{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T05:47:09Z","timestamp":1785649629879,"version":"3.56.0"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032316653","type":"print"},{"value":"9783032316660","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T00:00:00Z","timestamp":1785715200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T00:00:00Z","timestamp":1785715200000},"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":[[2027]]},"DOI":"10.1007\/978-3-032-31666-0_30","type":"book-chapter","created":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T05:45:32Z","timestamp":1785649532000},"page":"452-467","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SelfXTFace: Attention Based Feature Pyramid Network in\u00a0Face Detection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7864-4736","authenticated-orcid":false,"given":"Furkan","family":"Kas\u0131m","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5342-1235","authenticated-orcid":false,"given":"Carlos","family":"Kirchdorfer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8165-0054","authenticated-orcid":false,"given":"Salman","family":"Mohammad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1489-7448","authenticated-orcid":false,"given":"Manuel","family":"G\u00fcnther","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,3]]},"reference":[{"key":"30_CR1","unstructured":"Bulat, A., Tzimiropoulos, G.: How far are we from solving the 2D & 3D face alignment problem? In: International Conference on Computer Vision (ICCV) (2017)"},{"key":"30_CR2","doi-asserted-by":"crossref","unstructured":"Carion, N., et al.: End-to-end object detection with transformers. In: European Conference on Computer Vision (ECCV) (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"30_CR3","doi-asserted-by":"crossref","unstructured":"Chen, Z., Yang, C., Li, Q., Zhao, F., Zha, Z.J., Wu, F.: Disentangle your dense object detector. In: ACM International Conference on Multimedia (2021)","DOI":"10.1145\/3474085.3475351"},{"key":"30_CR4","doi-asserted-by":"crossref","unstructured":"Deng, J., et al.: RetinaFace: single-shot multi-level face localisation in the wild. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00525"},{"key":"30_CR5","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (ICLR) (2021)"},{"key":"30_CR6","doi-asserted-by":"crossref","unstructured":"Du, H., Shi, H., Zeng, D., Zhang, X.P., Mei, T.: The elements of end-to-end deep face recognition: a survey of recent advances. ACM Comput. Surv. (2022)","DOI":"10.1145\/3507902"},{"key":"30_CR7","doi-asserted-by":"crossref","unstructured":"Du, Z., Hu, Z., Zhao, G., Jin, Y., Ma, H.: Cross-layer feature pyramid transformer for small object detection in aerial images. Trans. Geosci. Remote Sens. (2025)","DOI":"10.1109\/TGRS.2025.3572706"},{"key":"30_CR8","doi-asserted-by":"crossref","unstructured":"G\u00fcnther, M., Rozsa, A., Boult, T.E.: AFFACT: alignment-free facial attribute classification technique. In: International Joint Conference on Biometrics (IJCB) (2017)","DOI":"10.1109\/BTAS.2017.8272686"},{"key":"30_CR9","doi-asserted-by":"crossref","unstructured":"Guo, C., Fan, B., Zhang, Q., Xiang, S., Pan, C.: AugFPN: improving multi-scale feature learning for object detection. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.01261"},{"key":"30_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"30_CR11","doi-asserted-by":"crossref","unstructured":"Hu, H., Zhang, Z., Xie, Z., Lin, S.: Local relation networks for image recognition. In: International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00356"},{"key":"30_CR12","doi-asserted-by":"crossref","unstructured":"Hu, M., Li, Y., Fang, L., Wang, S.: A2-FPN: attention aggregation based feature pyramid network for instance segmentation. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.01509"},{"key":"30_CR13","doi-asserted-by":"crossref","unstructured":"Hu, P., Ramanan, D.: Finding tiny faces. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.166"},{"key":"30_CR14","unstructured":"Jeong, J., Kim, B., Yu, J., Yoo, Y.J.: EResFD: rediscovery of the effectiveness of standard convolution for lightweight face detection. In: Winter Conference on Applications of Computer Vision (WACV) (2022)"},{"key":"30_CR15","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems (NeurIPS) (2012)"},{"key":"30_CR16","doi-asserted-by":"crossref","unstructured":"Li, J., Wang, Y., Wang, C., Tai, Y., Qian, J., et\u00a0al.: DSFD: dual shot face detector. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00520"},{"key":"30_CR17","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"30_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"30_CR19","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Feature pyramid networks for object detection. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"30_CR20","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00913"},{"key":"30_CR21","doi-asserted-by":"crossref","unstructured":"Liu, Y., Tang, X.: BFBox: searching face-appropriate backbone and feature pyramid network for face detector. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.01358"},{"key":"30_CR22","doi-asserted-by":"crossref","unstructured":"Liu, Y., Tang, X., Han, J., Liu, J., Rui, D., Wu, X.: HAMBox: delving into mining high-quality anchors on face detection. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.01306"},{"key":"30_CR23","doi-asserted-by":"crossref","unstructured":"Liu, Y., Wang, F., Deng, J., Zhou, Z., Sun, B., Li, H.: MogFace: towards a deeper appreciation on face detection. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.00406"},{"key":"30_CR24","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"30_CR25","doi-asserted-by":"crossref","unstructured":"Ming, X., Wei, F., Zhang, T., Chen, D., Wen, F.: Group sampling for scale invariant face detection. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00356"},{"key":"30_CR26","doi-asserted-by":"crossref","unstructured":"Najibi, M., Samangouei, P., Chellappa, R., Davis, L.S.: SSH: single stage headless face detector. In: International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.522"},{"key":"30_CR27","doi-asserted-by":"crossref","unstructured":"Ren, S., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. Trans. Pattern Anal. Mach. Intell. (TPAMI) (2016)","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"30_CR28","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., Le, Q.V.: EfficientDet: scalable and efficient object detection. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"30_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"812","DOI":"10.1007\/978-3-030-01240-3_49","volume-title":"Computer Vision \u2013 ECCV 2018","author":"X Tang","year":"2018","unstructured":"Tang, X., Du, D.K., He, Z., Liu, J.: PyramidBox: a context-assisted single shot face detector. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 812\u2013828. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01240-3_49"},{"key":"30_CR30","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, NeurIPS (2017)"},{"key":"30_CR31","unstructured":"Viola, P.A., Jones, M.J.: Robust real-time face detection. Int. J. Comput. Vision (IJCV) (2001)"},{"key":"30_CR32","doi-asserted-by":"crossref","unstructured":"Yang, G., Lei, J., Tian, H., Feng, Z., Liang, R.: Asymptotic feature pyramid network for labeling pixels and regions. Trans. Circ. Syst. Video Technol. (TCSVT) (2024)","DOI":"10.1109\/TCSVT.2024.3376773"},{"key":"30_CR33","doi-asserted-by":"crossref","unstructured":"Yang, S., Luo, P., Loy, C.C., Tang, X.: WIDER FACE: a face detection benchmark. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.596"},{"key":"30_CR34","doi-asserted-by":"crossref","unstructured":"Zeiler, M.D., Taylor, G.W., Fergus, R.: Adaptive deconvolutional networks for mid and high level feature learning. In: International Conference on Computer Vision (ICCV) (2011)","DOI":"10.1109\/ICCV.2011.6126474"},{"key":"30_CR35","unstructured":"Zhang, B., et al.: ASFD: automatic and scalable face detector. In: ACM International Conference on Multimedia (ACM MM) (2021)"},{"key":"30_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1007\/978-3-030-58604-1_20","volume-title":"Computer Vision \u2013 ECCV 2020","author":"D Zhang","year":"2020","unstructured":"Zhang, D., Zhang, H., Tang, J., Wang, M., Hua, X., Sun, Q.: Feature pyramid transformer. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12373, pp. 323\u2013339. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58604-1_20"},{"key":"30_CR37","unstructured":"Zhang, S., Chi, C., Lei, Z., Li, S.: RefineFace: refinement neural network for high performance face detection. Trans. Pattern Anal. Mach. Intell. (TPAMI) (2019)"},{"key":"30_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, S., Zhu, X., Lei, Z., Shi, H., et al.: S$$^{3}$$FD: single shot scale-invariant face detector. In: International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.30"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-31666-0_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T05:45:36Z","timestamp":1785649536000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-31666-0_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,3]]},"ISBN":["9783032316653","9783032316660"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-31666-0_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,3]]},"assertion":[{"value":"3 August 2026","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":"Lyon","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":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 August 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 August 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2026.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}