{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T18:58:41Z","timestamp":1778180321537,"version":"3.51.4"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031092817","type":"print"},{"value":"9783031092824","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-09282-4_4","type":"book-chapter","created":{"date-parts":[[2022,5,28]],"date-time":"2022-05-28T13:05:49Z","timestamp":1653743149000},"page":"40-52","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Comparative Study of Activation Functions and Their Impact on the YOLOv5 Object Detection Model"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2167-6101","authenticated-orcid":false,"given":"John","family":"Doherty","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5642-6850","authenticated-orcid":false,"given":"Bryan","family":"Gardiner","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4551-1272","authenticated-orcid":false,"given":"Emmett","family":"Kerr","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0642-2357","authenticated-orcid":false,"given":"Nazmul","family":"Siddique","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3623-6723","authenticated-orcid":false,"given":"Sunilkumar S.","family":"Manvi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,5,29]]},"reference":[{"key":"4_CR1","doi-asserted-by":"crossref","unstructured":"Sultana, F., Sufian, A., Dutta, P.: A review of object detection models based on convolutional neural network. In: Advances in Intelligent Systems and Computing, pp. 1\u201316 (2020)","DOI":"10.1007\/978-981-15-4288-6_1"},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Soviany, P., Ionescu, R.T.: Optimizing the trade-off between single-stage and two-stage deep object detectors using image difficulty prediction. In: 20th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing, SYNASC (2018)","DOI":"10.1109\/SYNASC.2018.00041"},{"issue":"15","key":"4_CR3","doi-asserted-by":"publisher","first-page":"3651","DOI":"10.1049\/iet-ipr.2020.0077","volume":"14","author":"Q Hou","year":"2020","unstructured":"Hou, Q., Xing, J.: KSSD: single\u2010stage multi\u2010object detection algorithm with higher accuracy. IET Image Process. 14(15), 3651\u20133661 (2020). https:\/\/doi.org\/10.1049\/iet-ipr.2020.0077","journal-title":"IET Image Process."},{"key":"4_CR4","doi-asserted-by":"publisher","first-page":"20828","DOI":"10.1109\/ACCESS.2021.3054879","volume":"9","author":"S Kim","year":"2021","unstructured":"Kim, S., Kim, H.: Zero-centered fixed-point quantization with iterative retraining for deep convolutional neural network-based object detectors. IEEE Access 9, 20828\u201320839 (2021). https:\/\/doi.org\/10.1109\/ACCESS.2021.3054879","journal-title":"IEEE Access"},{"key":"4_CR5","doi-asserted-by":"publisher","first-page":"102495","DOI":"10.1016\/j.bspc.2021.102495","volume":"66","author":"A Shakarami","year":"2021","unstructured":"Shakarami, A., Menhaj, M.B., Mahdavi-Hormat, A., Tarrah, H.: A fast and yet efficient YOLOv3 for blood cell detection. Biomed. Sig. Process. Control 66, 102495 (2021). https:\/\/doi.org\/10.1016\/j.bspc.2021.102495","journal-title":"Biomed. Sig. Process. Control"},{"key":"4_CR6","series-title":"Studies in Computational Intelligence","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-030-31760-7_1","volume-title":"Deep Learning: Algorithms and Applications","author":"M Goyal","year":"2020","unstructured":"Goyal, M., Goyal, R., Reddy, P.V., Lall, B.: Activation functions. In: Pedrycz, W., Chen, S.-M. (eds.) Deep Learning: Algorithms and Applications. SCI, vol. 865, pp. 1\u201330. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-31760-7_1"},{"key":"4_CR7","series-title":"Lecture Notes in Networks and Systems","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1007\/978-981-15-7106-0_52","volume-title":"Machine Learning for Predictive Analysis","author":"S Patel","year":"2021","unstructured":"Patel, S., Patel, A.: Object detection with convolutional neural networks. In: Joshi, A., Khosravy, M., Gupta, N. (eds.) Machine Learning for Predictive Analysis. LNNS, vol. 141, pp. 529\u2013539. Springer, Singapore (2021). https:\/\/doi.org\/10.1007\/978-981-15-7106-0_52"},{"key":"4_CR8","unstructured":"Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press (2016)"},{"key":"4_CR9","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1007\/s11063-012-9241-1","volume":"37","author":"S Li","year":"2013","unstructured":"Li, S., Chen, S., Liu, B.: Accelerating a recurrent neural network to finite-time convergence for solving time-varying Sylvester equation by using a sign-bi-power activation function. Neural Process. Lett. 37, 189\u2013205 (2013). https:\/\/doi.org\/10.1007\/s11063-012-9241-1","journal-title":"Neural Process. Lett."