-Scale Video Understanding (2017)"}],"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_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,22]],"date-time":"2023-01-22T01:19:33Z","timestamp":1674350373000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-11018-5_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030110178","9783030110185"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-11018-5_18","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"}]}}