{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T16:55:23Z","timestamp":1758905723466,"version":"3.40.3"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031277610"},{"type":"electronic","value":"9783031277627"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-27762-7_27","type":"book-chapter","created":{"date-parts":[[2023,3,2]],"date-time":"2023-03-02T12:48:04Z","timestamp":1677761284000},"page":"282-293","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Deep Learning for Image and Sound Data: An Overview"],"prefix":"10.1007","author":[{"given":"Hilali","family":"Manal","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ezzati","family":"Abdellah","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ben Alla","family":"Said","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,3,1]]},"reference":[{"issue":"2","key":"27_CR1","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1007\/s11263-019-01247-4","volume":"128","author":"L Liu","year":"2019","unstructured":"Liu, L., et al.: Deep learning for generic object detection: a survey. Int. J. Comput. Vis. 128(2), 261\u2013318 (2019). https:\/\/doi.org\/10.1007\/s11263-019-01247-4","journal-title":"Int. J. Comput. Vis."},{"key":"27_CR2","doi-asserted-by":"publisher","unstructured":"Sornam, M., Muthusubash, K., Vanitha, V.: A survey on image classification and activity recognition using deep convolutional neural network architecture. In: 2017 9th International Conference on Advanced Computing (ICoAC), pp. 121\u2013126 (2017). https:\/\/doi.org\/10.1109\/ICoAC.2017.8441512","DOI":"10.1109\/ICoAC.2017.8441512"},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Garcia-Garcia, A., Orts-Escolano, S., Oprea, S., Villena-Martinez, V., Garcia-Rodriguez, J.: A review on deep learning techniques applied to semantic segmentation. arXiv:1704.06857 [cs] (2017)","DOI":"10.1016\/j.asoc.2018.05.018"},{"key":"27_CR4","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1016\/j.asoc.2018.05.018","volume":"70","author":"A Garcia-Garcia","year":"2018","unstructured":"Garcia-Garcia, A., Orts-Escolano, S., Oprea, S., Villena-Martinez, V., Martinez-Gonzalez, P., Garcia-Rodriguez, J.: A survey on deep learning techniques for image and video semantic segmentation. Appl. Soft Comput. 70, 41\u201365 (2018). https:\/\/doi.org\/10.1016\/j.asoc.2018.05.018","journal-title":"Appl. Soft Comput."},{"key":"27_CR5","doi-asserted-by":"publisher","first-page":"114417","DOI":"10.1016\/j.eswa.2020.114417","volume":"169","author":"X Yuan","year":"2021","unstructured":"Yuan, X., Shi, J., Gu, L.: A review of deep learning methods for semantic segmentation of remote sensing imagery. Expert Syst. Appl. 169, 114417 (2021). https:\/\/doi.org\/10.1016\/j.eswa.2020.114417","journal-title":"Expert Syst. Appl."},{"key":"27_CR6","unstructured":"Nekrasov, P., Freeze, J., Batista, V.: Using restricted boltzmann machines to model molecular geometries. arXiv:2012.06984 [physics] (2020)"},{"key":"27_CR7","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Pereira, F., Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, vol. 25, pp. 1097\u20131105. Curran Associates, Inc. (2012)"},{"key":"27_CR8","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556 [cs] (2015)"},{"key":"27_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. arXiv:1512.03385 [cs] (2015)","DOI":"10.1109\/CVPR.2016.90"},{"key":"27_CR10","doi-asserted-by":"publisher","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1\u20139. IEEE, Boston, MA, USA (2015). https:\/\/doi.org\/10.1109\/CVPR.2015.7298594","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"27_CR11","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, 1735\u20131780 (1997). https:\/\/doi.org\/10.1162\/neco.1997.9.8.1735","journal-title":"Neural Comput."