{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T08:59:35Z","timestamp":1767085175967,"version":"3.40.3"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030012274"},{"type":"electronic","value":"9783030012281"}],"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\/978-3-030-01228-1_9","type":"book-chapter","created":{"date-parts":[[2018,10,6]],"date-time":"2018-10-06T05:03:51Z","timestamp":1538802231000},"page":"139-155","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":38,"title":["Fine-Grained Video Categorization with Redundancy Reduction Attention"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3103-8752","authenticated-orcid":false,"given":"Chen","family":"Zhu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9162-8570","authenticated-orcid":false,"given":"Xiao","family":"Tan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1132-5877","authenticated-orcid":false,"given":"Feng","family":"Zhou","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5689-9786","authenticated-orcid":false,"given":"Xiao","family":"Liu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1820-3223","authenticated-orcid":false,"given":"Kaiyu","family":"Yue","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1867-5378","authenticated-orcid":false,"given":"Errui","family":"Ding","sequence":"additional","affiliation":[]},{"given":"Yi","family":"Ma","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"key":"9_CR1","doi-asserted-by":"crossref","unstructured":"Cai, S., Zuo, W., Zhang, L.: Higher-order integration of hierarchical convolutional activations for fine-grained visual categorization. In: The IEEE International Conference on Computer Vision (ICCV), October 2017","DOI":"10.1109\/ICCV.2017.63"},{"key":"9_CR2","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. arXiv preprint arXiv:1705.07750 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"9_CR3","doi-asserted-by":"crossref","unstructured":"Caba Heilbron, F., Escorcia, V., Ghanem, B., Carlos Niebles, J.: ActivityNet: a large-scale video benchmark for human activity understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 961\u2013970 (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"9_CR4","doi-asserted-by":"crossref","unstructured":"Fu, J., Zheng, H., Mei, T.: Look closer to see better: recurrent attention convolutional neural network for fine-grained image recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017","DOI":"10.1109\/CVPR.2017.476"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"Fukui, A., Park, D.H., Yang, D., Rohrbach, A., Darrell, T., Rohrbach, M.: Multimodal compact bilinear pooling for visual question answering and visual grounding. arXiv preprint arXiv:1606.01847 (2016)","DOI":"10.18653\/v1\/D16-1044"},{"key":"9_CR6","doi-asserted-by":"crossref","unstructured":"Gebru, T., Hoffman, J., Fei-Fei, L.: Fine-grained recognition in the wild: a multi-task domain adaptation approach. In: The IEEE International Conference on Computer Vision (ICCV), October 2017","DOI":"10.1109\/ICCV.2017.151"},{"key":"9_CR7","unstructured":"Girdhar, R., Ramanan, D.: Attentional pooling for action recognition. In: Advances in Neural Information Processing Systems, pp. 34\u201345 (2017)"},{"key":"9_CR8","doi-asserted-by":"crossref","unstructured":"Hara, K., Kataoka, H., Satoh, Y.: Learning spatio-temporal features with 3D residual networks for action recognition. arXiv preprint arXiv:1708.07632 (2017)","DOI":"10.1109\/ICCVW.2017.373"},{"key":"9_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"9_CR10","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. arXiv preprint arXiv:1709.01507 (2017)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"9_CR11","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 448\u2013456 (2015)"},{"key":"9_CR12","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., et al.: Spatial transformer networks. In: Advances in Neural Information Processing Systems, pp. 2017\u20132025 (2015)"},{"issue":"1","key":"9_CR13","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"S Ji","year":"2013","unstructured":"Ji, S., Xu, W., Yang, M., Yu, K.: 3D convolutional neural networks for human action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35(1), 221\u2013231 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"9_CR14","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: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017","DOI":"10.1109\/CVPR.2017.604"},{"key":"9_CR15","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 conference on Computer Vision and Pattern Recognition, pp. 1725\u20131732 (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"9_CR16","unstructured":"Kay, W., et al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"9_CR17","unstructured":"Kingma, D., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"9_CR18","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3D object representations for fine-grained categorization. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 554\u2013561 (2013)","DOI":"10.1109\/ICCVW.2013.77"},{"key":"9_CR19","unstructured":"Larochelle, H., Hinton, G.E.: Learning to combine foveal glimpses with a third-order Boltzmann machine. In: Advances in Neural Information Processing Systems, pp. 1243\u20131251 (2010)"},{"key":"9_CR20","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1016\/j.cviu.2017.10.011","volume":"166","author":"Z Li","year":"2017","unstructured":"Li, Z., Gavrilyuk, K., Gavves, E., Jain, M., Snoek, C.G.: VideoLSTM convolves, attends and flows for action recognition. Comput. Vis. Image Underst. 166, 41\u201350 (2017)","journal-title":"Comput. Vis. Image Underst."},{"key":"9_CR21","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., RoyChowdhury, A., Maji, S.: Bilinear CNN models for fine-grained visual recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1449\u20131457 (2015)","DOI":"10.1109\/ICCV.2015.170"},{"key":"9_CR22","doi-asserted-by":"crossref","unstructured":"Long, X., Gan, C., de Melo, G., Wu, J., Liu, X., Wen, S.: Attention clusters: purely attention based local feature integration for video classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7834\u20137843 (2018)","DOI":"10.1109\/CVPR.2018.00817"},{"key":"9_CR23","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":"9_CR24","doi-asserted-by":"crossref","unstructured":"Qiu, Z., Yao, T., Mei, T.: Learning spatio-temporal representation with pseudo-3D residual networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5533\u20135541 (2017)","DOI":"10.1109\/ICCV.2017.590"},{"key":"9_CR25","doi-asserted-by":"crossref","unstructured":"Saito, T., Kanezaki, A., Harada, T.: IBC127: video dataset for fine-grained bird classification. In: 2016 IEEE International Conference on Multimedia and Expo (ICME), pp. 1\u20136. IEEE (2016)","DOI":"10.1109\/ICME.2016.7552915"},{"key":"9_CR26","unstructured":"Sharma, S., Kiros, R., Salakhutdinov, R.: Action recognition using visual attention. arXiv preprint arXiv:1511.04119 (2015)"},{"key":"9_CR27","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Advances in Neural Information Processing Systems, pp. 568\u2013576 (2014)"},{"key":"9_CR28","doi-asserted-by":"crossref","unstructured":"Sun, L., Jia, K., Chen, K., Yeung, D.Y., Shi, B.E., Savarese, S.: Lattice long short-term memory for human action recognition. arXiv preprint arXiv:1708.03958 (2017)","DOI":"10.1109\/ICCV.2017.236"},{"key":"9_CR29","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"9_CR30","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The Caltech-UCSD Birds-200-2011 dataset. Technical report (2011)"},{"key":"9_CR31","doi-asserted-by":"crossref","unstructured":"Wang, H., Schmid, C.: Action recognition with improved trajectories. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3551\u20133558 (2013)","DOI":"10.1109\/ICCV.2013.441"},{"key":"9_CR32","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":"9_CR33","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057 (2015)"},{"key":"9_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: SPDA-CNN: unifying semantic part detection and abstraction for fine-grained recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1143\u20131152 (2016)","DOI":"10.1109\/CVPR.2016.129"},{"key":"9_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1007\/978-3-319-10590-1_54","volume-title":"Computer Vision \u2013 ECCV 2014","author":"N Zhang","year":"2014","unstructured":"Zhang, N., Donahue, J., Girshick, R., Darrell, T.: Part-based R-CNNs for fine-grained category detection. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 834\u2013849. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10590-1_54"},{"key":"9_CR36","doi-asserted-by":"crossref","unstructured":"Zheng, H., Fu, J., Mei, T., Luo, J.: Learning multi-attention convolutional neural network for fine-grained image recognition. In: The IEEE International Conference on Computer Vision (ICCV), October 2017","DOI":"10.1109\/ICCV.2017.557"},{"key":"9_CR37","doi-asserted-by":"crossref","unstructured":"Zhu, W., Hu, J., Sun, G., Cao, X., Qiao, Y.: A key volume mining deep framework for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1991\u20131999 (2016)","DOI":"10.1109\/CVPR.2016.219"}],"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\/978-3-030-01228-1_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,6]],"date-time":"2022-10-06T00:24:28Z","timestamp":1665015868000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01228-1_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012274","9783030012281"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01228-1_9","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":"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"}]}}