{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T15:31:08Z","timestamp":1761060668104,"version":"3.40.3"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030012182"},{"type":"electronic","value":"9783030012199"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-01219-9_21","type":"book-chapter","created":{"date-parts":[[2018,10,6]],"date-time":"2018-10-06T14:23:51Z","timestamp":1538835831000},"page":"348-364","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":85,"title":["Quantized Densely Connected U-Nets for Efficient Landmark Localization"],"prefix":"10.1007","author":[{"given":"Zhiqiang","family":"Tang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xi","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shijie","family":"Geng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lingfei","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaoting","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dimitris","family":"Metaxas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,10,7]]},"reference":[{"key":"21_CR1","doi-asserted-by":"crossref","unstructured":"Andriluka, M., Pishchulin, L., Gehler, P., Schiele, B.: 2D human pose estimation: New benchmark and state of the art analysis. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.471"},{"key":"21_CR2","first-page":"385","volume":"22","author":"R Begleiter","year":"2004","unstructured":"Begleiter, R., El-Yaniv, R., Yona, G.: On prediction using variable order Markov models. J. Artif. Res. 22, 385\u2013421 (2004)","journal-title":"J. Artif. Res."},{"key":"21_CR3","doi-asserted-by":"crossref","unstructured":"Belagiann., V., Zisserman, A.: Recurrent human pose estimation. In: FG (2017)","DOI":"10.1109\/FG.2017.64"},{"key":"21_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"717","DOI":"10.1007\/978-3-319-46478-7_44","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Bulat","year":"2016","unstructured":"Bulat, A., Tzimiropoulos, G.: Human pose estimation via convolutional part heatmap regression. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 717\u2013732. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46478-7_44"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Bulat, A., Tzimiropoulos, G.: Binarized convolutional landmark localizers for human pose estimation and face alignment with limited resources. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.400"},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"Carreira, J., Agrawal, P., Fragkiadaki, K., Malik, J.: Human pose estimation with iterative error feedback. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.512"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Y., Shen, C., Wei, X.S., Liu, L., Yang, J.: Adversarial posenet: A structure-aware convolutional network for human pose estimation. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.137"},{"key":"21_CR8","doi-asserted-by":"crossref","unstructured":"Chu, X., Yang, W., Ouyang, W., Ma, C., Yuille, A., Wang, X.: Multi-context attention for human pose estimation. In: CVPR (2016)","DOI":"10.1109\/CVPR.2017.601"},{"key":"21_CR9","unstructured":"Courbariaux, M., Hubara, I., Soudry, D., El-Yaniv, R., Bengio, Y.: Binarized neural networks: training deep neural networks with weights and activations constrained to +1 or $$-1$$. arXiv (2016)"},{"key":"21_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"728","DOI":"10.1007\/978-3-319-46493-0_44","volume-title":"Computer Vision \u2013 ECCV 2016","author":"G Gkioxari","year":"2016","unstructured":"Gkioxari, G., Toshev, A., Jaitly, N.: Chained predictions using convolutional neural networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 728\u2013743. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_44"},{"key":"21_CR11","unstructured":"Glorot, X., Bordes, A., Bengio, Y.: Deep sparse rectifier neural networks. In: AISTAT (2011)"},{"key":"21_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Hu, P., Ramanan, D.: Bottom-up and top-down reasoning with hierarchical rectified Gaussians. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.604"},{"key":"21_CR14","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Weinberger, K.Q., van der Maaten, L.: Densely connected convolutional networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"21_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1007\/978-3-319-46466-4_3","volume-title":"Computer Vision \u2013 ECCV 2016","author":"E Insafutdinov","year":"2016","unstructured":"Insafutdinov, E., Pishchulin, L., Andres, B., Andriluka, M., Schiele, B.: DeeperCut: a deeper, stronger, and faster multi-person pose estimation model. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 34\u201350. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46466-4_3"},{"key":"21_CR16","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: ICML (2015)"},{"key":"21_CR17","doi-asserted-by":"crossref","unstructured":"Johnson, S., Everingham, M.: Clustered pose and nonlinear appearance models for human pose estimation. In: BMVC (2010)","DOI":"10.5244\/C.24.12"},{"key":"21_CR18","doi-asserted-by":"crossref","unstructured":"Li, D., Wang, X., Kong, D.: DeepRebirth: accelerating deep neural network execution on mobile devices. AAAI (2018)","DOI":"10.1609\/aaai.v32i1.11876"},{"key":"21_CR19","unstructured":"Li, F., Zhang, B., Liu, B.: Ternary weight networks. arXiv (2016)"},{"key":"21_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"246","DOI":"10.1007\/978-3-319-46475-6_16","volume-title":"Computer Vision \u2013 ECCV 2016","author":"I Lifshitz","year":"2016","unstructured":"Lifshitz, I., Fetaya, E., Ullman, S.: Human pose estimation using deep consensus voting. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 246\u2013260. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_16"},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"Lv, J., Shao, X., Xing, J., Cheng, C., Zhou, X.: A deep regression architecture with two-stage re-initialization for high performance facial landmark detection. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.393"},{"key":"21_CR22","unstructured":"McMahan, H.B., Moore, E., Ramage, D., Hampson, S., et al.: Communication-efficient learning of deep networks from decentralized data. arXiv (2016)"},{"key":"21_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1007\/978-3-319-46484-8_29","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Newell","year":"2016","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 483\u2013499. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_29"},{"key":"21_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1007\/978-3-319-46448-0_3","volume-title":"Computer Vision \u2013 ECCV 2016","author":"X Peng","year":"2016","unstructured":"Peng, X., Feris, R.S., Wang, X., Metaxas, D.N.: A recurrent encoder-decoder network for sequential face alignment. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 38\u201356. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_3"},{"key":"21_CR25","doi-asserted-by":"crossref","unstructured":"Peng, X., Feris, R.S., Wang, X., Metaxas, D.N.: RED-Net: a recurrent encoder-decoder network for video-based face alignment. IJCV (2018)","DOI":"10.1007\/s11263-018-1095-1"},{"key":"21_CR26","doi-asserted-by":"crossref","unstructured":"Peng, X., Tang, Z., Yang, F., Feris, R.S., Metaxas, D.: Jointly optimize data augmentation and network training: adversarial data augmentation in human pose estimation. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00237"},{"key":"21_CR27","doi-asserted-by":"crossref","unstructured":"Pishchulin, L., Andriluka, M., Gehler, P., Schiele, B.: Strong appearance and expressive spatial models for human pose estimation. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.433"},{"key":"21_CR28","doi-asserted-by":"crossref","unstructured":"Pishchulin, L., et al.: DeepCut: joint subset partition and labeling for multi person pose estimation. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.533"},{"key":"21_CR29","unstructured":"Pleiss, G., Chen, D., Huang, G., Li, T., van der Maaten, L., Weinberger, K.Q.: Memory-efficient implementation of DenseNets. arXiv (2017)"},{"key":"21_CR30","doi-asserted-by":"crossref","unstructured":"Rafi, U., Leibe, B., Gall, J., Kostrikov, I.: An efficient convolutional network for human pose estimation. In: BMVC (2016)","DOI":"10.5244\/C.30.109"},{"key":"21_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1007\/978-3-319-46493-0_32","volume-title":"Computer Vision \u2013 ECCV 2016","author":"M Rastegari","year":"2016","unstructured":"Rastegari, M., Ordonez, V., Redmon, J., Farhadi, A.: XNOR-Net: ImageNet classification using binary convolutional neural networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 525\u2013542. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_32"},{"key":"21_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"21_CR33","doi-asserted-by":"crossref","unstructured":"Sagonas, C., Tzimiropoulos, G., Zafeiriou, S., Pantic, M.: 300 faces in-the-wild challenge: the first facial landmark localization challenge. In: ICCVW (2013)","DOI":"10.1109\/ICCVW.2013.59"},{"key":"21_CR34","unstructured":"Shi, B., Bai, X., Liu, W., Wang, J.: Deep regression for face alignment. arXiv (2014)"},{"key":"21_CR35","doi-asserted-by":"crossref","unstructured":"Tompson, J., Goroshin, R., Jain, A., LeCun, Y., Bregler, C.: Efficient object localization using convolutional networks. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298664"},{"key":"21_CR36","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: NIPS (2014)"},{"key":"21_CR37","doi-asserted-by":"crossref","unstructured":"Toshev, A., Szegedy, C.: DeepPose: human pose estimation via deep neural networks. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.214"},{"key":"21_CR38","doi-asserted-by":"crossref","unstructured":"Trigeorgis, G., Snape, P., Nicolaou, M.A., Antonakos, E., Zafeiriou, S.: Mnemonic descent method: a recurrent process applied for end-to-end face alignment. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.453"},{"key":"21_CR39","doi-asserted-by":"crossref","unstructured":"Wei, S.E., Ramakrishna, V., Kanade, T., Sheikh, Y.: Convolutional pose machines. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.511"},{"key":"21_CR40","unstructured":"Wu, S., Li, G., Chen, F., Shi, L.: Training and inference with integers in deep neural networks. In: ICLR (2018)"},{"key":"21_CR41","doi-asserted-by":"crossref","unstructured":"Xiong, X., De la Torre, F.: Supervised descent method and its applications to face alignment. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.75"},{"key":"21_CR42","doi-asserted-by":"crossref","unstructured":"Yang, W., Li, S., Ouyang, W., Li, H., Wang, X.: Learning feature pyramids for human pose estimation. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.144"},{"key":"21_CR43","doi-asserted-by":"crossref","unstructured":"Zafeiriou, S., Trigeorgis, G., Chrysos, G., Deng, J., Shen, J.: The Menpo facial landmark localisation challenge: a step towards the solution. In: CVPRW (2017)","DOI":"10.1109\/CVPRW.2017.263"},{"key":"21_CR44","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-319-10605-2_1","volume-title":"Computer Vision \u2013 ECCV 2014","author":"J Zhang","year":"2014","unstructured":"Zhang, J., Shan, S., Kan, M., Chen, X.: Coarse-to-fine auto-encoder networks (CFAN) for real-time face alignment. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8690, pp. 1\u201316. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10605-2_1"},{"key":"21_CR45","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1007\/978-3-319-10599-4_7","volume-title":"Computer Vision \u2013 ECCV 2014","author":"Z Zhang","year":"2014","unstructured":"Zhang, Z., Luo, P., Loy, C.C., Tang, X.: Facial landmark detection by deep multi-task learning. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 94\u2013108. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10599-4_7"},{"key":"21_CR46","doi-asserted-by":"crossref","unstructured":"Zhao, L., Peng, X., Tian, Y., Kapadia, M., Metaxas, D.: Learning to forecast and refine residual motion for image-to-video generation. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01267-0_24"},{"key":"21_CR47","unstructured":"Zhou, S., Wu, Y., Ni, Z., Zhou, X., Wen, H., Zou, Y.: DoReFa-Net: training low bitwidth convolutional neural networks with low bitwidth gradients. arXiv (2016)"},{"key":"21_CR48","unstructured":"Zhu, S., Li, C., Change Loy, C., Tang, X.: Face alignment by coarse-to-fine shape searching. In: CVPR (2015)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01219-9_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,6]],"date-time":"2022-10-06T01:11:25Z","timestamp":1665018685000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01219-9_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012182","9783030012199"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01219-9_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"7 October 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}