{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T15:53:55Z","timestamp":1770911635249,"version":"3.50.1"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2023,7,10]],"date-time":"2023-07-10T00:00:00Z","timestamp":1688947200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,7,10]],"date-time":"2023-07-10T00:00:00Z","timestamp":1688947200000},"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":["Vis Comput"],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1007\/s00371-023-02988-7","type":"journal-article","created":{"date-parts":[[2023,7,10]],"date-time":"2023-07-10T06:01:56Z","timestamp":1688968916000},"page":"2819-2831","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["MAPD: multi-receptive field and attention mechanism for multispectral pedestrian detection"],"prefix":"10.1007","volume":"40","author":[{"given":"Ying","family":"Zang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Runlong","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1361-1500","authenticated-orcid":false,"given":"Wenjun","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingshan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,7,10]]},"reference":[{"key":"2988_CR1","doi-asserted-by":"crossref","unstructured":"Hwang, S., Park, J., Kim, N., Choi, Y., So\u00a0Kweon, I.: Multispectral pedestrian detection: Benchmark dataset and baseline. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1037\u20131045 (2015)","DOI":"10.1109\/CVPR.2015.7298706"},{"key":"2988_CR2","doi-asserted-by":"crossref","unstructured":"Liu, J., Zhang, S., Wang, S., Metaxas, D.N.: Multispectral deep neural networks for pedestrian detection. arXiv preprint arXiv:1611.02644 (2016)","DOI":"10.5244\/C.30.73"},{"key":"2988_CR3","doi-asserted-by":"crossref","unstructured":"Konig, D., Adam, M., Jarvers, C., Layher, G., Neumann, H., Teutsch, M.: Fully convolutional region proposal networks for multispectral person detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 49\u201356 (2017)","DOI":"10.1109\/CVPRW.2017.36"},{"key":"2988_CR4","doi-asserted-by":"crossref","unstructured":"Xu, D., Ouyang, W., Ricci, E., Wang, X., Sebe, N.: Learning cross-modal deep representations for robust pedestrian detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5363\u20135371 (2017)","DOI":"10.1109\/CVPR.2017.451"},{"key":"2988_CR5","unstructured":"Li, C., Song, D., Tong, R., Tang, M.: Multispectral pedestrian detection via simultaneous detection and segmentation. arXiv preprint arXiv:1808.04818 (2018)"},{"key":"2988_CR6","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1016\/j.patcog.2018.03.007","volume":"80","author":"K Park","year":"2018","unstructured":"Park, K., Kim, S., Sohn, K.: Unified multi-spectral pedestrian detection based on probabilistic fusion networks. Pattern Recogn. 80, 143\u2013155 (2018)","journal-title":"Pattern Recogn."},{"key":"2988_CR7","unstructured":"Zheng, Y., Izzat, I.H., Ziaee, S.: Gfd-ssd: gated fusion double ssd for multispectral pedestrian detection. arXiv preprint arXiv:1903.06999 (2019)"},{"key":"2988_CR8","doi-asserted-by":"crossref","unstructured":"Zhang, L., Zhu, X., Chen, X., Yang, X., Lei, Z., Liu, Z.: Weakly aligned cross-modal learning for multispectral pedestrian detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5127\u20135137 (2019)","DOI":"10.1109\/ICCV.2019.00523"},{"key":"2988_CR9","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1016\/j.patcog.2018.08.005","volume":"85","author":"C Li","year":"2019","unstructured":"Li, C., Song, D., Tong, R., Tang, M.: Illumination-aware faster r-cnn for robust multispectral pedestrian detection. Pattern Recogn. 85, 161\u2013171 (2019)","journal-title":"Pattern Recogn."},{"key":"2988_CR10","doi-asserted-by":"crossref","unstructured":"Zhou, K., Chen, L., Cao, X.: Improving multispectral pedestrian detection by addressing modality imbalance problems. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XVIII 16, pp. 787\u2013803 (2020)","DOI":"10.1007\/978-3-030-58523-5_46"},{"issue":"4","key":"2988_CR11","doi-asserted-by":"publisher","first-page":"7846","DOI":"10.1109\/LRA.2021.3099870","volume":"6","author":"J Kim","year":"2021","unstructured":"Kim, J., Kim, H., Kim, T., Kim, N., Choi, Y.: Mlpd: multi-label pedestrian detector in multispectral domain. IEEE Robot. Autom. Lett. 6(4), 7846\u20137853 (2021)","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"9","key":"2988_CR12","doi-asserted-by":"publisher","first-page":"1627","DOI":"10.1109\/TPAMI.2009.167","volume":"32","author":"PF Felzenszwalb","year":"2009","unstructured":"Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. IEEE Trans. Pattern Anal. Mach. Intell. 