},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779\u2013788. IEEE (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"4_CR11","unstructured":"Jocher, G.: YOLOv5 Github. https:\/\/github.com\/ultralytics\/yolov5"},{"key":"4_CR12","doi-asserted-by":"crossref","unstructured":"Feng, C., Zhong, Y., Gao, Y., Scott, M., Huang, W.: TOOD: task-aligned one-stage object detection. In: IEEE\/CVF International Conference on Computer Vision, pp. 3510\u20133519 (2021)","DOI":"10.1109\/ICCV48922.2021.00349"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., He, T.: FCOS: fully convolutional one-stage object detection. In: IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9626\u20139635. IEEE (2019)","DOI":"10.1109\/ICCV.2019.00972"},{"key":"4_CR14","doi-asserted-by":"publisher","first-page":"107334","DOI":"10.1016\/j.patcog.2020.107334","volume":"105","author":"Q Chen","year":"2020","unstructured":"Chen, Q., Wang, P., Cheng, A., Wang, W., Zhang, Y., Cheng, J.: Robust one-stage object detection with location-aware classifiers. Pattern Recogn. 105, 107334 (2020). https:\/\/doi.org\/10.1016\/j.patcog.2020.107334","journal-title":"Pattern Recogn."},{"key":"4_CR15","unstructured":"Hui, J.: Real-time Object Detection with YOLO, YOLOv2 and now YOLOv3. https:\/\/jonathan-hui.medium.com\/real-time-object-detection-with-yolo-yolov2-28b1b93e2088"},{"key":"4_CR16","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Liang, D., Zhang, S., Huang, X., Li, B., Hu, S.: Traffic-sign detection and classification in the wild. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2110\u20132118 (2016)","DOI":"10.1109\/CVPR.2016.232"},{"key":"4_CR17","doi-asserted-by":"publisher","first-page":"64145","DOI":"10.1109\/ACCESS.2020.2984554","volume":"8","author":"H Zhang","year":"2020","unstructured":"Zhang, H., et al.: Real-time detection method for small traffic signs based on Yolov3. IEEE Access 8, 64145\u201364156 (2020). https:\/\/doi.org\/10.1109\/ACCESS.2020.2984554","journal-title":"IEEE Access"},{"issue":"11","key":"4_CR18","doi-asserted-by":"publisher","first-page":"6533","DOI":"10.1007\/s00521-019-04086-z","volume":"32","author":"Z Liang","year":"2019","unstructured":"Liang, Z., Shao, J., Zhang, D., Gao, L.: Traffic sign detection and recognition based on pyramidal convolutional networks. Neural Comput. Appl. 32(11), 6533\u20136543 (2019). https:\/\/doi.org\/10.1007\/s00521-019-04086-z","journal-title":"Neural Comput. Appl."},{"key":"4_CR19","doi-asserted-by":"crossref","unstructured":"Wang, G., Ren, G., Wu, Z., Zhao, Y., Jiang, L.: A robust, coarse-to-fine traffic sign detection method. In: International Joint Conference on Neural Networks (IJCNN), pp. 1\u20135. IEEE (2013)","DOI":"10.1109\/IJCNN.2013.6706812"},{"key":"4_CR20","unstructured":"Bochkovskiy, A., Wang, C.-Y., Liao, H.-Y.M.: YOLOv4: optimal speed and accuracy of object detection. arXiv (2020)"},{"key":"4_CR21","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8759\u20138768. IEEE (2018)","DOI":"10.1109\/CVPR.2018.00913"},{"key":"4_CR22","doi-asserted-by":"crossref","unstructured":"Tan, S., Lu, G., Jiang, Z., Huang, L.: Improved YOLOv5 network model and application in safety helmet detection. In: IEEE International Conference on Intelligence and Safety for Robotics (ISR), pp. 330\u2013333. (2021)","DOI":"10.1109\/ISR50024.2021.9419561"},{"key":"4_CR23","unstructured":"Nelson, J.: YOLOv5 is here: state-of-the-art object detection at 140 FPS. https:\/\/blog.roboflow.com\/yolov5-is-here\/. Accessed 11 Dec 2021"},{"key":"4_CR24","unstructured":"Ampadu, H.: Yolov3 and Yolov4 in object detection. https:\/\/ai-pool.com\/a\/s\/yolov3-and-yolov4-in-object-detection"},{"key":"4_CR25","unstructured":"Solawetz, J., Nelson, J.: YOLOv5 improvement strategy. https:\/\/blog.roboflow.com\/how-to-train-yolov5-on-a-custom-dataset\/. Accessed 10 Dec 2021"},{"key":"4_CR26","unstructured":"Ramachandran, P., Zoph, N., Le, Q. V.: Searching for activation functions. In: 6th International Conference on Learning Representations, ICLR 2018 - Workshop Track Proceedings (2018)"},{"key":"4_CR27","unstructured":"Ye, A.: Swish: booting ReLU from the activation function