},{"key":"27_CR12","doi-asserted-by":"crossref","unstructured":"Cho, K., et al.: Learning phrase representations using rnn encoder-decoder for statistical machine translation. arXiv:1406.1078 [cs, stat] (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"27_CR13","unstructured":"Goodfellow, I.J., et al.: Generative adversarial networks. arXiv:1406.2661 [cs, stat] (2014)"},{"key":"27_CR14","doi-asserted-by":"publisher","first-page":"101764","DOI":"10.1016\/j.media.2020.101764","volume":"65","author":"S Rahman","year":"2020","unstructured":"Rahman, S., Wang, L., Sun, C., Zhou, L.: Deep learning based HEp-2 image classification: A comprehensive review. Med. Image Anal. 65, 101764 (2020). https:\/\/doi.org\/10.1016\/j.media.2020.101764","journal-title":"Med. Image Anal."},{"key":"27_CR15","doi-asserted-by":"crossref","unstructured":"Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. arXiv:1311.2901 [cs] (2013)","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"27_CR16","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. arXiv:1311.2524 [cs] (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"27_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1007\/978-3-319-10578-9_23","volume-title":"Computer Vision \u2013 ECCV 2014","author":"K He","year":"2014","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8691, pp. 346\u2013361. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10578-9_23"},{"key":"27_CR18","doi-asserted-by":"publisher","first-page":"2372","DOI":"10.1109\/TMM.2016.2602060","volume":"18","author":"C Huang","year":"2016","unstructured":"Huang, C., He, Z., Cao, G., Cao, W.: Task-driven progressive part localization for fine-grained object recognition. IEEE Trans. Multimedia 18, 2372\u20132383 (2016). https:\/\/doi.org\/10.1109\/TMM.2016.2602060","journal-title":"IEEE Trans. Multimedia"},{"key":"27_CR19","doi-asserted-by":"publisher","first-page":"532","DOI":"10.1109\/TCSVT.2019.2893318","volume":"30","author":"L Kong","year":"2020","unstructured":"Kong, L., Huang, D., Qin, J., Wang, Y.: A joint framework for athlete tracking and action recognition in sports videos. IEEE Trans. Circuits Syst. Video Technol. 30, 532\u2013548 (2020). https:\/\/doi.org\/10.1109\/TCSVT.2019.2893318","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"27_CR20","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. arXiv:1504.08083 [cs] (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"27_CR21","doi-asserted-by":"crossref","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. arXiv:1506.01497 [cs] (2016)","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"27_CR22","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1016\/j.biosystemseng.2020.12.002","volume":"202","author":"S Parvathi","year":"2021","unstructured":"Parvathi, S., Selvi, S.T.: Detection of maturity stages of coconuts in complex background using Faster R-CNN model. Biosyst. Eng. 202, 119\u2013132 (2021). https:\/\/doi.org\/10.1016\/j.biosystemseng.2020.12.002","journal-title":"Biosyst. Eng."},{"key":"27_CR23","unstructured":"Dai, J., Li, Y., He, K., Sun, J.: R-FCN: object detection via region-based fully convolutional networks vol. 9"},{"key":"27_CR24","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. arXiv:1612.03144 [cs] (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"27_CR25","doi-asserted-by":"publisher","unstructured":"Cai, Z., Vasconcelos, N.: Cascade R-CNN: delving into high quality object detection. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6154\u20136162. IEEE, Salt Lake City, UT (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00644","DOI":"10.1109\/CVPR.2018.00644"},{"key":"27_CR26","doi-asserted-by":"crossref","unstructured":"Wu, C.-E., Chan, Y.-M., Chen, C.-H., Chen, W.-C., Chen, C.