{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T15:59:04Z","timestamp":1773417544952,"version":"3.50.1"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2021,5,3]],"date-time":"2021-05-03T00:00:00Z","timestamp":1620000000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,5,3]],"date-time":"2021-05-03T00:00:00Z","timestamp":1620000000000},"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":[[2021,11]]},"DOI":"10.1007\/s11760-021-01916-3","type":"journal-article","created":{"date-parts":[[2021,5,3]],"date-time":"2021-05-03T20:07:16Z","timestamp":1620072436000},"page":"1757-1765","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["Pose estimation at night in infrared images using a lightweight multi-stage attention network"],"prefix":"10.1007","volume":"15","author":[{"given":"Ying","family":"Zang","sequence":"first","affiliation":[]},{"given":"Chunpeng","family":"Fan","sequence":"additional","affiliation":[]},{"given":"Zeyu","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Dongsheng","family":"Yang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,5,3]]},"reference":[{"key":"1916_CR1","first-page":"1097","volume":"pp","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Bartlett, P., Pereira, F., Burges, C., Bottou, L., Weinberger, K (eds.) Advances in Neural Information Processing Systems pp, 1097\u20131105 (2012)","journal-title":"In: Bartlett, P., Pereira, F., Burges, C., Bottou, L., Weinberger, K (eds.) Advances in Neural Information Processing Systems"},{"key":"1916_CR2","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556 (2014)"},{"key":"1916_CR3","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"1916_CR4","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S.: 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":"1916_CR5","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 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"1916_CR6","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., Berg, A.C.S.S.D.: Single Shot MultiBox Detector. arXiv: 1512.02325 (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"1916_CR7","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. arXiv:1411.4038 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"issue":"12","key":"1916_CR8","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","volume":"39","author":"V Badrinarayanan","year":"2016","unstructured":"Badrinarayanan, V., Kendall, A., Cipolla, R.: Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(12), 2481\u20132495 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1916_CR9","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. arXiv:1612.01105 (2017)","DOI":"10.1109\/CVPR.2017.660"},{"key":"1916_CR10","doi-asserted-by":"crossref","unstructured":"Toshev, A., Sezedy, C.: Deeppose: Human pose estimation via deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1653\u20131660 (2014)","DOI":"10.1109\/CVPR.2014.214"},{"key":"1916_CR11","doi-asserted-by":"crossref","unstructured":"Pfister, T., Charlse, J., Zisserman, A.: Flowing convnets for human pose estimation in videos. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1913\u20131921 (2015)","DOI":"10.1109\/ICCV.2015.222"},{"key":"1916_CR12","doi-asserted-by":"crossref","unstructured":"Wei, S.E., Ramakrishna, V., Kanade, T.: Convolutional pose machines. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4724\u20134732 (2016)","DOI":"10.1109\/CVPR.2016.511"},{"key":"1916_CR13","doi-asserted-by":"crossref","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: European Conference on Computer Vision, pp. 483\u2013499 (2016)","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"1916_CR14","doi-asserted-by":"crossref","unstructured":"Papandreou, G., Zhu, T., Kanazawa, N., Toshev, A., Tompson, J., Bregler, C., Murphy, K.: Towards accurate multi-person pose estimation in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4903\u20134911 (2017)","DOI":"10.1109\/CVPR.2017.395"},{"key":"1916_CR15","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"key":"1916_CR16","doi-asserted-by":"crossref","unstructured":"Tang, Z., Peng, X., Geng, S., Wu, L., Zhang, S., Metaxas, D.: Quantized densely connected u-nets for efficient landmark localization. In: Proceedings of the European Conference on Computer Vision, pp. 339\u2013354 (2018)","DOI":"10.1007\/978-3-030-01219-9_21"},{"key":"1916_CR17","doi-asserted-by":"crossref","unstructured":"Debnath, B., O\u2019Brien, M., Yamaguchi, M., Behera, A.: Adapting mobilenets for mobile based upper body pose estimation. In: Proceedings of the IEEE Conference on Advanced Video and Signal Based Surveillance, pp. 1\u20136 (2018)","DOI":"10.1109\/AVSS.2018.8639378"},{"key":"1916_CR18","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, Wang, W., Weyand, T., Andreetto, M., Adam, H.: Mobilenets: Ecient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"1916_CR19","unstructured":"Feng, Z., Xiatian, Z., Mao, Y.: Fast human pose estimation. In: Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20138 (2019)"},{"key":"1916_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1117\/1.JEI.27.4.043035","volume":"17","author":"D Heo","year":"2018","unstructured":"Heo, D., Lee, E., Ko, B.C.: Pedestrian detection at night using deep neural networks and saliency maps. Electron. Imaging 17, 1\u20139 (2018)","journal-title":"Electron. Imaging"},{"key":"1916_CR21","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: YOLO9000: Better, faster, stronger. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, pp. 7263\u20137271 (2017)","DOI":"10.1109\/CVPR.2017.690"},{"key":"1916_CR22","doi-asserted-by":"publisher","first-page":"135023","DOI":"10.1109\/ACCESS.2019.2932749","volume":"7","author":"Z Cao","year":"2019","unstructured":"Cao, Z., Yang, H., Zhao, J., Pan, X., Zhang, L., Liu, Z.: A new region proposal network for far-infrared pedestrian detection. IEEE Access 7, 135023\u2013135030 (2019)","journal-title":"IEEE Access"},{"key":"1916_CR23","doi-asserted-by":"publisher","first-page":"34","DOI":"10.3390\/s20010034","volume":"20","author":"J Park","year":"2020","unstructured":"Park, J., Chen, J., Cho, Y.K., Kang, D.Y., Son, B.J.: CNN-based person detection using infrared images for night-time intrusion warning systems. Sensors 20, 34 (2020)","journal-title":"Sensors"},{"key":"1916_CR24","doi-asserted-by":"publisher","first-page":"809","DOI":"10.3390\/app10030809","volume":"10","author":"Y Chen","year":"2020","unstructured":"Chen, Y., Shin, H.: Pedestrian detection at night in infrared images using an attention-guided encoder-decoder convolutional neural network. Appl. Sci. 10, 809 (2020). https:\/\/doi.org\/10.3390\/app10030809","journal-title":"Appl. Sci."},{"key":"1916_CR25","doi-asserted-by":"crossref","unstructured":"Howard, A., Sandler, M., Chu, G., et\u00a0al.: Searching for MobileNetV3. In: IEEE International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00140"},{"key":"1916_CR26","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., Kweon, I.S.: CBAM: convolutional block attention module. European conference on computer vision (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"1916_CR27","doi-asserted-by":"crossref","unstructured":"Shrivastava, A., Gupta, A., Girshick, R.: Training regionbased object detectors with online hard example mining. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 761\u2013769 (2016)","DOI":"10.1109\/CVPR.2016.89"},{"key":"1916_CR28","doi-asserted-by":"crossref","unstructured":"Andriluka, M., PishchulinL, P., Gehler, Schiele, B.: 2D human pose estimation: New benchmark and state of the art analysis. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.471"},{"key":"1916_CR29","unstructured":"https:\/\/challenger.ai\/datasets\/keypoint"},{"key":"1916_CR30","doi-asserted-by":"crossref","unstructured":"Carreira, J., Agrawal, P., Fragkiadaki, K., Malik, J.: Human pose estimation with iterative error feedback. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4733\u20134742 (2016)","DOI":"10.1109\/CVPR.2016.512"},{"key":"1916_CR31","doi-asserted-by":"crossref","unstructured":"Sun, X., Shang, J., Liang, S., Wei, Y.: Compositional human pose regression. In: Proceedings of the IEEE International Conference on Computer Vision, p. 7 (2017)","DOI":"10.1109\/ICCV.2017.284"},{"key":"1916_CR32","first-page":"1799","volume":"pp.","author":"JJ Tompson","year":"2014","unstructured":"Tompson, J.J., Jain, A., LeCun, Y., Bregler, C.: Joint training of a convolutional network and a graphical model for human pose estimation. In: Cortes, C., Welling, M., Lawrence, N., Ghahramani, Z., Weinberger, K (eds.) Advances in Neural Information Processing Systems pp., 1799\u20131807 (2014)","journal-title":"In: Cortes, C., Welling, M., Lawrence, N., Ghahramani, Z., Weinberger, K (eds.) Advances in Neural Information Processing Systems"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-021-01916-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-021-01916-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-021-01916-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,10]],"date-time":"2021-10-10T08:03:06Z","timestamp":1633852986000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-021-01916-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,3]]},"references-count":32,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2021,11]]}},"alternative-id":["1916"],"URL":"https:\/\/doi.org\/10.1007\/s11760-021-01916-3","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,3]]},"assertion":[{"value":"21 November 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 February 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 April 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 May 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}