{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T03:16:02Z","timestamp":1743131762108,"version":"3.40.3"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031160745"},{"type":"electronic","value":"9783031160752"}],"license":[{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-16075-2_36","type":"book-chapter","created":{"date-parts":[[2022,8,31]],"date-time":"2022-08-31T10:02:42Z","timestamp":1661940162000},"page":"508-519","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Hard Samples Make Difference: An Improved Training Procedure for Video Action Recognition Tasks"],"prefix":"10.1007","author":[{"given":"Alexander","family":"Zarichkovyi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Inna V.","family":"Stetsenko","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,9,1]]},"reference":[{"issue":"3","key":"36_CR1","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vision"},{"key":"36_CR2","unstructured":"Papers with Code http:\/\/paperswithcode.com\/task\/image-classification Accessed 11 Feb 2022"},{"issue":"7553","key":"36_CR3","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y Lecun","year":"2015","unstructured":"Lecun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436\u2013444 (2015)","journal-title":"Nature"},{"key":"36_CR4","unstructured":"Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press http:\/\/www.deeplearningbook.org (2016)"},{"issue":"11","key":"36_CR5","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P., et al.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"36_CR6","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing systems, pp.1097\u20131105 (2012)"},{"key":"36_CR7","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR, vol. abs\/1409.1556 http:\/\/arxiv.org\/abs\/1409.1556 (2014)"},{"key":"36_CR8","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., et al.: Going deeper with convolutions. In: The IEEE Conference on Computer Vision and Pattern Recognition (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"36_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"36_CR10","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700\u20134708 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"36_CR11","doi-asserted-by":"crossref","unstructured":"Lin, T., Goyal, P., Girshick, R., et al.: Focal loss for dense object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence (2018)","DOI":"10.1109\/ICCV.2017.324"},{"key":"36_CR12","doi-asserted-by":"publisher","unstructured":"Nguyen, X., Hu, Y., Ahmad Amin, M., et al.: Detecting video inter-frame forgeries based on convolutional neural network model. International Journal of Image, Graphics and Signal Processing (IJIGSP) 12(3), 1\u201312 (2020). https:\/\/doi.org\/10.5815\/ijigsp.2020.03.01","DOI":"10.5815\/ijigsp.2020.03.01"},{"key":"36_CR13","doi-asserted-by":"publisher","unstructured":"Aung, M., Khaing, P., San, M.: Study for license plate detection. International Journal of Image, Graphics and Signal Processing (IJIGSP) 11(12), 39\u201346 (2019). https:\/\/doi.org\/10.5815\/ijigsp.2019.12.05","DOI":"10.5815\/ijigsp.2019.12.05"},{"key":"36_CR14","doi-asserted-by":"publisher","unstructured":"AL-Alimi, D, Shao, Y., Alalimi, A., Abdu, A.: Mask R-CNN for geospatial object detection. Int. J. Inf. Technol. Computer Sci.(IJITCS) 12(5), 63\u201372 (2020). https:\/\/doi.org\/10.5815\/ijitcs.2020.05.05","DOI":"10.5815\/ijitcs.2020.05.05"},{"key":"36_CR15","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., et al.: Vivit: A video vision transformer. CoRR, vol. abs\/2103.15691 (2021). http:\/\/arxiv.org\/abs\/2103.15691","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"36_CR16","unstructured":"Bao, H., Dong, L., Wei, F., et al.: Unilmv2: Pseudo-masked language models for unified language model pre-training. International Conference on Machine Learning, pp. 642\u2013652 (2020)"},{"key":"36_CR17","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is Space-Time Attention All You Need for Video Understanding? CoRR, vol. abs\/2102.05095 (2021). http:\/\/arxiv.org\/abs\/2102.05095"},{"key":"36_CR18","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. International Conference on Learning Representations (2021)"},{"key":"36_CR19","unstructured":"Touvron, H., Cord, M., Douze, M., et al.: Training Data-Efficient Image Transformers & Distillation Through Attention. CoRR, vol. abs\/2012.12877 (2020). http:\/\/arxiv.org\/abs\/2012.12877"},{"key":"36_CR20","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., et al.: Swin transformer: Hierarchical vision transformer using shifted windows. CoRR, vol. abs\/2103.14030 (2021). http:\/\/arxiv.org\/abs\/2103.14030","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"36_CR21","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"36_CR22","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3d convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4489\u20134497 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"36_CR23","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 International Conference on Computer Vision, pp. 5533\u20135541 (2017)","DOI":"10.1109\/ICCV.2017.590"},{"key":"36_CR24","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":"36_CR25","unstructured":"Liu, Z., Ning, J., Cao, Y., Wei, Y., et al: Video Swin Transformer. CoRR, vol. abs\/2106.13230 (2021). http:\/\/arxiv.org\/abs\/2106.13230"},{"key":"36_CR26","unstructured":"Wightman, R., Touvron, H., J\u00e9gou, H.: ResNet Strikes Back: An Improved Training Procedure in Timm. CoRR, vol. abs\/2110.00476 (2021). http:\/\/arxiv.org\/abs\/2110.00476"},{"key":"36_CR27","unstructured":"Zhang, X., Wang, Q., Zhang, J., Zhong, Z.: Adversarial AutoAugment. CoRR, vol. abs\/1912.11188 (2019). http:\/\/arxiv.org\/abs\/1912.11188"},{"key":"36_CR28","unstructured":"Robinson, J., Chuang, C., Sra, S., Jegelka, S.: Contrastive Learning with Hard Negative Samples. CoRR, vol. abs\/2010.04592 (2020). http:\/\/arxiv.org\/abs\/2010.04592"},{"key":"36_CR29","doi-asserted-by":"crossref","unstructured":"Lin, T., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal Loss for Dense Object Detection. CoRR, vol. abs\/1708.02002 (2017). http:\/\/arxiv.org\/abs\/1708.02002","DOI":"10.1109\/ICCV.2017.324"},{"key":"36_CR30","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo Vadis, Action Recognition? a new model and the kinetics dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"36_CR31","unstructured":"Wu, W., He, D., Lin, T., et al.: MVFNet: Multi-View Fusion Network for Efficient Video Recognition. CoRR, vol. abs\/2012.06977 (2020). http:\/\/arxiv.org\/abs\/2012.06977"},{"key":"36_CR32","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., et al.: A closer look at spatiotemporal convolutions for action recognition. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp. 6450\u20136459 (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"36_CR33","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"36_CR34","doi-asserted-by":"crossref","unstructured":"Cao, Y., Xu, J., Lin, S., Wei, F., Hu, H.: Gcnet: Non-local networks meet squeeze excitation networks and beyond. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) Workshops (2019)","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"36_CR35","doi-asserted-by":"crossref","unstructured":"Yin, M., Yao, Z., Cao, Y., et al.: Disentangled non-local neural networks. In: Proceedings of the European Conference on Computer Vision (2020)","DOI":"10.1007\/978-3-030-58555-6_12"},{"key":"36_CR36","doi-asserted-by":"crossref","unstructured":"Neimark, D., Bar, O., Zohar, M., Asselmann, D.: Video Transformer Network. CoRR, vol. abs\/2102.00719 (2021). http:\/\/arxiv.org\/abs\/2102.00719","DOI":"10.1109\/ICCVW54120.2021.00355"},{"key":"36_CR37","unstructured":"Fan, H., Xiong, B., Mangalam, K., et al.: Multiscale Vision Transformers. CoRR, vol. abs\/2104.11227 (2021). http:\/\/arxiv.org\/abs\/2104.11227"},{"key":"36_CR38","unstructured":"Li, X., Zhang, Y., Liu, C., et al.: Vidtr: Video Transformer Without Convolutions. CoRR, vol. abs\/2104.11746 (2021). http:\/\/arxiv.org\/abs\/2104.11746"},{"key":"36_CR39","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6202\u20136211 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"36_CR40","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C.: X3d: Expanding architectures for efficient video recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 203\u2013213 (2020)","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"36_CR41","unstructured":"Nanjundan, S., Sankaran, S., Arjun, C.R., Paavai Anand, G.: Identifying the Number of Clusters for K-Means: A Hypersphere Density Based Approach. CoRR, vol. abs\/1912.00643 (2019). http:\/\/arxiv.org\/abs\/1912.00643"},{"key":"36_CR42","unstructured":"Kay, W., Carreira, J., Simonyan, K., et al.: The Kinetics Human Action Video Dataset. CoRR, vol. abs\/1705.06950 (2017). http:\/\/arxiv.org\/abs\/1705.06950"},{"key":"36_CR43","unstructured":"Chen, K., Wang, J., Pang, J., et al.: MMAction2: Open-Source Toolbox for Video Understanding. https:\/\/github.com\/open-mmlab\/mmaction2 Accessed 11 Feb 2022"},{"key":"36_CR44","unstructured":"Kingma, D.P., Ba, J.: Adam: A Method for Stochastic Optimization. CoRR, vol. abs\/1412.6980 (2014). http:\/\/arxiv.org\/abs\/1412.6980"},{"key":"36_CR45","doi-asserted-by":"publisher","unstructured":"Huang, G., Sun, Y., Liu, Z., Sedra, D., Weinberger, K. Q.: Deep networks with stochastic depth. European conference on computer vision, pp. 646\u2013661, Springer (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_39","DOI":"10.1007\/978-3-319-46493-0_39"}],"container-title":["Lecture Notes in Networks and Systems","Intelligent Systems and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-16075-2_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,31]],"date-time":"2022-08-31T10:03:20Z","timestamp":1661940200000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-16075-2_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,1]]},"ISBN":["9783031160745","9783031160752"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-16075-2_36","relation":{},"ISSN":["2367-3370","2367-3389"],"issn-type":[{"type":"print","value":"2367-3370"},{"type":"electronic","value":"2367-3389"}],"subject":[],"published":{"date-parts":[[2022,9,1]]},"assertion":[{"value":"1 September 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IntelliSys","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Proceedings of SAI Intelligent Systems Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Amsterdam","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"intellisys2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/saiconference.com\/IntelliSys","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}