-S.: IMMVP: an efficient daytime and nighttime on-road object detector. In: 2019 IEEE 21st International Workshop on Multimedia Signal Processing (MMSP 2019). IEEE, New York (2019)","DOI":"10.1109\/MMSP.2019.8901824"},{"key":"27_CR27","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. arXiv:1506.02640 [cs] (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"27_CR28","doi-asserted-by":"publisher","unstructured":"Shin, S., Han, H., Lee, S.H.: Improved YOLOv3 with duplex FPN for object detection based on deep learning. Int. J. Elec. Eng. Educ. https:\/\/doi.org\/10.1177\/0020720920983524","DOI":"10.1177\/0020720920983524"},{"key":"27_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"27_CR30","doi-asserted-by":"publisher","first-page":"102949","DOI":"10.1016\/j.dsp.2020.102949","volume":"110","author":"L Ding","year":"2021","unstructured":"Ding, L., Xu, X., Cao, Y., Zhai, G., Yang, F., Qian, L.: Detection and tracking of infrared small target by jointly using SSD and pipeline filter. Digital Signal Process. 110, 102949 (2021). https:\/\/doi.org\/10.1016\/j.dsp.2020.102949","journal-title":"Digital Signal Process."},{"key":"27_CR31","unstructured":"Fu, C.-Y., Liu, W., Ranga, A., Tyagi, A., Berg, A.C.: DSSD: deconvolutional single shot detector. arXiv:1701.06659 [cs] (2017)"},{"key":"27_CR32","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. arXiv:1708.02002 [cs] (2018)","DOI":"10.1109\/ICCV.2017.324"},{"key":"27_CR33","doi-asserted-by":"publisher","first-page":"104133","DOI":"10.1016\/j.compbiomed.2020.104133","volume":"129","author":"BCG da Silva","year":"2021","unstructured":"da Silva, B.C.G., Tam, R., Ferrari, R.J.: Detecting cells in intravital video microscopy using a deep convolutional neural network. Comput. Biol. Med. 129, 104133 (2021). https:\/\/doi.org\/10.1016\/j.compbiomed.2020.104133","journal-title":"Comput. Biol. Med."},{"key":"27_CR34","doi-asserted-by":"publisher","unstructured":"Pang, J., Chen, K., Shi, J., Feng, H., Ouyang, W., Lin, D.: Libra R-CNN: towards balanced learning for object detection. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 821\u2013830. IEEE, Long Beach, CA, USA (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00091","DOI":"10.1109\/CVPR.2019.00091"},{"key":"27_CR35","doi-asserted-by":"publisher","first-page":"114602","DOI":"10.1016\/j.eswa.2021.114602","volume":"172","author":"Y Liu","year":"2021","unstructured":"Liu, Y., Sun, P., Wergeles, N., Shang, Y.: A survey and performance evaluation of deep learning methods for small object detection. Expert Syst. Appl. 172, 114602 (2021). https:\/\/doi.org\/10.1016\/j.eswa.2021.114602","journal-title":"Expert Syst. Appl."},{"key":"27_CR36","unstructured":"Logan, B.: Mel frequency cepstral coefficients for music modeling. In: International Symposium on Music Information Retrieval (2000)"},{"key":"27_CR37","doi-asserted-by":"crossref","unstructured":"Honig, F., Stemmer, G., Hacker, C., Brugnara, F.: Revising perceptual linear prediction (PLP), vol. 4 (2005)","DOI":"10.21437\/Interspeech.2005-138"},{"key":"27_CR38","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/j.specom.2019.01.004","volume":"108","author":"D Palaz","year":"2019","unstructured":"Palaz, D., Magimai-Doss, M., Collobert, R.: End-to-end acoustic modeling using convolutional neural networks for HMM-based automatic speech recognition. Speech Commun. 108, 15\u201332 (2019). https:\/\/doi.org\/10.1016\/j.specom.2019.01.004","journal-title":"Speech Commun."},{"key":"27_CR39","doi-asserted-by":"publisher","first-page":"107573","DOI":"10.1016\/j.apacoust.2020.107573","volume":"171","author":"Y Dokuz","year":"2021","unstructured":"Dokuz, Y., Tufekci, Z.: Mini-batch sample selection strategies for deep learning based speech recognition. Appl. Acoust. 171, 107573 (2021). https:\/\/doi.org\/10.1016\/j.apacoust.2020.107573","journal-title":"Appl. Acoust."},{"key":"27_CR40","doi-asserted-by":"publisher","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: Proceedings of the 23rd International Conference on Machine Learning, pp. 369\u2013376. Association for Computing Machinery, New York, NY, USA (2006). https:\/\/doi.org\/10.1145\/1143844.1143891","DOI":"10.1145\/1143844.1143891"},{"key":"27_CR41","doi-asserted-by":"publisher","first-page":"101027","DOI":"10.1016\/j.csl.2019.101027","volume":"60","author":"A Nagrani","year":"2020","unstructured":"Nagrani, A., Chung, J.S., Xie, W., Zisserman, A.: Voxceleb: large-scale speaker verification in the wild. Comput. Speech Lang. 60, 101027 (2020). https:\/\/doi.org\/10.1016\/j.csl.2019.101027","journal-title":"Comput. Speech Lang."