{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,7,29]],"date-time":"2024-07-29T06:30:41Z","timestamp":1722234641954},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T00:00:00Z","timestamp":1643155200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T00:00:00Z","timestamp":1643155200000},"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":["SIViP"],"published-print":{"date-parts":[[2022,10]]},"DOI":"10.1007\/s11760-022-02133-2","type":"journal-article","created":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T19:02:15Z","timestamp":1643223735000},"page":"1763-1771","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Usage of compressed domain in fast frameworks"],"prefix":"10.1007","volume":"16","author":[{"given":"Hasan Sait","family":"Arslan","sequence":"first","affiliation":[]},{"given":"Simon","family":"Archambault","sequence":"additional","affiliation":[]},{"given":"Prakruti","family":"Bhatt","sequence":"additional","affiliation":[]},{"given":"Keita","family":"Watanabe","sequence":"additional","affiliation":[]},{"given":"Josue","family":"Cuevaz","sequence":"additional","affiliation":[]},{"given":"Phuc","family":"Le","sequence":"additional","affiliation":[]},{"given":"Denis","family":"Miller","sequence":"additional","affiliation":[]},{"given":"Viktor","family":"Zhumatiy","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,1,26]]},"reference":[{"key":"2133_CR1","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":"2133_CR2","first-page":"91","volume":"28","author":"S Ren","year":"2015","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst. 28, 91\u201399 (2015)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"2133_CR3","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"2133_CR4","unstructured":"Tan, M., Le, Q.V.: Efficientnet: rethinking model scaling for convolutional neural networks. arXiv:1905.11946 (2019)"},{"key":"2133_CR5","unstructured":"Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: YOLOv4: optimal speed and accuracy of object detection. arXiv:2004.10934 (2020)"},{"key":"2133_CR6","doi-asserted-by":"crossref","unstructured":"Bolya, D., Zhou, C., Xiao, F., Lee, Y.J.: Yolact: real-time instance segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 9157\u20139166 (2019)","DOI":"10.1109\/ICCV.2019.00925"},{"key":"2133_CR7","first-page":"3933","volume":"31","author":"L Gueguen","year":"2018","unstructured":"Gueguen, L., Sergeev, A., Kadlec, B., Liu, R., Yosinski, J.: Faster neural networks straight from jpeg. Adv. Neural Inf. Process. Syst. 31, 3933 (2018)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"2133_CR8","doi-asserted-by":"crossref","unstructured":"Tan, M., Chen, B., Pang, R., Vasudevan, V., Sandler, M., Howard, A., Le, Q.V.: Mnasnet: platform-aware neural architecture search for mobile. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2820\u20132828 (2019)","DOI":"10.1109\/CVPR.2019.00293"},{"key":"2133_CR9","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2133_CR10","unstructured":"Jocher,G., Stoken,A., Borovec,J., NanoCode012, ChristopherSTAN, Changyu,L., Laughing, tkianai, yxNONG, Hogan,A., lorenzomammana, AlexWang1900, Chaurasia,A.,Diaconu, L., Marc, wanghaoyang0106, ml5ah, Doug, Durgesh, F.Ingham, Frederik, Guilhen, A.Colmagro, H.Ye, Jacobsolawetz, J.Poznanski, J.Fang, J.Kim, K.Doan, L.Yu. ultralytics\/yolov5: v4.0 - nn.SiLU() activations, Weights & Biases logging, PyTorch Hub integration (2021). 10.5281\/zenodo.4418161. https:\/\/doi.org\/10.5281\/zenodo.4418161"},{"key":"2133_CR11","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft coco: common objects in context. In: European Conference on Computer Vision, pp. 740\u2013755. Springer (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"issue":"1","key":"2133_CR12","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham, M., Eslami, S.M.A., VanGool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The pascal visual object classes challenge: a retrospective. Int. J. Comput. Vis. 111(1), 98 (2015)","journal-title":"Int. J. Comput. Vis."