{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T21:16:35Z","timestamp":1742937395740,"version":"3.40.3"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031783401"},{"type":"electronic","value":"9783031783418"}],"license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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\/978-3-031-78341-8_17","type":"book-chapter","created":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T15:14:56Z","timestamp":1733066096000},"page":"259-274","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MIHNet: Multi-scale Intra-layer Fusion with\u00a0Hybrid Structure for\u00a0Low-Quality 3D Face Recognition"],"prefix":"10.1007","author":[{"given":"Yuting","family":"Hu","sequence":"first","affiliation":[]},{"given":"Yue","family":"Ming","sequence":"additional","affiliation":[]},{"given":"Panzi","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Jiangwan","family":"Zhou","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,2]]},"reference":[{"key":"17_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1007\/978-3-030-98358-1_27","volume-title":"MultiMedia Modeling","author":"H Zheng","year":"2022","unstructured":"Zheng, H., Wang, W., Wen, F., Liu, P.: A complementary fusion strategy for RGB-D face recognition. In: P\u00f3r J\u00f3nsson, B., et al. (eds.) MMM 2022. LNCS, vol. 13141, pp. 339\u2013351. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-030-98358-1_27"},{"key":"17_CR2","doi-asserted-by":"publisher","first-page":"2461","DOI":"10.1109\/TIFS.2021.3053458","volume":"16","author":"H Uppal","year":"2021","unstructured":"Uppal, H., Sepas-Moghaddam, A., Greenspan, M., Etemad, A.: Depth as attention for face representation learning. IEEE Trans. Inf. Forensics Secur. 16, 2461\u20132476 (2021)","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"17_CR3","doi-asserted-by":"crossref","unstructured":"Lin, S., Jiang, C., Liu, F., Shen, L.: High quality facial data synthesis and fusion for 3D low-quality face recognition. In: 2021 IEEE International Joint Conference on Biometrics (IJCB), pp. 1\u20138. IEEE (2021)","DOI":"10.1109\/IJCB52358.2021.9484339"},{"issue":"1","key":"17_CR4","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1109\/THMS.2022.3199777","volume":"53","author":"P Zhao","year":"2022","unstructured":"Zhao, P., Ming, Y., Meng, X., Yu, H.: LMFNet: a lightweight multiscale fusion network with hierarchical structure for low-quality 3-D face recognition. IEEE Trans. Hum.-Mach. Syst. 53(1), 239\u2013252 (2022)","journal-title":"IEEE Trans. Hum.-Mach. Syst."},{"issue":"4","key":"17_CR5","doi-asserted-by":"publisher","first-page":"486","DOI":"10.1109\/TBIOM.2022.3197437","volume":"4","author":"C Jiang","year":"2022","unstructured":"Jiang, C., Lin, S., Chen, W., Liu, F., Shen, L.: PointFace: point cloud encoder-based feature embedding for 3-D face recognition. IEEE Trans. Biom. Behav. Identity Sci. 4(4), 486\u2013497 (2022)","journal-title":"IEEE Trans. Biom. Behav. Identity Sci."},{"key":"17_CR6","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1016\/j.patrec.2022.12.027","volume":"166","author":"Y Zhu","year":"2023","unstructured":"Zhu, Y., Gao, J., Wu, T., Liu, Q., Zhou, X.: Exploiting enhanced and robust RGB-D face representation via progressive multi-modal learning. Pattern Recogn. Lett. 166, 38\u201345 (2023)","journal-title":"Pattern Recogn. Lett."},{"key":"17_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2023.103757","volume":"91","author":"W Niu","year":"2023","unstructured":"Niu, W., Zhao, Y., Yu, Z., Liu, Y., Gong, Y.: Research on a face recognition algorithm based on 3D face data and 2D face image matching. J. Vis. Commun. Image Represent. 91, 103757 (2023)","journal-title":"J. Vis. Commun. Image Represent."},{"key":"17_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109936","volume":"145","author":"R Xu","year":"2024","unstructured":"Xu, R., et al.: Depth map denoising network and lightweight fusion network for enhanced 3D face recognition. Pattern Recogn. 145, 109936 (2024)","journal-title":"Pattern Recogn."},{"key":"17_CR9","doi-asserted-by":"crossref","unstructured":"Fan, Q., Huang, H., Chen, M., Liu, H., He, R.: RMT: retentive networks meet vision transformers. arXiv preprint arXiv:2309.11523 (2023)","DOI":"10.1109\/CVPR52733.2024.00539"},{"key":"17_CR10","unstructured":"Vasu, P.K.A., Gabriel, J., Zhu, J., Tuzel, O., Ranjan, A.: FastViT: a fast hybrid vision transformer using structural reparameterization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5785\u20135795 (2023)"},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"Lin, W., Wu, Z., Chen, J., Huang, J., Jin, L.: Scale-aware modulation meet transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6015\u20136026 (2023)","DOI":"10.1109\/ICCV51070.2023.00553"},{"key":"17_CR12","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems 30 (2017)"},{"key":"17_CR13","doi-asserted-by":"publisher","first-page":"4341","DOI":"10.1109\/TIP.2023.3297408","volume":"32","author":"Y Quan","year":"2023","unstructured":"Quan, Y., et al.: Centralized feature pyramid for object detection. IEEE Trans. Image Process. 