{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T17:50:19Z","timestamp":1769017819638,"version":"3.49.0"},"publisher-location":"Cham","reference-count":60,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012694","type":"print"},{"value":"9783030012700","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\/978-3-030-01270-0_23","type":"book-chapter","created":{"date-parts":[[2018,10,5]],"date-time":"2018-10-05T22:07:51Z","timestamp":1538777271000},"page":"388-404","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":69,"title":["Interaction-Aware Spatio-Temporal Pyramid Attention Networks for Action Classification"],"prefix":"10.1007","author":[{"given":"Yang","family":"Du","sequence":"first","affiliation":[]},{"given":"Chunfeng","family":"Yuan","sequence":"additional","affiliation":[]},{"given":"Bing","family":"Li","sequence":"additional","affiliation":[]},{"given":"Lili","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Yangxi","family":"Li","sequence":"additional","affiliation":[]},{"given":"Weiming","family":"Hu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"key":"23_CR1","unstructured":"Abu-El-Haija, S., et al.: Youtube-8m: a large-scale video classification benchmark. In: CoRR (2016)"},{"key":"23_CR2","unstructured":"Awad, G., et al.: Trecvid 2016: evaluating video search, video event detection, localization, and hyperlinking. In: TRECVID (2016)"},{"key":"23_CR3","unstructured":"Gorban, A., et al.: THUMOS challenge: Action recognition with a large number of classes. http:\/\/www.thumos.info\/ (2013)"},{"key":"23_CR4","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":"23_CR5","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":"23_CR6","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human actions classes from videos in the wild. In: CRCVTR-12-01 (2012)"},{"key":"23_CR7","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":"23_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"23_CR9","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)"},{"key":"23_CR10","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V.: Inception-v4, inception-resnet and the impact of residual connections on learning. arXiv preprint arXiv:1602.07261 (2016)","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"23_CR11","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS (2017)"},{"key":"23_CR12","unstructured":"Lin, Z., et al.: A structured self-attentive sentence embedding. In: ICLR (2017)"},{"key":"23_CR13","unstructured":"Sharma, S., Kiros, R., Salakhutdinov, R.: Action recognition using visual attention. arXiv preprint arXiv:1511.04119 (2016)"},{"key":"23_CR14","unstructured":"Li, Z., Gavves, E., Jain, M., Snoek, C.G.M.: Attends and flows for action recognition. In: arXiv preprint arXiv:1607.01794 (2016)"},{"key":"23_CR15","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"23_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. In: IEEE TPAMI (2015)","DOI":"10.1109\/TPAMI.2015.2389824"},{"key":"23_CR17","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Dollar, P., Girshick, R.: Feature pyramid networks for object detection. In: CVPR (2016)","DOI":"10.1109\/CVPR.2017.106"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Wang, H., Schmid, C.: Action recognition with improved trajectories. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.441"},{"key":"23_CR19","doi-asserted-by":"crossref","unstructured":"Wang, L., Qiao, Y., Tang, X.: Action recognition with trajectory-pooled deep-convolutional descriptors. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"23_CR20","doi-asserted-by":"crossref","unstructured":"Lowe, D.: Object recognition from local scale-invariant keypoints. In: ICCV (1999)","DOI":"10.1109\/ICCV.1999.790410"},{"key":"23_CR21","doi-asserted-by":"crossref","unstructured":"Laptev, I., Marszalek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: CVPR (2008)","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"23_CR22","unstructured":"Dalal, N., Triggs, B.: Histogram of oriented gradients for human detection. In: CVPR (2005)"},{"key":"23_CR23","doi-asserted-by":"crossref","unstructured":"Klaser, A., Marszalek, M., Schmid, C.: A spatio-temporal descriptor based on 3d-gradients. In: BMVC (2008)","DOI":"10.5244\/C.22.99"},{"key":"23_CR24","doi-asserted-by":"crossref","unstructured":"Dalal, N., Triggs, B., Schmid, C.: Human detection using oriented histograms of flow and appearance. In: ECCV (2006)","DOI":"10.1007\/11744047_33"},{"key":"23_CR25","doi-asserted-by":"crossref","unstructured":"Willems, G., Tuytelaars, T., Gool, L.J.V.: An efficient dense and scale-invariant spatio-temporal interest point detector. In: ECCV (2008)","DOI":"10.1007\/978-3-540-88688-4_48"},{"key":"23_CR26","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: NIPS (2014)"},{"key":"23_CR27","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":"23_CR28","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1007\/978-3-319-46484-8_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Limin Wang","year":"2016","unstructured":"Wang, L., et al.: Temporal segment networks: Towards good practices for deep action recognition. In: ECCV (2016)"},{"key":"23_CR29","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Wildes, R.: Spatiotemporal residual networks for video action recognition. In: NIPS (2016)","DOI":"10.1109\/CVPR.2017.787"},{"issue":"1","key":"23_CR30","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"Shuiwang Ji","year":"2013","unstructured":"Ji, S., Xu, W., Yang, M., Yu, K.: 3D convolutional neural networks for human action recognition. In: TPAMI 