},{"key":"2133_CR13","unstructured":"Shao, S., Zhao, Z., Li, B., Xiao, T., Yu, G., Zhang, X., Sun, J.: Crowdhuman: a benchmark for detecting human in a crowd. arXiv:1805.00123 (2018)"},{"key":"2133_CR14","unstructured":"Deguerre, B., Chatelain, C., Gasso, G.: Object detection in the DCT domain: is luminance the solution? arXiv:2006.05732 (2020)"},{"key":"2133_CR15","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., Berg, A.C.: SSD: single shot multibox detector. In: European Conference on Computer Vision, pp. 21\u201337. Springer (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"2133_CR16","unstructured":"Simonyan, K., Zisserman, A.:Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556 (2014)"},{"key":"2133_CR17","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., Adam, H.: Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv:1704.04861 (2017)"},{"key":"2133_CR18","doi-asserted-by":"crossref","unstructured":"Fukushima, K., Miyake, S.: Neocognitron: a self-organizing neural network model for a mechanism of visual pattern recognition. In: Competition and Cooperation in Neural Nets, pp. 267\u2013285. Springer (1982)","DOI":"10.1007\/978-3-642-46466-9_18"},{"key":"2133_CR19","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning (PMLR, 2015), pp. 448\u2013456"},{"key":"2133_CR20","unstructured":"Hendrycks, D., Gimpel, K.:Gaussian error linear units (gelus). arXiv:1606.08415 (2016)"},{"key":"2133_CR21","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.neunet.2017.12.012","volume":"107","author":"S Elfwing","year":"2018","unstructured":"Elfwing, S., Uchibe, E., Doya, K.: Sigmoid-weighted linear units for neural network function approximation in reinforcement learning. Neural Netw 107, 3 (2018)","journal-title":"Neural Netw"},{"key":"2133_CR22","unstructured":"Ramachandran, P., Zoph, B., Le, Q.V.: Swish: a self-gated activation function. Neural Evol. Comput. (2017)"},{"key":"2133_CR23","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Liao, H.Y.M., Wu, Y.H., Chen, P.Y., Hsieh, J.W., Yeh, I.H.: CSPNet: a new backbone that can enhance learning capability of CNN. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 390\u2013391 (2020)","DOI":"10.1109\/CVPRW50498.2020.00203"},{"key":"2133_CR24","doi-asserted-by":"crossref","unstructured":"Huang, Z., Wang, J., Fu, X., Yu, T., Guo, Y., Wang, R.: DC-SPP-YOLO: dense connection and spatial pyramid pooling based YOLO for object detection. Inf. Sci. 522, 241 (2020)","DOI":"10.1016\/j.ins.2020.02.067"},{"key":"2133_CR25","doi-asserted-by":"crossref","unstructured":"Nagi, J., Ducatelle, F., DiCaro, G.A., Cire\u015fan, D., Meier, U., Giusti, A., Nagi, F., Schmidhuber, J., Gambardella, L.M.: Max-pooling convolutional neural networks for vision-based hand gesture recognition. In: 2011 IEEE International Conference on Signal and Image Processing Applications (ICSIPA), pp. 342\u2013347. IEEE (2011)","DOI":"10.1109\/ICSIPA.2011.6144164"},{"key":"2133_CR26","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al.: Pytorch: an imperative style, high-performance deep learning library. arXiv:1912.01703 (2019)"},{"key":"2133_CR27","doi-asserted-by":"crossref","unstructured":"Marcel, S., Rodriguez, Y.: Torchvision the machine-vision package of torch. In: Proceedings of the 18th ACM International Conference on Multimedia, pp. 1485\u20131488 (2010)","DOI":"10.1145\/1873951.1874254"},{"key":"2133_CR28","doi-asserted-by":"publisher","DOI":"10.3390\/info11020125","author":"A Buslaev","year":"2020","unstructured":"Buslaev, A., Iglovikov, V.I., Khvedchenya, E., Parinov, A., Druzhinin, M., Kalinin, A.A.: Albumentations: fast and flexible image augmentations. Information (2020). https:\/\/doi.org\/10.3390\/info11020125","journal-title":"Information"},{"key":"2133_CR29","unstructured":"Everingham, M., VanGool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL visual object classes challenge 2012 (VOC2012) results. http:\/\/www.pascal-network.org\/challenges\/VOC\/voc2012\/workshop\/index.html"},{"key":"2133_CR30","unstructured":"Everingham, M., VanGool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL visual object classes challenge 2007 (VOC2007) results. http:\/\/www.pascal-network.org\/challenges\/VOC\/voc2007\/workshop\/index.html"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-022-02133-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-022-02133-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-022-02133-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,10]],"date-time":"2022-08-10T19:56:13Z","timestamp":1660161373000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-022-02133-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,26]]},"references-count":30,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2022,10]]}},"alternative-id":["2133"],"URL":"https:\/\/doi.org\/10.1007\/s11760-022-02133-2","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,26]]},"assertion":[{"value":"9 September 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 December 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 January 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 January 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}