{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T14:21:19Z","timestamp":1770819679458,"version":"3.50.1"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585976","type":"print"},{"value":"9783030585983","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\/978-3-030-58598-3_27","type":"book-chapter","created":{"date-parts":[[2020,11,6]],"date-time":"2020-11-06T16:03:52Z","timestamp":1604678632000},"page":"449-465","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":27,"title":["AttentionNAS: Spatiotemporal Attention Cell Search for Video Classification"],"prefix":"10.1007","author":[{"given":"Xiaofang","family":"Wang","sequence":"first","affiliation":[]},{"given":"Xuehan","family":"Xiong","sequence":"additional","affiliation":[]},{"given":"Maxim","family":"Neumann","sequence":"additional","affiliation":[]},{"given":"AJ","family":"Piergiovanni","sequence":"additional","affiliation":[]},{"given":"Michael S.","family":"Ryoo","sequence":"additional","affiliation":[]},{"given":"Anelia","family":"Angelova","sequence":"additional","affiliation":[]},{"given":"Kris M.","family":"Kitani","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Hua","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,7]]},"reference":[{"key":"27_CR1","unstructured":"Baker, B., Gupta, O., Naik, N., Raskar, R.: Designing neural network architectures using reinforcement learning. In: ICLR (2017)"},{"key":"27_CR2","doi-asserted-by":"crossref","unstructured":"Bello, I., Zoph, B., Vaswani, A., Shlens, J., Le, Q.V.: Attention augmented convolutional networks. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00338"},{"key":"27_CR3","unstructured":"Cao, S., Wang, X., Kitani, K.M.: Learnable embedding space for efficient neural architecture compression. In: ICLR (2019)"},{"key":"27_CR4","unstructured":"Carreira, J., Noland, E., Banki-Horvath, A., Hillier, C., Zisserman, A.: A short note about kinetics-600. arXiv preprint arXiv:1808.01340 (2018)"},{"key":"27_CR5","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"27_CR6","doi-asserted-by":"crossref","unstructured":"Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. In: CVPR (2015)","DOI":"10.21236\/ADA623249"},{"key":"27_CR7","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"27_CR8","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Zisserman, A.: Convolutional two-stream network fusion for video action recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.213"},{"key":"27_CR9","doi-asserted-by":"crossref","unstructured":"He, D., et al.: StNET: local and global spatial-temporal modeling for action recognition. In: AAAI (2019)","DOI":"10.1609\/aaai.v33i01.33018401"},{"key":"27_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"27_CR11","unstructured":"Kandasamy, K., Neiswanger, W., Schneider, J., Poczos, B., Xing, E.P.: Neural architecture search with Bayesian optimisation and optimal transport. In: NeurIPS (2018)"},{"key":"27_CR12","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NeurIPS (2012)"},{"key":"27_CR13","unstructured":"Li, L., Talwalkar, A.: Random search and reproducibility for neural architecture search. In: UAI (2019)"},{"key":"27_CR14","doi-asserted-by":"crossref","unstructured":"Liu, C., et al.: Auto-deeplab: hierarchical neural architecture search for semantic image segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00017"},{"key":"27_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/978-3-030-01246-5_2","volume-title":"Computer Vision \u2013 ECCV 2018","author":"C Liu","year":"2018","unstructured":"Liu, C.: Progressive neural architecture search. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 19\u201335. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01246-5_2"},{"key":"27_CR16","unstructured":"Liu, H., Simonyan, K., Yang, Y.: DARTS: differentiable architecture search. In: ICLR (2019)"},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Liu, X., Lee, J.Y., Jin, H.: Learning video representations from correspondence proposals. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00440"},{"key":"27_CR18","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. TPAMI 42, 502\u2013508 (2019)","journal-title":"TPAMI"},{"key":"27_CR19","unstructured":"Park, J., Woo, S., Lee, J.Y., Kweon, I.S.: Bam: bottleneck attention module. In: BMVC (2018)"},{"key":"27_CR20","doi-asserted-by":"crossref","unstructured":"Qiu, Z., Yao, T., Mei, T.: Learning spatio-temporal representation with pseudo-3D residual networks. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.590"},{"key":"27_CR21","doi-asserted-by":"crossref","unstructured":"Real, E., Aggarwal, A., Huang, Y., Le, Q.V.: Regularized evolution for image classifier architecture search. In: AAAI (2019)","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"27_CR22","unstructured":"Real, E., et al.: Large-scale evolution of image classifiers. In: ICML (2017)"},{"key":"27_CR23","unstructured":"Ryoo, M.S., Piergiovanni, A., Tan, M., Angelova, A.: Assemblenet: searching for multi-stream neural connectivity in video architectures. In: ICLR (2020)"},{"key":"27_CR24","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: NeurIPS (2014)"},{"key":"27_CR25","unstructured":"Snoek, J., Larochelle, H., Adams, R.P.: Practical Bayesian optimization of machine learning algorithms. In: NeurIPS (2012)"},{"key":"27_CR26","unstructured":"Srinivas, N., Krause, A., Kakade, S.M., Seeger, M.W.: Gaussian process optimization in the bandit setting: no regret and experimental design. In: ICML (2009)"},{"key":"27_CR27","doi-asserted-by":"crossref","unstructured":"Stroud, J., Ross, D., Sun, C., Deng, J., Sukthankar, R.: D3d: Distilled 3D networks for video action recognition. In: WACV (2020)","DOI":"10.1109\/WACV45572.2020.9093274"},{"key":"27_CR28","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"27_CR29","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"27_CR30","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"27_CR31","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":"27_CR32","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"27_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-01234-2_1","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Woo","year":"2018","unstructured":"Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 3\u201319. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_1"},{"key":"27_CR34","doi-asserted-by":"crossref","unstructured":"Xie, L., Yuille, A.: Genetic CNN. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.154"},{"key":"27_CR35","doi-asserted-by":"crossref","unstructured":"Xie, S., Kirillov, A., Girshick, R., He, K.: Exploring randomly wired neural networks for image recognition. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00137"},{"key":"27_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1007\/978-3-030-01267-0_19","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Xie","year":"2018","unstructured":"Xie, S., Sun, C., Huang, J., Tu, Z., Murphy, K.: Rethinking spatiotemporal feature learning: speed-accuracy trade-offs in video classification. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11219, pp. 318\u2013335. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01267-0_19"},{"key":"27_CR37","unstructured":"Yu, K., Sciuto, C., Jaggi, M., Musat, C., Salzmann, M.: Evaluating the search phase of neural architecture search. In: ICLR (2020)"},{"key":"27_CR38","doi-asserted-by":"crossref","unstructured":"Yue-Hei Ng, J., Hausknecht, M., Vijayanarasimhan, S., Vinyals, O., Monga, R., Toderici, G.: Beyond short snippets: Deep networks for video classification. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"27_CR39","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Yan, J., Wu, W., Shao, J., Liu, C.L.: Practical block-wise neural network architecture generation. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00257"},{"key":"27_CR40","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"831","DOI":"10.1007\/978-3-030-01246-5_49","volume-title":"Computer Vision \u2013 ECCV 2018","author":"B Zhou","year":"2018","unstructured":"Zhou, B., Andonian, A., Oliva, A., Torralba, A.: Temporal relational reasoning in videos. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 831\u2013846. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01246-5_49"},{"key":"27_CR41","unstructured":"Zoph, B., Le, Q.V.: Neural architecture search with reinforcement learning. In: ICLR (2017)"},{"key":"27_CR42","doi-asserted-by":"crossref","unstructured":"Zoph, B., Vasudevan, V., Shlens, J., Le, Q.V.: Learning transferable architectures for scalable image recognition. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00907"}],"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\/978-3-030-58598-3_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T00:31:50Z","timestamp":1730853110000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58598-3_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585976","9783030585983"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58598-3_27","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":"7 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.","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)"}}]}}