{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T07:36:56Z","timestamp":1765438616091,"version":"3.37.3"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2020,3,4]],"date-time":"2020-03-04T00:00:00Z","timestamp":1583280000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,3,4]],"date-time":"2020-03-04T00:00:00Z","timestamp":1583280000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2020,4]]},"DOI":"10.1007\/s11263-020-01302-5","type":"journal-article","created":{"date-parts":[[2020,3,4]],"date-time":"2020-03-04T15:02:32Z","timestamp":1583334152000},"page":"1047-1059","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Inference, Learning and Attention Mechanisms that Exploit and Preserve Sparsity in CNNs"],"prefix":"10.1007","volume":"128","author":[{"given":"Timo","family":"Hackel","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4789-5994","authenticated-orcid":false,"given":"Mikhail","family":"Usvyatsov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Silvano","family":"Galliani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jan D.","family":"Wegner","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Konrad","family":"Schindler","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,3,4]]},"reference":[{"key":"1302_CR1","unstructured":"Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., et\u00a0al. (2016). Tensorflow: A system for large-scale machine learning. In USENIX OSDI."},{"key":"1302_CR2","doi-asserted-by":"publisher","unstructured":"Alabi, T., Blanchard, J. D., Gordon, B., & Steinbach, R. (2012). Fast k-selection algorithms for graphics processing units. Journal of Experimental Algorithmics. https:\/\/doi.org\/10.1145\/2133803.2345676.","DOI":"10.1145\/2133803.2345676"},{"key":"1302_CR3","unstructured":"Boulch, A. (2019). Generalizing discrete convolutions for unstructured point clouds. In Eurographics 3DOR."},{"key":"1302_CR4","unstructured":"Brock, A., Lim, T., Ritchie, J., & Weston, N. (2017). Generative and discriminative voxel modeling with convolutional neural networks. arXiv:1608.04236."},{"issue":"4","key":"1302_CR5","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2018","unstructured":"Chen, L. C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2018). Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE TPAMI, 40(4), 834\u2013848.","journal-title":"IEEE TPAMI"},{"key":"1302_CR6","unstructured":"Chetlur, S., Woolley, C., Vandermersch, P., Cohen, J., Tran, J., Catanzaro, B., & Shelhamer, E. (2014). CUDNN: Efficient primitives for deep learning. arXiv:1410.0759."},{"key":"1302_CR7","doi-asserted-by":"crossref","unstructured":"Choy, C., Gwak, J., & Savarese, S. (2019). 4D spatio-temporal convnets: Minkowski convolutional neural networks. In CVPR.","DOI":"10.1109\/CVPR.2019.00319"},{"key":"1302_CR8","doi-asserted-by":"crossref","unstructured":"Dai,A., Chang, A. X., Savva, M., Halber, M., Funkhouser, T., & Nie\u00dfner, M. (2017). ScanNet: Richly-annotated 3d reconstructions of indoor scenes. In CVPR.","DOI":"10.1109\/CVPR.2017.261"},{"key":"1302_CR9","unstructured":"Denil, M., Shakibi, B., Dinh, L., de\u00a0Freitas, N., et al. (2013). Predicting parameters in deep learning. In NIPS."},{"key":"1302_CR10","unstructured":"Denton, E. L., Zaremba, W., Bruna, J., LeCun, Y., & Fergus, R. (2014). Exploiting linear structure within convolutional networks for efficient evaluation. In: NIPS."},{"key":"1302_CR11","first-page":"2121","volume":"12","author":"J Duchi","year":"2011","unstructured":"Duchi, J., Hazan, E., & Singer, Y. (2011). Adaptive subgradient methods for online learning and stochastic optimization. Journal of Machine Learning Research, 12, 2121\u20132159.","journal-title":"Journal of Machine Learning Research"},{"key":"1302_CR12","unstructured":"Engelcke, M., Rao, D., Wang, D. Z., Tong, C. H., & Posner, I. (2016). Vote3Deep: Fast object detection in 3d point clouds using efficient convolutional neural networks. In ICRA."},{"key":"1302_CR13","unstructured":"Graham, B. (2014). Spatially-sparse convolutional neural networks. arXiv:1409.6070."},{"key":"1302_CR14","unstructured":"Graham, B., & van der, Maaten L. (2017). Submanifold sparse convolutional networks. arXiv:1706.01307."},{"key":"1302_CR15","doi-asserted-by":"crossref","unstructured":"Graham, B., Engelcke, M., & van\u00a0der Maaten, L. (2018) 3d semantic segmentation with submanifold sparse convolutional networks. In CVPR.","DOI":"10.1109\/CVPR.2018.00961"},{"key":"1302_CR16","unstructured":"Hackel, T., Usvyatsov, M., Galliani, S., Wegner, J. D., & Schindler, K., (2018). Inference, learning and attention mechanisms that exploit and preserve sparsity in CNNs. In German conference on pattern recognition (GCPR)."