32, 4341\u20134354 (2023)","journal-title":"IEEE Trans. Image Process."},{"key":"17_CR14","doi-asserted-by":"crossref","unstructured":"Mu, G., Huang, D., Hu, G., Sun, J., Wang, Y.: Led3D: a lightweight and efficient deep approach to recognizing low-quality 3D faces. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5773\u20135782 (2019)","DOI":"10.1109\/CVPR.2019.00592"},{"key":"17_CR15","unstructured":"Dosovitskiy, A., et al.: An image is worth $$16\\times 16$$ words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"17_CR16","doi-asserted-by":"crossref","unstructured":"Sun, L., Lian, Z., Liu, B., Tao, J.: MAE-DFER: efficient masked autoencoder for self-supervised dynamic facial expression recognition. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 6110\u20136121 (2023)","DOI":"10.1145\/3581783.3612365"},{"key":"17_CR17","doi-asserted-by":"crossref","unstructured":"Nguyen, X.-B., Duong, C.N., Li, X., Gauch, S., Seo, H.-S., Luu, K.: Micron-BERT: BERT-based facial micro-expression recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1482\u20131492 (2023)","DOI":"10.1109\/CVPR52729.2023.00149"},{"key":"17_CR18","unstructured":"Zhong, Y., Deng, W.: Face transformer for recognition. arXiv preprint arXiv:2103.14803 (2021)"},{"key":"17_CR19","doi-asserted-by":"crossref","unstructured":"Dan, J., et al.: TransFace: calibrating transformer training for face recognition from a data-centric perspective. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 20642\u201320653 (2023)","DOI":"10.1109\/ICCV51070.2023.01887"},{"key":"17_CR20","doi-asserted-by":"crossref","unstructured":"Zhang, Z., et al.: Learning flexibly distributional representation for low-quality 3D face recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 4, pp. 3465\u20133473 (2021)","DOI":"10.1609\/aaai.v35i4.16460"},{"key":"17_CR21","unstructured":"Li, K., et al.: UniFormer: unified transformer for efficient spatiotemporal representation learning. arXiv preprint arXiv:2201.04676 (2022)"},{"key":"17_CR22","doi-asserted-by":"crossref","unstructured":"Guo, J., et al.: CMT: convolutional neural networks meet vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12175\u201312185 (2022)","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"17_CR23","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 568\u2013578 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"17_CR24","doi-asserted-by":"crossref","unstructured":"Ren, S., et al.: Shunted self-attention via multi-scale token aggregation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10853\u201310862 (2022)","DOI":"10.1109\/CVPR52688.2022.01058"},{"key":"17_CR25","unstructured":"Chu, X., et al.: Twins: revisiting the design of spatial attention in vision transformers. In: Advances in Neural Information Processing Systems 34, pp. 9355\u20139366 (2021)"},{"key":"17_CR26","doi-asserted-by":"crossref","unstructured":"Li, J., Wen, Y., He, L.: SCConv: spatial and channel reconstruction convolution for feature redundancy. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6153\u20136162 (2023)","DOI":"10.1109\/CVPR52729.2023.00596"},{"key":"17_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, J., Huang, D., Wang, Y., Sun, J.: Lock3DFace: a large-scale database of low-cost kinect 3D faces. In: 2016 International Conference on Biometrics (ICB), pp. 1\u20138. IEEE (2016)","DOI":"10.1109\/ICB.2016.7550062"},{"issue":"11","key":"17_CR28","doi-asserted-by":"publisher","first-page":"1534","DOI":"10.1109\/TSMC.2014.2331215","volume":"44","author":"R Min","year":"2014","unstructured":"Min, R., Kose, N., Dugelay, J.-L.: KinectFaceDB: a kinect database for face recognition. IEEE Trans. Syst. Man Cybern. Syst. 44(11), 1534\u20131548 (2014)","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"key":"17_CR29","doi-asserted-by":"crossref","unstructured":"Phillips, P.J., et al.: Overview of the face recognition grand challenge. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005), vol. 1, pp. 947\u2013954 (2005)","DOI":"10.1109\/CVPR.2005.268"},{"key":"17_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1007\/978-3-540-89991-4_7","volume-title":"Biometrics and Identity Management","author":"N Aly\u00fcz","year":"2008","unstructured":"Aly\u00fcz, N., et al.: 3D face recognition benchmarks on the bosphorus\u00a0database with focus on facial expressions. In: Schouten, B., Juul, N.C., Drygajlo, A., Tistarelli, M. (eds.) BioID 2008. LNCS, vol. 5372, pp. 57\u201366. