{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T00:54:38Z","timestamp":1760316878749,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031882166"},{"type":"electronic","value":"9783031882173"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-88217-3_21","type":"book-chapter","created":{"date-parts":[[2025,5,26]],"date-time":"2025-05-26T10:23:42Z","timestamp":1748255022000},"page":"284-292","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Multi-modal Object Detection with\u00a0Data Augmentation, Focal Loss, and\u00a0Model Ensembling"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-3445-6067","authenticated-orcid":false,"given":"Junyu","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1073-1150","authenticated-orcid":false,"given":"Yuhao","family":"Chao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9297-7729","authenticated-orcid":false,"given":"Jie","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,27]]},"reference":[{"key":"21_CR1","doi-asserted-by":"publisher","unstructured":"Ghiasi, G., et al.: Simple copy-paste is a strong data augmentation method for instance segmentation. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Los Alamitos, CA, USA, pp. 2917\u20132927. IEEE Computer Society (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.00294, https:\/\/doi.ieeecomputersociety.org\/10.1109\/CVPR46437.2021.00294","DOI":"10.1109\/CVPR46437.2021.00294"},{"key":"21_CR2","doi-asserted-by":"publisher","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 (CVPR), pp. 770\u2013778 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"issue":"6","key":"21_CR3","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Commun. ACM 60(6), 84\u201390 (2017). https:\/\/doi.org\/10.1145\/3065386","journal-title":"Commun. ACM"},{"key":"21_CR4","doi-asserted-by":"crossref","unstructured":"Li, H., Wu, X.J., Kittler, J.: Infrared and visible image fusion using a deep learning framework. In: 2018 24th International Conference on Pattern Recognition (ICPR), pp. 2705\u20132710. IEEE (2018)","DOI":"10.1109\/ICPR.2018.8546006"},{"issue":"2","key":"21_CR5","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1109\/TPAMI.2018.2858826","volume":"42","author":"TY Lin","year":"2020","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. IEEE Trans. Pattern Anal. Mach. Intell. 42(2), 318\u2013327 (2020). https:\/\/doi.org\/10.1109\/TPAMI.2018.2858826","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation (2018). https:\/\/arxiv.org\/abs\/1803.01534","DOI":"10.1109\/CVPR.2018.00913"},{"key":"21_CR7","doi-asserted-by":"publisher","unstructured":"Paolanti, M., Frontoni, E.: Multidisciplinary pattern recognition applications: a review. Comput. Sci. Rev. 37, 100276 (2020). https:\/\/doi.org\/10.1016\/j.cosrev.2020.100276, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S1574013719300899","DOI":"10.1016\/j.cosrev.2020.100276"},{"key":"21_CR8","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection (2016). https:\/\/arxiv.org\/abs\/1506.02640","DOI":"10.1109\/CVPR.2016.91"},{"key":"21_CR9","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: Proceedings of the International Conference on Learning Representations (ICLR) (2015). https:\/\/arxiv.org\/abs\/1409.1556, arXiv preprint arXiv:1409.1556"},{"key":"21_CR10","doi-asserted-by":"crossref","unstructured":"Solovyev, R., Wang, W., Gabruseva, T.: Weighted boxes fusion: Ensembling boxes from different object detection models. Image Vis. Comput.\u00a01\u20136 (2021)","DOI":"10.1016\/j.imavis.2021.104117"},{"issue":"1","key":"21_CR11","doi-asserted-by":"publisher","first-page":"3","DOI":"10.11834\/jig.220422","volume":"28","author":"L Tang","year":"2023","unstructured":"Tang, L., Zhang, H., Xu, H., Ma, J.: Deep learning-based image fusion: a survey. J. Image Graphics 28(1), 3\u201336 (2023)","journal-title":"J. Image Graphics"},{"key":"21_CR12","doi-asserted-by":"publisher","unstructured":"Theodoridis, S., Koutroumbas, K.: Pattern Recognition. Academic Press, 4th edn. (2009). https:\/\/doi.org\/10.1016\/B978-1-59749-272-0.X0001-2","DOI":"10.1016\/B978-1-59749-272-0.X0001-2"},{"key":"21_CR13","doi-asserted-by":"publisher","unstructured":"Varghese, R., M., S.: Yolov8: a novel object detection algorithm with enhanced performance and robustness. In: 2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems (ADICS), pp.\u00a01\u20136 (2024) https:\/\/doi.org\/10.1109\/ADICS58448.2024.10533619","DOI":"10.1109\/ADICS58448.2024.10533619"},{"key":"21_CR14","unstructured":"Wang, A., et al.: Yolov10: real-time end-to-end object detection. arXiv:abs\/2405.14458 (2024). https:\/\/api.semanticscholar.org\/CorpusID:269983404"},{"key":"21_CR15","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Liao, H.Y.M., Yeh, I.H., Wu, Y.H., Chen, P.Y., Hsieh, J.W.: CSPNet: a new backbone that can enhance learning capability of CNN (2019). https:\/\/arxiv.org\/abs\/1911.11929","DOI":"10.1109\/CVPRW50498.2020.00203"},{"key":"21_CR16","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Yeh, I.H., Liao, H.: Yolov9: learning what you want to learn using programmable gradient information. arXiv:abs\/2402.13616 (2024). https:\/\/api.semanticscholar.org\/CorpusID:267770251","DOI":"10.1007\/978-3-031-72751-1_1"},{"issue":"4","key":"21_CR17","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1007\/s13244-018-0639-9","volume":"9","author":"R Yamashita","year":"2018","unstructured":"Yamashita, R., Nishio, M., Do, R., Togashi, K.: Convolutional neural networks: an overview and application in radiology. Insights Imaging 9(4), 611\u2013629 (2018). https:\/\/doi.org\/10.1007\/s13244-018-0639-9","journal-title":"Insights Imaging"},{"key":"21_CR18","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: Mixup: beyond empirical risk minimization. In: International Conference on Learning Representations (2018)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition. ICPR 2024 International Workshops and Challenges"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-88217-3_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T19:14:09Z","timestamp":1760296449000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-88217-3_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031882166","9783031882173"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-88217-3_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"27 May 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}