},{"key":"1302_CR17","first-page":"1135","volume":"1","author":"S Han","year":"2015","unstructured":"Han, S., Pool, J., Tran, J., & Dally, W. (2015). Learning both weights and connections for efficient neural network. Advances in Neural Information Processing Systems, 1, 1135\u20131143.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"1302_CR18","doi-asserted-by":"crossref","unstructured":"H\u00e4ne, C., Tulsiani, S., & Malik, J.(2017). Hierarchical surface prediction for 3d object reconstruction. In 3DV.","DOI":"10.1109\/3DV.2017.00054"},{"key":"1302_CR19","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In CVPR.","DOI":"10.1109\/CVPR.2016.90"},{"key":"1302_CR20","doi-asserted-by":"crossref","unstructured":"Huang, J., & You, S. (2016). Point cloud labeling using 3d convolutional neural network. In ICPR.","DOI":"10.1109\/ICPR.2016.7900038"},{"key":"1302_CR21","unstructured":"Ilg, E., Mayer, N., Saikia, T., Keuper, M., Dosovitskiy, A., & Brox, T. (2017). Flownet 2.0: Evolution of optical flow estimation with deep networks. In CVPR."},{"key":"1302_CR22","doi-asserted-by":"crossref","unstructured":"Jaderberg, M., Vedaldi, A., & Zisserman, A. (2014). Speeding up convolutional neural networks with low rank expansions. In BMVC.","DOI":"10.5244\/C.28.88"},{"key":"1302_CR23","doi-asserted-by":"crossref","unstructured":"Jampani, V., Kiefel, M., & Gehler, P. V. (2016). Learning sparse high dimensional filters: Image filtering, dense CRFs and bilateral neural networks. In CVPR.","DOI":"10.1109\/CVPR.2016.482"},{"key":"1302_CR24","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., & Fei-Fei, L. (2014) Large-scale video classification with convolutional neural networks. In CVPR.","DOI":"10.1109\/CVPR.2014.223"},{"key":"1302_CR25","unstructured":"Krizhevsky, A., Sutskever,I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. In NIPS."},{"key":"1302_CR26","doi-asserted-by":"crossref","unstructured":"Lai, K., Bo, L., & Fox, D. (2014). Unsupervised feature learning for 3d scene labeling. In ICRA.","DOI":"10.1109\/ICRA.2014.6907298"},{"issue":"11","key":"1302_CR27","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. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278\u20132324.","journal-title":"Proceedings of the IEEE"},{"key":"1302_CR28","unstructured":"Li, Y., Pirk, S., Su, H., Qi, C. R., & Guibas, L. J. (2016). FPNN: Field probing neural networks for 3d data. In NIPS."},{"key":"1302_CR29","unstructured":"Liu, B., Wang, M., Foroosh, H., Tappen, M., & Pensky, M. (2015). Sparse convolutional neural networks. In CVPR."},{"key":"1302_CR30","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. In CVPR.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"1302_CR31","doi-asserted-by":"crossref","unstructured":"Maturana, D., & Scherer, S. (2015). Voxnet: A 3d convolutional neural network for real-time object recognition. In IROS.","DOI":"10.1109\/IROS.2015.7353481"},{"issue":"1","key":"1302_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/0010-0285(87)90002-8","volume":"19","author":"MJ Nissen","year":"1987","unstructured":"Nissen, M. J., & Bullemer, P. (1987). Attentional requirements of learning: Evidence from performance measures. Cognitive Psychology, 19(1), 1\u201332.","journal-title":"Cognitive Psychology"},{"key":"1302_CR33","doi-asserted-by":"crossref","unstructured":"Parashar, A., Rhu, M., Mukkara, A., Puglielli, A., Venkatesan, R., Khailany, B., Emer, J., Keckler, S. W., & Dally, W. J. (2017). SCNN: An accelerator for compressed-sparse convolutional neural networks. In Int\u2019l symposium on computer architecture.","DOI":"10.1145\/3079856.3080254"},{"key":"1302_CR34","unstructured":"Park, J., Li, S., Wen, W., Tang, P. T. P., Li, H., Chen, Y., & Dubey, P. (2017). Faster CNNs with direct sparse convolutions and guided pruning. In ICLR."},{"issue":"5","key":"1302_CR35","doi-asserted-by":"publisher","first-page":"858","DOI":"10.1109\/TNN.2010.2044802","volume":"21","author":"D Prokhorov","year":"2010","unstructured":"Prokhorov, D. (2010). A Convolutional learning system for object classification in 3-D lidar data. IEEE Transactions on Neural Networks, 21(5), 858\u2013863.","journal-title":"IEEE Transactions on Neural Networks"},{"key":"1302_CR36","unstructured":"Qi, C. R., Su, H., Mo, K., & Guibas, L. J. (2017a) PointNet: Deep learning on point sets for 3d classification and segmentation. In CVPR."