{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,3]],"date-time":"2025-05-03T06:46:03Z","timestamp":1746254763980,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":22,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789811978661"},{"type":"electronic","value":"9789811978678"}],"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\/978-981-19-7867-8_59","type":"book-chapter","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T12:02:18Z","timestamp":1683288138000},"page":"747-759","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Target Detection Using Transformer: A Study Using DETR"],"prefix":"10.1007","author":[{"given":"Akhilesh","family":"Kumar","sequence":"first","affiliation":[]},{"given":"Satish Kumar","family":"Singh","sequence":"additional","affiliation":[]},{"given":"Shiv Ram","family":"Dubey","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,5,6]]},"reference":[{"key":"59_CR1","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation (2013). (Online). Available: http:\/\/arxiv.org\/abs\/1311.2524","DOI":"10.1109\/CVPR.2014.81"},{"key":"59_CR2","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN (2015). (Online). Available: http:\/\/arxiv.org\/abs\/1504.08083","DOI":"10.1109\/ICCV.2015.169"},{"issue":"6","key":"59_CR3","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2017). https:\/\/doi.org\/10.1109\/TPAMI.2016.2577031","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"2","key":"59_CR4","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1109\/TPAMI.2018.2844175","volume":"42","author":"K He","year":"2020","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. IEEE Trans. Pattern Anal. Mach. Intell. 42(2), 386\u2013397 (2020). https:\/\/doi.org\/10.1109\/TPAMI.2018.2844175","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"2","key":"59_CR5","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","volume":"104","author":"JRR Uijlings","year":"2013","unstructured":"Uijlings, J.R.R., van de Sande, K.E.A., Gevers, T., Smeulders, A.W.M.: Selective search for object recognition. Int. J. Comput. Vision 104(2), 154\u2013171 (2013). https:\/\/doi.org\/10.1007\/s11263-013-0620-5","journal-title":"Int. J. Comput. Vision"},{"key":"59_CR6","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You Only Look Once: Unified, Real-Time Object Detection (2015) (Online). Available: http:\/\/arxiv.org\/abs\/1506.02640","DOI":"10.1109\/CVPR.2016.91"},{"key":"59_CR7","unstructured":"Redmon, J., Farhadi, A.: YOLOv3: An incremental improvement. arXiv (2018)"},{"key":"59_CR8","doi-asserted-by":"publisher","unstructured":"Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: Proceedings\u201430th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, vol. 2017-Janua, pp. 6517\u20136525 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.690.","DOI":"10.1109\/CVPR.2017.690"},{"key":"59_CR9","doi-asserted-by":"publisher","unstructured":"Liu, W., et al.: SSD: single shot multibox detector. In: Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics), vol. 9905 LNCS, pp. 21\u201337 (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"59_CR10","unstructured":"Vaswani, A., et al.: Attention Is All You Need (2017). (Online). Available: http:\/\/arxiv.org\/abs\/1706.03762"},{"key":"59_CR11","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-End Object Detection with Transformers (2020). (Online). Available: http:\/\/arxiv.org\/abs\/2005.12872","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"59_CR12","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: Deformable Transformers for End-to-End Object Detection (2020). (Online). Available: http:\/\/arxiv.org\/abs\/2010.04159"},{"key":"59_CR13","unstructured":"El-Nouby, A., et al.: XCiT: Cross-Covariance Image Transformers. (2021). (Online). Available: http:\/\/arxiv.org\/abs\/2106.09681"},{"key":"59_CR14","unstructured":"Li, Y., Zhang, K., Cao, J., Timofte, R., van Gool, L.: LocalViT: Bringing Locality to Vision Transformers (2021). (Online). Available: http:\/\/arxiv.org\/abs\/2104.05707"},{"key":"59_CR15","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions (2021). (Online). Available: http:\/\/arxiv.org\/abs\/2102.12122","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"59_CR16","doi-asserted-by":"crossref","unstructured":"Zhang, P., et al.: Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding (2021). (Online). Available: http:\/\/arxiv.org\/abs\/2103.15358","DOI":"10.1109\/ICCV48922.2021.00299"},{"key":"59_CR17","doi-asserted-by":"crossref","unstructured":"Dubey, S.R., Singh, S.K., Chu, W.-T.: Vision Transformer Hashing for Image Retrieval (2021). (Online). Available: http:\/\/arxiv.org\/abs\/2109.12564","DOI":"10.1109\/ICME52920.2022.9859900"},{"key":"59_CR18","unstructured":"Mu\u00f1oz, E.: Attention is all you need: Discovering the Transformer paper (2020)"},{"key":"59_CR19","doi-asserted-by":"publisher","unstructured":"Lin, T.Y., et al.: Microsoft COCO: common objects in context. In: Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics), vol. 8693 LNCS, no. PART 5, pp. 740\u2013755 (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"59_CR20","unstructured":"Yu, J., Li, J., Yu, Z., Huang, Q.: Multimodal Transformer with Multi-View Visual Representation for Image Captioning (2019). (Online). Available: http:\/\/arxiv.org\/abs\/1905.07841"},{"issue":"2","key":"59_CR21","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vision 88(2), 303\u2013338 (2010). https:\/\/doi.org\/10.1007\/s11263-009-0275-4","journal-title":"Int. J. Comput. Vision"},{"key":"59_CR22","unstructured":"fmassa et al.: facebookresearch\/detr (2020)"}],"container-title":["Lecture Notes in Networks and Systems","Computer Vision and Machine Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-19-7867-8_59","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T12:10:35Z","timestamp":1683288635000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-19-7867-8_59"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9789811978661","9789811978678"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-981-19-7867-8_59","relation":{},"ISSN":["2367-3370","2367-3389"],"issn-type":[{"type":"print","value":"2367-3370"},{"type":"electronic","value":"2367-3389"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"6 May 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}