35(1) (2013)","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"23_CR31","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":"23_CR32","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":"23_CR33","unstructured":"Varol, G., Laptev, I., Schmid, C.: Long-term temporal convolutions for action recognition. In: CoRRarXiv (2016)"},{"key":"23_CR34","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"},{"issue":"2","key":"23_CR35","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1207\/s15516709cog1402_1","volume":"14","author":"Jeffrey L. Elman","year":"1990","unstructured":"Elman, J.L.: Finding structure in time. Cogn. Sci. 14(2), 179\u2013211 (1990)","journal-title":"Cognitive Science"},{"issue":"8","key":"23_CR36","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"Sepp Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Computation"},{"key":"23_CR37","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":"23_CR38","unstructured":"Ng, J.Y.H., Hausknecht, M., Vijayanarasimhan, S., Vinyals, O., Monga, R., Toderici, G.: Beyond short snippets: deep networks for video classification. In: CVPR (2015)"},{"key":"23_CR39","doi-asserted-by":"crossref","unstructured":"Girdhar, R., Ramanan, D., Gupta, A., Sivic, J., Russell, B.: Actionvlad: learning spatio-temporal aggregation for action classification. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.337"},{"key":"23_CR40","doi-asserted-by":"crossref","unstructured":"Diba, A., Sharma, V., Gool, L.V.: Deep temporal linear encoding networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.168"},{"key":"23_CR41","unstructured":"Mnih, V., Heess, N., Graves, A., et al.: Recurrent models of visual attention. In: NIPS (2014)"},{"key":"23_CR42","unstructured":"Ba, J., Mnih, V., Kavukcuoglu, K.: Multiple object recognition with visual attention. arXiv preprint arXiv:1412.7755 (2014)"},{"key":"23_CR43","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Girshick, R., Malik, J.: Contextual action recognition with R*CNN. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.129"},{"key":"23_CR44","doi-asserted-by":"crossref","unstructured":"Mallya, A., Lazebnik, S.: Learning models for actions and person-object interactions with transfer to question answering. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46448-0_25"},{"key":"23_CR45","unstructured":"Li, Z., Gavves, E., Jain, M., Snoek, C.G.M.: Videolstm convolves, attends and flows for action recognition. arXiv preprint arXiv:1607.01794 (2016)"},{"key":"23_CR46","unstructured":"Girdhar, R., Ramanan, D.: Attentional pooling for action recognition. In: NIPS (2017)"},{"key":"23_CR47","doi-asserted-by":"crossref","unstructured":"Long, X., Gan, C., Melo, G., Wu, J., Liu, X., Wen, S.: Attention clusters: purely attention based local feature integration for video classification. arXiv preprint arXiv:1711.09550 (2017)","DOI":"10.1109\/CVPR.2018.00817"},{"key":"23_CR48","doi-asserted-by":"crossref","unstructured":"Ma, C.Y., Kadav, A., Melvin, I., Kira, Z., AlRegib, G., Graf, H.P.: Attend and interact: higher-order object interactions for video understanding. arXiv preprint arXiv:1711.06330 (2017)","DOI":"10.1109\/CVPR.2018.00710"},{"key":"23_CR49","doi-asserted-by":"crossref","unstructured":"Jegou, H., Douze, M., Schmid, C., Perez, P.: Aggregating local descriptors into a compact image representation. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5540039"},{"key":"23_CR50","unstructured":"https:\/\/en.wikipedia.org\/wiki\/Principal_component_analysis"},{"key":"23_CR51","unstructured":"Yang, J., Zhang, D., Frangi, A.F., Yang, J.: Two-dimensional PCA: a new approach to appearance-based face representation and recognition. In: IEEE TPAMI (2004)"},{"key":"23_CR52","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: ICML (2015)"},{"key":"23_CR53","doi-asserted-by":"crossref","unstructured":"Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. In: IJCV (2015)","DOI":"10.1007\/s11263-015-0816-y"},{"key":"23_CR54","unstructured":"Wang, L., Xiong, Y., Wang, Z., Qiao, Y.: Towards good practices for very deep two-stream convnets. In: CoRR (2015)"},{"key":"23_CR55","unstructured":"Abadi, M., et al.: Tensorflow: Large-scale machine learning on heterogeneous systems. Software available from www.tensorflow.org (2015)"},{"key":"23_CR56","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":"23_CR57","doi-asserted-by":"crossref","unstructured":"Lev, G., Sadeh, G., Klein, B., Wolf, L.: RNN fisher vectors for action recognition and image annotation. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46466-4_50"},{"key":"23_CR58","doi-asserted-by":"crossref","unstructured":"Kar, A., Rai, N., Sikka, K., Sharma, G.: Adascan: adaptive scan pooling in deep convolutional neural networks for human action recognition in videos. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.604"},{"key":"23_CR59","doi-asserted-by":"crossref","unstructured":"Cai, Z., Wang, L., Peng, X., Qiao., Y.: Multi-view super vector for action recognition. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.83"},{"key":"23_CR60","unstructured":"https:\/\/github.com\/tensorflow\/models\/tree\/master\/research\/slim#pre-trained-models"}],"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\/978-3-030-01270-0_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,6]],"date-time":"2022-10-06T00:44:15Z","timestamp":1665017055000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01270-0_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012694","9783030012700"],"references-count":60,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01270-0_23","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":"6 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"}]}}