{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T22:24:27Z","timestamp":1784413467985,"version":"3.55.0"},"publisher-location":"Cham","reference-count":56,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012663","type":"print"},{"value":"9783030012670","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\/978-3-030-01267-0_19","type":"book-chapter","created":{"date-parts":[[2018,10,6]],"date-time":"2018-10-06T17:02:36Z","timestamp":1538845356000},"page":"318-335","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":909,"title":["Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification"],"prefix":"10.1007","author":[{"given":"Saining","family":"Xie","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuowen","family":"Tu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kevin","family":"Murphy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,10,7]]},"reference":[{"key":"19_CR1","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS (2012)"},{"key":"19_CR2","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"19_CR3","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)"},{"key":"19_CR4","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":"19_CR5","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":"19_CR6","unstructured":"Kay, W., et al.: The kinetics human action video dataset. In: CVPR (2017)"},{"key":"19_CR7","doi-asserted-by":"crossref","unstructured":"Goyal, R., et al.: The something something video database for learning and evaluating visual common sense. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.622"},{"key":"19_CR8","doi-asserted-by":"crossref","unstructured":"Caba Heilbron, F., Escorcia, V., Ghanem, B., Niebles, J.C.: ActivityNet: A large-scale video benchmark for human activity understanding. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"19_CR9","doi-asserted-by":"crossref","unstructured":"Sigurdsson, G.A., Varol, G., Wang, X., Farhadi, A., Laptev, I., Gupta, A.: Hollywood in homes: crowdsourcing data collection for activity understanding. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"19_CR10","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":"19_CR11","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. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"19_CR12","doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: Deep learning with depthwise separable convolutions. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.195"},{"key":"19_CR13","unstructured":"Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications (2017). arXiv:1704.04861"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"19_CR15","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":"19_CR16","doi-asserted-by":"crossref","unstructured":"Sun, L., Jia, K., Yeung, D.Y., Shi, B.E.: Human action recognition using factorized spatio-temporal convolutional networks. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.522"},{"key":"19_CR17","unstructured":"Girdhar, R., Ramanan, D.: Attentional pooling for action recognition. In: NIPS (2017)"},{"key":"19_CR18","unstructured":"Dauphin, Y.N., Fan, A., Auli, M., Grangier, D.: Language modeling with gated convolutional networks. In: ICML (2017)"},{"key":"19_CR19","doi-asserted-by":"crossref","unstructured":"Perez, E., Strub, F., de Vries, H., Dumoulin, V., Courville, A.: Film: visual reasoning with a general conditioning layer. In: AAAI (2018)","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"19_CR20","doi-asserted-by":"crossref","unstructured":"Elfwing, S., Uchibe, E., Doya, K.: Sigmoid-weighted linear units for neural network function approximation in reinforcement learning. Neural Netw. (2018)","DOI":"10.1016\/j.neunet.2017.12.012"},{"key":"19_CR21","unstructured":"Ramachandran, P., Zoph, B., Le, Q.V.: Swish: a self-gated activation function (2017). arXiv:1710.05941"},{"key":"19_CR22","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"19_CR23","unstructured":"Miech, A., Laptev, I., Sivic, J.: Learnable pooling with context gating for video classification (2017). arXiv:1706.06905"},{"key":"19_CR24","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: INIPS (2014)"},{"key":"19_CR25","doi-asserted-by":"crossref","unstructured":"Bilen, H., Fernando, B., Gavves, E., Vedaldi, A., Gould, S.: Dynamic image networks for action recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.331"},{"key":"19_CR26","doi-asserted-by":"crossref","unstructured":"Bilen, H., Fernando, B., Gavves, E., Vedaldi, A.: Action recognition with dynamic image networks. IEEE PAMI (2017)","DOI":"10.1109\/TPAMI.2017.2769085"},{"key":"19_CR27","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Wildes, R.P.: Temporal residual networks for dynamic scene recognition. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.786"},{"key":"19_CR28","unstructured":"Wang, L., Xiong, Y., Wang, Z., Qiao, Y.: Towards good practices for very deep two-stream convnets (2015). arXiv:1507.02159"},{"key":"19_CR29","unstructured":"Ng, J.Y., Hausknecht, M.J., Vijayanarasimhan, S., Vinyals, O., Monga, R., Toderici, G.: Beyond short snippets: deep networks for video classification. In: CVPR (2015)"},{"key":"19_CR30","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":"19_CR31","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Wildes, R.: Spatiotemporal multiplier networks for video action recognition. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.787"},{"key":"19_CR32","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Wildes, R.P.: Spatiotemporal residual networks for video action recognition. In: NIPS (2016)","DOI":"10.1109\/CVPR.2017.787"},{"key":"19_CR33","doi-asserted-by":"crossref","unstructured":"Zolfaghari, M., Oliveira, G.L., Sedaghat, N., Brox, T.: Chained multi-stream networks exploiting pose, motion, and appearance for action classification and detection. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.316"},{"key":"19_CR34","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":"19_CR35","doi-asserted-by":"crossref","unstructured":"Wang, X., Farhadi, A., Gupta, A.: Actions transformations. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.291"},{"key":"19_CR36","doi-asserted-by":"crossref","unstructured":"Wang, L., Xiong, Y., Wang, Z., Qiao, Y., Lin, D., Tang, X., Van Gool, L.: Temporal segment networks: Towards good practices for deep action recognition. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"19_CR37","doi-asserted-by":"crossref","unstructured":"Pickup, L.C., et al.: Seeing the arrow of time. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.262"},{"key":"19_CR38","unstructured":"Maaten, L.V.D., Hinton, G.: Visualizing data using t-SNE. JMLR (2008)"},{"key":"19_CR39","doi-asserted-by":"crossref","unstructured":"Zhou, B., Andonian, A., Torralba, A.: Temporal relational reasoning in videos (2017). arXiv:1711.08496","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"19_CR40","unstructured":"Zach, C., Pock, T., Bischof, H.: A duality based approach for realtime tv-l1 optical flow. Pattern Recognit. (2007)"},{"key":"19_CR41","unstructured":"Bian, Y., et al.: Revisiting the effectiveness of off-the-shelf temporal modeling approaches for large-scale video classification (2017). arXiv:1708.03805"},{"key":"19_CR42","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":"19_CR43","doi-asserted-by":"crossref","unstructured":"Wang, L., Li, W., Li, W., Gool, L.V.: Appearance-and-relation networks for video classification. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00155"},{"key":"19_CR44","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: ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"19_CR45","unstructured":"Soomro, K., Zamir, A., Shah, M.: UCF101: a dataset of 101 human actions classes from videos in the wild. Technical Report CRCV-TR-12-01 (2012)"},{"key":"19_CR46","unstructured":"Tran, D., Bourdev, L.D., Fergus, R., Torresani, L., Paluri, M.: C3D: Generic features for video analysis (2014). arXiv:1412.0767"},{"key":"19_CR47","unstructured":"Tran, D., Ray, J., Shou, Z., Chang, S., Paluri, M.: Convnet architecture search for spatiotemporal feature learning (2017). arXiv:1708.05038"},{"key":"19_CR48","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"744","DOI":"10.1007\/978-3-319-46493-0_45","volume-title":"Computer Vision \u2013 ECCV 2016","author":"X Peng","year":"2016","unstructured":"Peng, X., Schmid, C.: Multi-region two-stream R-CNN for action detection. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 744\u2013759. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_45"},{"key":"19_CR49","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: Towards real-time object detection with region proposal networks. In: NIPS (2015)"},{"key":"19_CR50","doi-asserted-by":"crossref","unstructured":"Gu, C., et al.: AVA: A video dataset of spatio-temporally localized atomic visual actions. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00633"},{"key":"19_CR51","doi-asserted-by":"crossref","unstructured":"Jhuang, H., Gall, J., Zuffi, S., Schmid, C., Black, M.: Towards understanding action recognition. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.396"},{"key":"19_CR52","doi-asserted-by":"crossref","unstructured":"Saha, S., Sing, G., Cuzzolin, F.: AMTnet: Action-micro-tube regression by end-to-end trainable deep architecture. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.473"},{"key":"19_CR53","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Malik, J.: Finding action tubes. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298676"},{"key":"19_CR54","doi-asserted-by":"crossref","unstructured":"Huang, J., et al.: Speed\/accuracy trade-offs for modern convolutional object detectors. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.351"},{"key":"19_CR55","doi-asserted-by":"crossref","unstructured":"Weinzaepfel, P., Harchaoui, Z., Schmid, C.: Learning to track for spatio-temporal action localization. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.362"},{"key":"19_CR56","doi-asserted-by":"crossref","unstructured":"Kalogeiton, V., Weinzaepfel, P., Ferrari, V., Schmid, C.: Action tubelet detector for spatio-temporal action localization. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.472"}],"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\/978-3-030-01267-0_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,6]],"date-time":"2022-10-06T00:16:01Z","timestamp":1665015361000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01267-0_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012663","9783030012670"],"references-count":56,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01267-0_19","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":"7 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"}]}}