{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T16:16:04Z","timestamp":1761581764958,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030038397"},{"type":"electronic","value":"9783030038403"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-03840-3_28","type":"book-chapter","created":{"date-parts":[[2018,11,8]],"date-time":"2018-11-08T01:28:57Z","timestamp":1541640537000},"page":"375-386","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Top-Down Attention Recurrent VLAD Encoding for Action Recognition in Videos"],"prefix":"10.1007","author":[{"given":"Swathikiran","family":"Sudhakaran","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oswald","family":"Lanz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,11,9]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","key":"28_CR1","DOI":"10.1109\/CVPR.2016.90"},{"issue":"6","key":"28_CR2","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"doi-asserted-by":"crossref","unstructured":"Peng, C., Zhang, X., Yu, G., Luo, G., Sun, J.: Large kernel matters - improve semantic segmentation by global convolutional network. In: Proceedings of CVPR (2017)","key":"28_CR3","DOI":"10.1109\/CVPR.2017.189"},{"unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Conference on Neural Information Processing Systems (NIPS) (2014)","key":"28_CR4"},{"doi-asserted-by":"crossref","unstructured":"Wang, L., Qiao, Y., Tang, X.: Action recognition with trajectory-pooled deep-convolutional descriptors. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","key":"28_CR5","DOI":"10.1109\/CVPR.2015.7299059"},{"doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Wildes, R.: Spatiotemporal residual networks for video action recognition. In: Conference on Neural Information Processing Systems (NIPS) (2016)","key":"28_CR6","DOI":"10.1109\/CVPR.2017.787"},{"key":"28_CR7","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"},{"doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: IEEE International Conference on Computer Vision (ICCV) (2015)","key":"28_CR8","DOI":"10.1109\/ICCV.2015.510"},{"doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","key":"28_CR9","DOI":"10.1109\/CVPR.2017.502"},{"doi-asserted-by":"crossref","unstructured":"Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","key":"28_CR10","DOI":"10.1109\/CVPR.2015.7298878"},{"unstructured":"Sharma, S., Kiros, R., Salakhutdinov, R.: Action recognition using visual attention. In: NIPS Workshop on Time Series (2015)","key":"28_CR11"},{"doi-asserted-by":"crossref","unstructured":"Sudhakaran, S., Lanz, O.: Convolutional long short-term memory networks for recognizing first person interactions. In: IEEE International Conference on Computer Vision Workshops (ICCVW) (2017)","key":"28_CR12","DOI":"10.1109\/ICCVW.2017.276"},{"doi-asserted-by":"crossref","unstructured":"Sudhakaran, S., Lanz, O.: Learning to detect violent videos using convolutional long short-term memory. In: IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp. 1\u20136 (2017)","key":"28_CR13","DOI":"10.1109\/AVSS.2017.8078468"},{"doi-asserted-by":"crossref","unstructured":"Girdhar, R., Ramanan, D., Gupta, A., Sivic, J., Russell, B.: ActionVLAD: learning spatio-temporal aggregation for action classification. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","key":"28_CR14","DOI":"10.1109\/CVPR.2017.337"},{"unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning (ICML) (2015)","key":"28_CR15"},{"doi-asserted-by":"crossref","unstructured":"Teh, E.W., Rochan, M., Wang, Y.: Attention networks for weakly supervised object localization. In: British Machine Vision Conference (BMVC) (2016)","key":"28_CR16","DOI":"10.5244\/C.30.52"},{"unstructured":"Wang, W., Shen, J.: Deep visual attention prediction. arXiv preprint arXiv:1705.02544 (2017)","key":"28_CR17"},{"issue":"1","key":"28_CR18","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1146\/annurev.neuro.23.1.315","volume":"23","author":"S Kastner","year":"2000","unstructured":"Kastner, S., Ungerleider, L.G.: Mechanisms of visual attention in the human cortex. Ann. Rev. Neurosci. 23(1), 315\u2013341 (2000)","journal-title":"Ann. Rev. Neurosci."},{"doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","key":"28_CR19","DOI":"10.1109\/CVPR.2016.319"},{"doi-asserted-by":"crossref","unstructured":"J\u00e9gou, H., Douze, M., Schmid, C., P\u00e9rez, P.: Aggregating local descriptors into a compact image representation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2010)","key":"28_CR20","DOI":"10.1109\/CVPR.2010.5540039"},{"doi-asserted-by":"crossref","unstructured":"Arandjelovic, R., Gronat, P., Torii, A., Pajdla, T., Sivic, J.: NetVLAD: CNN architecture for weakly supervised place recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","key":"28_CR21","DOI":"10.1109\/CVPR.2016.572"},{"key":"28_CR22","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1016\/j.jvcir.2015.07.005","volume":"31","author":"T Kim","year":"2015","unstructured":"Kim, T., Kim, M.H.: Improving the search accuracy of the VLAD through weighted aggregation of local descriptors. J. Vis. Commun. Image Represent. 31, 237\u2013252 (2015)","journal-title":"J. Vis. Commun. Image Represent."},{"unstructured":"Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., Keutzer, K.: SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and<0.5\u00a0MB model size. arXiv preprint arXiv:1602.07360 (2016)","key":"28_CR23"},{"doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Weinberger, K.Q., van der Maaten, L.: Densely connected convolutional networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","key":"28_CR24","DOI":"10.1109\/CVPR.2017.243"},{"key":"28_CR25","doi-asserted-by":"publisher","first-page":"571","DOI":"10.1007\/978-3-642-33374-3_41","volume-title":"High Performance Computing in Science and Engineering 2012","author":"H Kuehne","year":"2013","unstructured":"Kuehne, H., Jhuang, H., Stiefelhagen, R., Serre, T.: HMDB51: a large video database for human motion recognition. In: Nagel, W., Kr\u00f6ner, D., Resch, M. (eds.) High Performance Computing in Science and Engineering 2012, pp. 571\u2013582. Springer, Berlin (2013). https:\/\/doi.org\/10.1007\/978-3-642-33374-3_41"},{"unstructured":"Chung, J., Gulcehre, C., Cho, K.H., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. In: Proceedings of the NIPS Workshop on Deep Learning (2014)","key":"28_CR26"},{"issue":"8","key":"28_CR27","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"doi-asserted-by":"crossref","unstructured":"Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1724\u20131734 (2014)","key":"28_CR28","DOI":"10.3115\/v1\/D14-1179"},{"doi-asserted-by":"crossref","unstructured":"Arandjelovic, R., Zisserman, A.: All about VLAD. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2013)","key":"28_CR29","DOI":"10.1109\/CVPR.2013.207"},{"unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)","key":"28_CR30"}],"container-title":["Lecture Notes in Computer Science","AI*IA 2018 \u2013 Advances in Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-03840-3_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,31]],"date-time":"2019-10-31T21:51:46Z","timestamp":1572558706000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-03840-3_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030038397","9783030038403"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-03840-3_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"AI*IA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference of the Italian Association for Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Trento","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"20 November 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 November 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aiia2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/aixia2018.fbk.eu\/index.php\/home\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"210","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"41","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"20% - 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"}},{"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"}},{"value":"2,5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}}]}}