},{"key":"1302_CR37","unstructured":"Qi, C. R., Yi, L., Su, H., & Guibas, L. J. (2017b). PointNet++: Deep hierarchical feature learning on point sets in a metric space. In NIPS."},{"key":"1302_CR38","unstructured":"Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster R-CNN: Towards real-time object detection with region proposal networks. In NIPS."},{"key":"1302_CR39","doi-asserted-by":"crossref","unstructured":"Riegler, G., Ulusoy, A. O., Bischof, H., & Geiger, A. (2017a) OctNetFusion: Learning depth fusion from data. In 3DV.","DOI":"10.1109\/3DV.2017.00017"},{"key":"1302_CR40","doi-asserted-by":"crossref","unstructured":"Riegler, G., Ulusoy, A. O., & Geiger, A. (2017b). OctNet: Learning deep 3d representations at high resolutions. In CVPR.","DOI":"10.1109\/CVPR.2017.701"},{"issue":"38","key":"1302_CR41","doi-asserted-by":"publisher","first-page":"10073","DOI":"10.1523\/JNEUROSCI.2747-07.2007","volume":"27","author":"EM Robertson","year":"2007","unstructured":"Robertson, E. M. (2007). The serial reaction time task: Implicit motor skill learning? Journal of Neuroscience, 27(38), 10073\u201310075.","journal-title":"Journal of Neuroscience"},{"key":"1302_CR42","doi-asserted-by":"crossref","unstructured":"Song, S., & Xiao, J. (2016). Deep sliding shapes for amodal 3d object detection in rgb-d images. In CVPR.","DOI":"10.1109\/CVPR.2016.94"},{"key":"1302_CR43","doi-asserted-by":"crossref","unstructured":"Tatarchenko, M., Dosovitskiy, A., & Brox, T. (2017). Octree generating networks: Efficient convolutional architectures for high-resolution 3d outputs. In ICCV.","DOI":"10.1109\/ICCV.2017.230"},{"key":"1302_CR44","doi-asserted-by":"crossref","unstructured":"Thomas, H., Qi, C. R., Deschaud, J. E., Marcotegui, B., Goulette, F., & Guibas, L. J. (2019). KPConv: Flexible and deformable convolution for point clouds. In ICCV.","DOI":"10.1109\/ICCV.2019.00651"},{"key":"1302_CR45","doi-asserted-by":"crossref","unstructured":"Uhrig, J., Schneider, N., Schneider, L., Franke, U., Brox, T., & Geiger, A. (2017). Sparsity invariant CNNs. In 3DV.","DOI":"10.1109\/3DV.2017.00012"},{"issue":"4","key":"1302_CR46","first-page":"1","volume":"36","author":"PS Wang","year":"2017","unstructured":"Wang, P. S., Liu, Y., Guo, Y. X., Sun, C. Y., & Tong, X. (2017). O-CNN: Octree-based convolutional neural networks for 3d shape analysis. ACM Transactions on Graphics (SIGGRAPH), 36(4), 1\u201311.","journal-title":"ACM Transactions on Graphics (SIGGRAPH)"},{"issue":"6","key":"1302_CR47","first-page":"1","volume":"37","author":"PS Wang","year":"2018","unstructured":"Wang, P. S., Sun, C. Y., Liu, Y., & Tong, X. (2018). Adaptive O-CNN: A patch-based deep representation of 3d shapes. ACM Transactions on Graphics (SIGGRAPH Asia), 37(6), 1\u201311.","journal-title":"ACM Transactions on Graphics (SIGGRAPH Asia)"},{"key":"1302_CR48","unstructured":"Wen, W., Wu, C., Wang, Y., Chen, Y., & Li, H. (2016). Learning structured sparsity in deep neural networks. In NIPS."},{"key":"1302_CR49","unstructured":"Wu, Z., Song, S., Khosla, A., Yu, F., Zhang, L., Tang, X., & Xiao, J. (2015). 3d shapenets: A deep representation for volumetric shapes. In CVPR."},{"key":"1302_CR50","doi-asserted-by":"crossref","unstructured":"Zhou, T., Brown, M., Snavely, N., & Lowe, D. G. (2017). Unsupervised learning of depth and ego-motion from video. In CVPR.","DOI":"10.1109\/CVPR.2017.700"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-020-01302-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11263-020-01302-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-020-01302-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,4]],"date-time":"2021-03-04T00:23:03Z","timestamp":1614817383000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11263-020-01302-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3,4]]},"references-count":50,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2020,4]]}},"alternative-id":["1302"],"URL":"https:\/\/doi.org\/10.1007\/s11263-020-01302-5","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"type":"print","value":"0920-5691"},{"type":"electronic","value":"1573-1405"}],"subject":[],"published":{"date-parts":[[2020,3,4]]},"assertion":[{"value":"18 March 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 February 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 March 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}