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-89991-4_7"},{"key":"17_CR31","unstructured":"Neto, J.B.C., Marana, A.N., Ferrari, C., Berretti, S., Del Bimbo, A.: Depth-based face recognition by learning from 3D-LBP images. In: 3DOR@ Eurographics, pp. 55\u201362 (2019)"},{"key":"17_CR32","doi-asserted-by":"crossref","unstructured":"Cui, J., Zhang, H., Han, H., Shan, S., Chen, X.: Improving 2D face recognition via discriminative face depth estimation. In: 2018 International Conference on Biometrics (ICB), pp. 140\u2013147. IEEE (2018)","DOI":"10.1109\/ICB2018.2018.00031"},{"key":"17_CR33","doi-asserted-by":"crossref","unstructured":"Hu, Z., Zhao, Q., Liu, F.: Revisiting depth-based face recognition from a quality perspective. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (2019)","DOI":"10.1109\/CVPRW.2019.00289"},{"key":"17_CR34","doi-asserted-by":"crossref","unstructured":"Mu, G., Huang, D., Li, W., Hu, G., Wang, Y.: Refining single low-quality facial depth map by lightweight and efficient deep model. In: IEEE International Joint Conference on Biometrics (IJCB), pp. 1\u20138 (2021)","DOI":"10.1109\/IJCB52358.2021.9484381"},{"key":"17_CR35","unstructured":"Cardia Neto, J.B.: 3D face recognition with descriptor images and shallow convolutional neural networks. Universidade Federal de S\u00e3o Carlos (2020)"},{"key":"17_CR36","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113319","volume":"150","author":"N Grati","year":"2020","unstructured":"Grati, N., Ben-Hamadou, A., Hammami, M.: Learning local representations for scalable RGB-D face recognition. Expert Syst. Appl. 150, 113319 (2020)","journal-title":"Expert Syst. Appl."},{"issue":"1s","key":"17_CR37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3527158","volume":"19","author":"JBC Neto","year":"2023","unstructured":"Neto, J.B.C., et al.: Learning streamed attention network from descriptor images for cross-resolution 3D face recognition. ACM Trans. Multimedia Comput. Commun. Appl. 19(1s), 1\u201320 (2023)","journal-title":"ACM Trans. Multimedia Comput. Commun. Appl."},{"issue":"8","key":"17_CR38","doi-asserted-by":"publisher","DOI":"10.1063\/5.0153077","volume":"13","author":"P Zhao","year":"2023","unstructured":"Zhao, P., et al.: DSNet: dual-stream multi-scale fusion network for low-quality 3D face recognition. AIP Adv. 13(8), 085310 (2023)","journal-title":"AIP Adv."},{"issue":"2","key":"17_CR39","doi-asserted-by":"publisher","first-page":"767","DOI":"10.1016\/j.patcog.2011.07.022","volume":"45","author":"A Savran","year":"2012","unstructured":"Savran, A., Sankur, B., Bilge, M.T.: Comparative evaluation of 3D vs. 2D modality for automatic detection of facial action units. Pattern Recogn. 45(2), 767\u2013782 (2012)","journal-title":"Pattern Recogn."},{"key":"17_CR40","doi-asserted-by":"crossref","unstructured":"Sandler, M., et al.: MobileNetV2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"17_CR41","unstructured":"Gilani, S.Z., Mian, A.: Learning from millions of 3D scans for large-scale 3D face recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1896\u20131905 (2018)"},{"key":"17_CR42","unstructured":"Lou, M., Zhou, H.-Y., Yang, S., Yu, Y.: TransXNet: learning both global and local dynamics with a dual dynamic token mixer for visual recognition. arXiv preprint arXiv:2310.19380 (2023)"},{"key":"17_CR43","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1007\/978-3-030-86608-2_46","volume-title":"Biometric Recognition","author":"S Xiao","year":"2021","unstructured":"Xiao, S., Li, S., Zhao, Q.: Low-quality 3D face recognition with\u00a0soft thresholding. In: Feng, J., Zhang, J., Liu, M., Fang, Y. (eds.) CCBR 2021. LNCS, vol. 12878, pp. 419\u2013427. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86608-2_46"},{"issue":"11","key":"17_CR44","doi-asserted-by":"publisher","first-page":"6506","DOI":"10.3390\/app13116506","volume":"13","author":"L He","year":"2023","unstructured":"He, L., He, L., Peng, L.: CFormerFaceNet: efficient lightweight network merging a CNN and transformer for face recognition. Appl. Sci. 13(11), 6506 (2023)","journal-title":"Appl. Sci."}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78341-8_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T16:06:28Z","timestamp":1733069188000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78341-8_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"ISBN":["9783031783401","9783031783418"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78341-8_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,2]]},"assertion":[{"value":"2 December 2024","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"}}]}}