32(9), 1627\u20131645 (2009)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2988_CR13","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., Berg, A.C.: Ssd: Single shot multibox detector. In: Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part I 14, pp. 21\u201337 (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"2988_CR14","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. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"2988_CR15","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: Convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18, pp. 234\u2013241 (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"2988_CR16","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8759\u20138768 (2018)","DOI":"10.1109\/CVPR.2018.00913"},{"key":"2988_CR17","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhang, S., Yu, Z., Feng, L., Zhang, W.: Scale-equalizing pyramid convolution for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13359\u201313368 (2020)","DOI":"10.1109\/CVPR42600.2020.01337"},{"key":"2988_CR18","doi-asserted-by":"crossref","unstructured":"Zhang, H., Fromont, E., Lef\u00e8vre, S., Avignon, B.: Guided attentive feature fusion for multispectral pedestrian detection. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 72\u201380 (2021)","DOI":"10.1109\/WACV48630.2021.00012"},{"key":"2988_CR19","doi-asserted-by":"crossref","unstructured":"Chen, Y.-T., Shi, J., Ye, Z., Mertz, C., Ramanan, D., Kong, S.: Multimodal object detection via probabilistic ensembling. In: Computer Vision\u2013ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part IX, pp. 139\u2013158 (2022)","DOI":"10.1007\/978-3-031-20077-9_9"},{"key":"2988_CR20","doi-asserted-by":"crossref","unstructured":"Liu, D., Cui, Y., Yan, L., Mousas, C., Yang, B., Chen, Y.: Densernet: Weakly supervised visual localization using multi-scale feature aggregation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 6101\u20136109 (2021)","DOI":"10.1609\/aaai.v35i7.16760"},{"key":"2988_CR21","doi-asserted-by":"crossref","unstructured":"Li, Z., Liu, F., Yang, W., Peng, S., Zhou, J.: A survey of convolutional neural networks: analysis, applications, and prospects. IEEE Trans. Neural Netw. Learn. Syst. (2021)","DOI":"10.1109\/TNNLS.2021.3084827"},{"key":"2988_CR22","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"2988_CR23","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: Cbam: Convolutional block attention module. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"2988_CR24","doi-asserted-by":"crossref","unstructured":"Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., Wei, Y.: Deformable convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 764\u2013773 (2017)","DOI":"10.1109\/ICCV.2017.89"},{"key":"2988_CR25","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part I 16, pp. 213\u2013229 (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"2988_CR26","unstructured":"Yuan, Y., Huang, L., Guo, J., Zhang, C., Chen, X., Wang, J.: Ocnet: Object context network for scene parsing. arXiv preprint arXiv:1809.00916 (2018)"},{"key":"2988_CR27","doi-asserted-by":"crossref","unstructured":"Fu, J., Liu, J., Tian, H., Li, Y., Bao, Y., Fang, Z., Lu, H.: Dual attention network for scene segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3146\u20133154 (2019)","DOI":"10.1109\/CVPR.2019.00326"},{"key":"2988_CR28","doi-asserted-by":"crossref","unstructured":"Yang, J., Ren, P., Zhang, D., Chen, D., Wen, F., Li, H., Hua, G.: Neural aggregation network for video face recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4362\u20134371 (2017)","DOI":"10.1109\/CVPR.2017.554"},{"key":"2988_CR29","doi-asserted-by":"crossref","unstructured":"Wang, Q., Wu, T., Zheng, H., Guo, G.: Hierarchical pyramid diverse attention networks for face recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8326\u20138335 (2020)","DOI":"10.1109\/CVPR42600.2020.00835"},{"key":"2988_CR30","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1848\/1\/012074","volume":"1848","author":"W Li","year":"2021","unstructured":"Li, W., Sun, Y., Wang, J., Cao, J., Xu, H., Yang, X., Sun, G., Ma, Y., Long, Y.: Collaborative attention network for person re-identification. J. Phys. Conf. Ser. 1848, 012074 (2021)","journal-title":"J. Phys. Conf. Ser."},{"key":"2988_CR31","doi-asserted-by":"crossref","unstructured":"Chen, B., Deng, W., Hu, J.: Mixed high-order attention network for person re-identification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 371\u2013381 (2019)","DOI":"10.1109\/ICCV.2019.00046"},{"key":"2988_CR32","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"issue":"3","key":"2988_CR33","doi-asserted-by":"publisher","first-page":"1347","DOI":"10.1109\/TIP.2017.2778563","volume":"27","author":"W Du","year":"2017","unstructured":"Du, W., Wang, Y., Qiao, Y.: Recurrent spatial-temporal attention network for action recognition in videos. IEEE Trans. Image Process. 