throne. https:\/\/towardsdatascience.com\/swish-booting-relu-from-the-activation-function-throne-78f87e5ab6eb. Accessed 13 Dec 2021"},{"key":"4_CR28","unstructured":"Nwankpa, C., Ijomah, W., Gachagan, A., Marshall, S.: Activation Functions: Comparison of trends in Practice and Research for Deep Learning (2018)"},{"key":"4_CR29","doi-asserted-by":"crossref","unstructured":"Shen, F., Gan, R., Zeng, G.: Weighted residuals for very deep networks. In: 3rd International Conference on Systems and Informatics (ICSAI), pp. 936\u2013941 (2016)","DOI":"10.1109\/ICSAI.2016.7811085"},{"key":"4_CR30","doi-asserted-by":"crossref","unstructured":"Xu, J., Li, Z., Du, B., Zhang, M., Liu, J.: Reluplex made more practical: leaky ReLU. In: IEEE Symposium on Computers and Communications (ISCC), pp. 1\u20137 (2020)","DOI":"10.1109\/ISCC50000.2020.9219587"},{"key":"4_CR31","doi-asserted-by":"crossref","unstructured":"Khalid, M., Baber, J., Kasi, M.K., Bakhtyar, M., Devi, V., Sheikh, N.: Empirical evaluation of activation functions in deep convolution neural network for facial expression recognition. In: 43rd International Conference on Telecommunications and Signal Processing (TSP), pp. 204\u2013207 (2020)","DOI":"10.1109\/TSP49548.2020.9163446"},{"key":"4_CR32","doi-asserted-by":"crossref","unstructured":"Qiu, S., Xu, X., Cai, B.: FReLU: flexible rectified linear units for improving convolutional neural networks. In: 24th International Conference on Pattern Recognition (ICPR), pp. 1223\u20131228 (2018)","DOI":"10.1109\/ICPR.2018.8546022"},{"key":"4_CR33","doi-asserted-by":"crossref","unstructured":"Howard, A., et al.: Searching for MobileNetV3. In: IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1314\u20131324. IEEE (2019)","DOI":"10.1109\/ICCV.2019.00140"},{"issue":"1","key":"4_CR34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-019-0233-0","volume":"6","author":"G Castaneda","year":"2019","unstructured":"Castaneda, G., Morris, P., Khoshgoftaar, T.M.: Evaluation of maxout activations in deep learning across several big data domains. J. Big Data 6(1), 1\u201335 (2019). https:\/\/doi.org\/10.1186\/s40537-019-0233-0","journal-title":"J. Big Data"},{"key":"4_CR35","doi-asserted-by":"crossref","unstructured":"Ma, N., Zhang, X., Liu, M., Sun, J.: Activate or not: learning customized activation (2020)","DOI":"10.1109\/CVPR46437.2021.00794"},{"key":"4_CR36","unstructured":"Misra, D.: Mish: a self regularized non-monotonic activation function (2019)"},{"key":"4_CR37","unstructured":"Wright, L.: Meet Mish\u2014new state of the art AI activation function. The successor to ReLU? https:\/\/lessw.medium.com\/meet-mish-new-state-of-the-art-ai-activation-function-the-successor-to-relu-846a6d93471f. Accessed 09 December 2021"},{"key":"4_CR38","unstructured":"Northern Ireland High Performance Computing. https:\/\/www.ni-hpc.ac.uk\/about\/"},{"key":"4_CR39","doi-asserted-by":"crossref","unstructured":"Rajendran, S.P., Shine, L., Pradeep, R., Vijayaraghavan, S.: Real-time traffic sign recognition using YOLOv3 based detector. In: International Conference on Computing, Communication and Networking Technologies, ICCCNT (2019)","DOI":"10.1109\/ICCCNT45670.2019.8944890"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-09282-4_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,28]],"date-time":"2022-05-28T13:06:13Z","timestamp":1653743173000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-09282-4_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031092817","9783031092824"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-09282-4_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"29 May 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPRAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition and Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Paris","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","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 June 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 June 2022","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":"icprai2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icprai2022.sciencesconf.org\/1.6.If","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"152","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"98","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"64% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.6","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"6","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}