},{"key":"27_CR42","doi-asserted-by":"publisher","first-page":"114416","DOI":"10.1016\/j.eswa.2020.114416","volume":"168","author":"A Garain","year":"2021","unstructured":"Garain, A., Singh, P.K., Sarkar, R.: FuzzyGCP: a deep learning architecture for automatic spoken language identification from speech signals. Expert Syst. Appl. 168, 114416 (2021). https:\/\/doi.org\/10.1016\/j.eswa.2020.114416","journal-title":"Expert Syst. Appl."},{"key":"27_CR43","doi-asserted-by":"publisher","unstructured":"Ubale, R., Qian, Y., Evanini, K.: Exploring end-to-end attention-based neural networks for native language identification. In: 2018 IEEE Spoken Language Technology Workshop (SLT), Athens, Greece (2018). https:\/\/doi.org\/10.1109\/SLT.2018.8639689","DOI":"10.1109\/SLT.2018.8639689"},{"key":"27_CR44","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1016\/j.ins.2020.09.047","volume":"548","author":"D Li","year":"2021","unstructured":"Li, D., Zhou, Y., Wang, Z., Gao, D.: Exploiting the potentialities of features for speech emotion recognition. Inf. Sci. 548, 328\u2013343 (2021). https:\/\/doi.org\/10.1016\/j.ins.2020.09.047","journal-title":"Inf. Sci."},{"key":"27_CR45","doi-asserted-by":"publisher","first-page":"106954","DOI":"10.1016\/j.asoc.2020.106954","volume":"100","author":"Y Yin","year":"2021","unstructured":"Yin, Y., Zheng, X., Hu, B., Zhang, Y., Cui, X.: EEG emotion recognition using fusion model of graph convolutional neural networks and LSTM. Appl. Soft Comput. 100, 106954 (2021). https:\/\/doi.org\/10.1016\/j.asoc.2020.106954","journal-title":"Appl. Soft Comput."},{"issue":"5","key":"27_CR46","doi-asserted-by":"publisher","first-page":"1787","DOI":"10.1007\/s12652-017-0644-8","volume":"10","author":"Y Huang","year":"2017","unstructured":"Huang, Y., Tian, K., Wu, A., Zhang, G.: Feature fusion methods research based on deep belief networks for speech emotion recognition under noise condition. J. Ambient. Intell. Humaniz. Comput. 10(5), 1787\u20131798 (2017). https:\/\/doi.org\/10.1007\/s12652-017-0644-8","journal-title":"J. Ambient. Intell. Humaniz. Comput."},{"key":"27_CR47","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1016\/j.apacoust.2016.06.021","volume":"113","author":"HB Huang","year":"2016","unstructured":"Huang, H.B., Huang, X.R., Li, R.X., Lim, T.C., Ding, W.P.: Sound quality prediction of vehicle interior noise using deep belief networks. Appl. Acoust. 113, 149\u2013161 (2016). https:\/\/doi.org\/10.1016\/j.apacoust.2016.06.021","journal-title":"Appl. Acoust."}],"container-title":["Lecture Notes on Data Engineering and Communications Technologies","The 3rd International Conference on Artificial Intelligence and Computer Vision (AICV2023), March 5\u20137, 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-27762-7_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,2]],"date-time":"2023-03-02T12:48:21Z","timestamp":1677761301000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-27762-7_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031277610","9783031277627"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-27762-7_27","relation":{},"ISSN":["2367-4512","2367-4520"],"issn-type":[{"type":"print","value":"2367-4512"},{"type":"electronic","value":"2367-4520"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"1 March 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AICV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The International Conference on Artificial Intelligence and Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Marrakesh","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Morocco","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 March 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 March 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aicv12023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/egyptscience.net\/AICV2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}