27(3), 1347\u20131360 (2017)","journal-title":"IEEE Trans. Image Process."},{"key":"2988_CR34","unstructured":"Su, W., Zhu, X., Cao, Y., Li, B., Lu, L., Wei, F., Dai, J.: Vl-bert: Pre-training of generic visual-linguistic representations. arXiv preprint arXiv:1908.08530 (2019)"},{"key":"2988_CR35","doi-asserted-by":"crossref","unstructured":"Xu, T., Zhang, P., Huang, Q., Zhang, H., Gan, Z., Huang, X., He, X.: Attngan: Fine-grained text to image generation with attentional generative adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1316\u20131324 (2018)","DOI":"10.1109\/CVPR.2018.00143"},{"key":"2988_CR36","unstructured":"Mnih, V., Heess, N., Graves, A., et al.: Recurrent models of visual attention. Adv. Neural Inf. Process. Syst. 27 (2014)"},{"key":"2988_CR37","unstructured":"Gregor, K., Danihelka, I., Graves, A., Rezende, D., Wierstra, D.: Draw: A recurrent neural network for image generation. In: International Conference on Machine Learning, pp. 1462\u20131471 (2015)"},{"key":"2988_CR38","unstructured":"Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhudinov, R., Zemel, R., Bengio, Y.: Show, attend and tell: Neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057 (2015)"},{"key":"2988_CR39","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., et al.: Spatial transformer networks. Adv. Neural Inf. Process. Syst. 28 (2015)"},{"key":"2988_CR40","doi-asserted-by":"crossref","unstructured":"Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., Hu, Q.: Eca-net: Efficient channel attention for deep convolutional neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11534\u201311542 (2020)","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"2988_CR41","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"2988_CR42","unstructured":"Wang, W., Liang, J., Liu, D.: Learning equivariant segmentation with instance-unique querying. arXiv preprint arXiv:2210.00911 (2022)"},{"key":"2988_CR43","doi-asserted-by":"crossref","unstructured":"Cui, Y., Yan, L., Cao, Z., Liu, D.: Tf-blender: Temporal feature blender for video object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8138\u20138147 (2021)","DOI":"10.1109\/ICCV48922.2021.00803"},{"issue":"6","key":"2988_CR44","doi-asserted-by":"publisher","first-page":"820","DOI":"10.3390\/s16060820","volume":"16","author":"A Gonz\u00e1lez","year":"2016","unstructured":"Gonz\u00e1lez, A., Fang, Z., Socarras, Y., Serrat, J., V\u00e1zquez, D., Xu, J., L\u00f3pez, A.M.: Pedestrian detection at day\/night time with visible and fir cameras: a comparison. Sensors 16(6), 820 (2016)","journal-title":"Sensors"},{"key":"2988_CR45","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1016\/j.inffus.2018.11.017","volume":"50","author":"D Guan","year":"2019","unstructured":"Guan, D., Cao, Y., Yang, J., Cao, Y., Yang, M.Y.: Fusion of multispectral data through illumination-aware deep neural networks for pedestrian detection. Inf. Fusion 50, 148\u2013157 (2019)","journal-title":"Inf. Fusion"},{"key":"2988_CR46","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1016\/j.inffus.2018.09.015","volume":"50","author":"L Zhang","year":"2019","unstructured":"Zhang, L., Liu, Z., Zhang, S., Yang, X., Qiao, H., Huang, K., Hussain, A.: Cross-modality interactive attention network for multispectral pedestrian detection. Inf. Fusion 50, 20\u201329 (2019)","journal-title":"Inf. Fusion"},{"key":"2988_CR47","unstructured":"Choi, H., Kim, S., Park, K., Sohn, K.: Multi-spectral pedestrian detection based on accumulated object proposal with fully convolutional networks. In: 2016 23rd International Conference on Pattern Recognition (ICPR), pp. 621\u2013626 (2016)"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-023-02988-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-023-02988-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-023-02988-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,5]],"date-time":"2024-04-05T17:09:06Z","timestamp":1712336946000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-023-02988-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,10]]},"references-count":47,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,4]]}},"alternative-id":["2988"],"URL":"https:\/\/doi.org\/10.1007\/s00371-023-02988-7","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,10]]},"assertion":[{"value":"13 June 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 July 2023","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}