請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/74641
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 莊永裕(Yung-Yu Chuang),林彥宇(Yen-Yu Lin) | |
dc.contributor.author | Tsun-Yi Yang | en |
dc.contributor.author | 楊存毅 | zh_TW |
dc.date.accessioned | 2021-06-17T08:47:22Z | - |
dc.date.available | 2019-08-16 | |
dc.date.copyright | 2019-08-16 | |
dc.date.issued | 2019 | |
dc.date.submitted | 2019-08-05 | |
dc.identifier.citation | [1] EirikurAgustsson,RaduTimofte,andLucVanGool.Anchoredregressionnetworks applied to age estimation and super resolution. In Proceedings of the IEEE Confer- ence on International Conference on Computer Vision (ICCV), 2017.
[2] Relja Arandjelovic, Petr Gronat, Akihiko Torii, Tomas Pajdla, and Josef Sivic. NetVLAD: CNN architecture for weakly supervised place recognition. In Proceed- ings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. [3] Relja Arandjelovic and Andrew Zisserman. All about VLAD. In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition (CVPR), 2013. [4] Relja Arandjelović and Andrew Zisserman. Dislocation: Scalable descriptor dis- tinctiveness for location recognition. In Proceedings of the Asian Conference on Computer Vision (ACCV), 2014. [5] Vassileios Balntas, Shuda Li, and VA Prisacariu. Relocnet: Continous metric learn- ing relocalisation using neural nets. In Proceedings of the European Conference on Computer Vision (ECCV), 2018. [6] Eric Brachmann, Alexander Krull, Sebastian Nowozin, Jamie Shotton, Frank Michel, Stefan Gumhold, and Carsten Rother. Dsac-differentiable ransac for cam- era localization. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. [7] Eric Brachmann and Carsten Rother. Learning less is more-6d camera localization via 3d surface regression. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018. [8] Adrian Bulat and Georgios Tzimiropoulos. How far are we from solving the 2D & 3D face alignment problem? (and a dataset of 230,000 3D facial landmarks). In Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017. [9] Kaidi Cao, Yu Rong, Cheng Li, Xiaoou Tang, and Chen Change Loy. Pose-robust face recognition via deep residual equivariant mapping. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018. [10] XudongCao,YichenWei,FangWen,andJianSun.Facealignmentbyexplicitshape regression. International Journal of Computer Vision (IJCV), 107(2):177–190, 2014. [11] Tommaso Cavallari, Stuart Golodetz, Nicholas A Lord, Julien Valentin, Vic- tor A Prisacariu, Luigi Di Stefano, and Philip HS Torr. Real-time rgb-d cam- era pose estimation in novel scenes using a relocalisation cascade. arXiv preprint arXiv:1810.12163, 2018. [12] Tommaso Cavallari, Stuart Golodetz, Nicholas A Lord, Julien PC Valentin, Luigi Di Stefano, and Philip HS Torr. On-the-fly adaptation of regression forests for online camera relocalisation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. [13] Chih-Chung Chang and Chih-Jen Lin. LIBSVM: A library for support vector ma- chines. ACM transactions on intelligent systems and technology (TIST), 2(3):27, 2011. [14] Feng Ju Chang, Anh Tuan Tran, Tal Hassner, Iacopo Masi, Ram Nevatia, and Ger- ard Medioni. FacePoseNet: Making a case for landmark-free face alignment. In Proceedings of the IEEE International Conference on Computer Vision Workshops (ICCVw), 2017. [15] Kuang-Yu Chang, Chu-Song Chen, and Yi-Ping Hung. Ordinal hyperplanes ranker with cost sensitivities for age estimation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011. [16] Dong Chen, Shaoqing Ren, Yichen Wei, Xudong Cao, and Jian Sun. Joint cascade face detection and alignment. In Proceedings of the IEEE Conference on European Conference on Computer Vision (ECCV), 2014. [17] ShixingChen,CaojinZhang,MingDong,JialiangLe,andMikeRao.Usingranking- CNN for age estimation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. [18] EunjiChong,NatanielRuiz,YongxinWang,YunZhang,AgataRozga,andJamesM Rehg. Connecting gaze, scene, and attention: Generalized attention estimation via joint modeling of gaze and scene saliency. In Proceedings of the IEEE Conference on European Conference on Computer Vision (ECCV), 2018. [19] Grigorios G Chrysos, Epameinondas Antonakos, Patrick Snape, Akshay Asthana, and Stefanos Zafeiriou. A comprehensive performance evaluation of deformable face tracking “in-the-wild”. International Journal of Computer Vision, 126(2- 4):198–232, 2018. [20] Ronald Clark, Sen Wang, Andrew Markham, Niki Trigoni, and Hongkai Wen. Vid- loc: A deep spatio-temporal model for 6-dof video-clip relocalization. In Proceed- ings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. [21] Timothy F Cootes, Christopher J Taylor, David H Cooper, and Jim Graham. Active shape models-their training and application. Computer vision and image understand- ing, 61(1):38–59, 1995. [22] Daniel F DeMenthon and Larry S Davis. Model-based object pose in 25 lines of code. In Proceedings of the IEEE Conference on European Conference on Computer Vision (ECCV), 1992. [23] Piotr Dollár, Peter Welinder, and Pietro Perona. Cascaded pose regression. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2010. [24] Gabriele Fanelli, Matthias Dantone, Juergen Gall, Andrea Fossati, and Luc Van Gool. Random forests for real time 3D face analysis. International Journal of Computer Vision (IJCV), 101(3):437–458, 2013. [25] Gabriele Fanelli, Thibaut Weise, Juergen Gall, and Luc Van Gool. Real time head pose estimation from consumer depth cameras. In Joint Pattern Recognition Sym- posium, pages 101–110. Springer, 2011. [26] Martin A Fischler and Robert C Bolles. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM, 1981. [27] Xin Geng, Qin Wang, and Yu Xia. Facial age estimation by adaptive label distribu- tion learning. In Proceedings of the International Conference on Pattern Recognition (ICPR), pages 4465–4470, 2014. [28] Petr Gronat, Guillaume Obozinski, Josef Sivic, and Tomas Pajdla. Learning and calibrating per-location classifiers for visual place recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013. [29] JinweiGu,XiaodongYang,ShaliniDeMello,andJanKautz.Dynamicfacialanaly- sis: From Bayesian filtering to recurrent neural network. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. [30] RichardHartleyandAndrewZisserman.Multipleviewgeometryincomputervision. Cambridge university press, 2003. [31] PengHou,XinGeng,Zeng-WeiHuo,andJia-QiLv.Semi-supervisedadaptivelabel distribution learning for facial age estimation. In Proceedings of the AAAI Confer- ence on Artificial Intelligence, pages 2015–2021, 2017. [32] Andrew G Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. MobileNets: Efficient con- volutional neural networks for mobile vision applications. arXiv:1704.04861, 2017. [33] GaoHuang,ZhuangLiu,LaurensvanderMaaten,andKilianQWeinberger.Densely connected convolutional networks. In Proceedings of the IEEE Conference on Com- puter Vision and Pattern Recognition (CVPR), 2017. [34] Amine Kacete, Thomas Wentz, and Jérôme Royan. Decision forest for efficient and robust camera relocalization. In Proceedings of the IEEE International Symposium on Mixed and Augmented Reality (ISMAR-Adjunct), 2017. [35] Vahid Kazemi and Josephine Sullivan. One millisecond face alignment with an en- semble of regression trees. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014. [36] Alex Kendall and Roberto Cipolla. Modelling uncertainty in deep learning for cam- era relocalization. In Proceedings of the IEEE international conference on Robotics and Automation (ICRA), 2016. [37] Alex Kendall, Roberto Cipolla, et al. Geometric loss functions for camera pose regression with deep learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. [38] Alex Kendall, Matthew Grimes, and Roberto Cipolla. Posenet: A convolutional network for real-time 6-dof camera relocalization. In Proceedings of the IEEE In- ternational Conference on Computer Vision (ICCV), 2015. [39] Diederik Kingma and Jimmy Ba. Adam: A method for stochastic optimization. arXiv:1412.6980, 2014. [40] Martin Koestinger, Paul Wohlhart, Peter M Roth, and Horst Bischof. Annotated facial landmarks in the wild: A large-scale, real-world database for facial landmark localization. In Proceedings of the IEEE Conference on International Conference on Computer Vision Workshops (ICCVw), 2011. [41] Amit Kumar, Azadeh Alavi, and Rama Chellappa. KEPLER: Keypoint and pose es- timation of unconstrained faces by learning efficient H-CNN regressors. In Proceed- ings of the IEEE International Conference on Automatic Face and Gesture Recog- nition, 2017. [42] Donghoon Lee, Hyunsin Park, and Chang D Yoo. Face alignment using cascade Gaussian process regression trees. In Proceedings of the IEEE Conference on Com- puter Vision and Pattern Recognition (CVPR), 2015. [43] Lin Liang, Rong Xiao, Fang Wen, and Jian Sun. Face alignment via component- based discriminative search. In Proceedings of the European Conference on Com- puter Vision (ECCV), 2008. [44] Liu Liu, Hongdong Li, and Yuchao Dai. Efficient global 2d-3d matching for cam- era localization in a large-scale 3d map. In Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017. [45] Xin Liu, Shaoxin Li, Meina Kan, Jie Zhang, Shuzhe Wu, Wenxian Liu, Hu Han, Shiguang Shan, and Xilin Chen. AgeNet: Deeply learned regressor and classifier for robust apparent age estimation. In Proceedings of the IEEE International Conference on Computer Vision Workshops (ICCVw), 2015. [46] Refik Can Malli, Mehmet Aygün, and Hazim Kemal Ekenel. Apparent age estima- tion using ensemble of deep learning models. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRw), 2016. [47] Manuel Martin, Florian Van De Camp, and Rainer Stiefelhagen. Real time head model creation and head pose estimation on consumer depth cameras. In 2014 2nd International Conference on 3D Vision (3DV), 2014. [48] Iain Matthews and Simon Baker. Active appearance models revisited. International journal of computer vision, 60(2):135–164, 2004. [49] Iaroslav Melekhov, Juha Ylioinas, Juho Kannala, and Esa Rahtu. Image-based lo- calization using hourglass networks. arXiv preprint arXiv:1703.07971, 2017. [50] Gregory P Meyer, Shalini Gupta, Iuri Frosio, Dikpal Reddy, and Jan Kautz. Robust model-based 3D head pose estimation. In Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2015. [51] Sankha S Mukherjee and Neil Martin Robertson. Deep head pose: Gaze-direction estimation in multimodal video. IEEE Transactions on Multimedia, 17(11):2094– 2107, 2015. [52] Erik Murphy-Chutorian and Mohan Manubhai Trivedi. Head pose estimation in computer vision: A survey. IEEE transactions on pattern analysis and machine intelligence, 31(4):607–626, 2009. [53] Zhenxing Niu, Mo Zhou, Le Wang, Xinbo Gao, and Gang Hua. Ordinal regression with multiple output CNN for age estimation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 4920–4928, 2016. [54] Narayanan Ramanathan, Rama Chellappa, and Soma Biswas. Age progression in human faces: A survey. Journal of Visual Languages and Computing, 15:3349– 3361, 2009. [55] Rajeev Ranjan, Vishal M. Patel, and Rama Chellappa. HyperFace: A deep multi- task learning framework for face detection, landmark localization, pose estimation, and gender recognition. Journal of the IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017. [56] Rajeev Ranjan, Swami Sankaranarayanan, Carlos D. Castillo, and Rama Chellappa. An all-in-one convolutional neural network for face analysis. In Proceedings of the IEEE International Conference on Automatic Face and Gesture Recognition, 2017. [57] Karl Ricanek and Tamirat Tesafaye. MORPH: A longitudinal image database of normal adult age-progression. In Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition, pages 341–345, 2006. [58] Rasmus Rothe, Radu Timofte, and Luc Van Gool. DEX: Deep expectation of appar- ent age from a single image. In Proceedings of the IEEE International Conference on Computer Vision Workshops (ICCVw), 2015. [59] Rasmus Rothe, Radu Timofte, and Luc Van Gool. Deep expectation of real and apparent age from a single image without facial landmarks. International Journal of Computer Vision (IJCV), 126(2-4):144–157, 2016. [60] Rasmus Rothe, Radu Timofte, and Luc Van Gool. Some like it hot-visual guidance for preference prediction. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 6663–5561, 2016. [61] Ethan Rublee, Vincent Rabaud, Kurt Konolige, and Gary Bradski. ORB: An ef- ficient alternative to SIFT or SURF. In Proceedings of the IEEE Conference on International Conference on Computer Vision (ICCV), 2011. [62] Nataniel Ruiz, Eunji Chong, and James M. Rehg. Fine-grained head pose estima- tion without keypoints. In Proceedings of the IEEE International Conference on Computer Vision Workshops (ICCVw), 2017. [63] OlgaRussakovsky,JiaDeng,HaoSu,JonathanKrause,SanjeevSatheesh,SeanMa, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein, Alexander Berg, and Li Fei-Fei. ImageNet large scale visual recognition challenge. Interna- tional Journal of Computer Vision (IJCV), 115(3):211–252, 2015. [64] Sara Sabour, Nicholas Frosst, and Geoffrey E Hinton. Dynamic routing between capsules. In Advances in Neural Information Processing Systems, pages 3856–3866, 2017. [65] Christos Sagonas, Georgios Tzimiropoulos, Stefanos Zafeiriou, and Maja Pantic. 300 faces in-the-wild challenge: The first facial landmark localization challenge. In Proceedings of the IEEE International Conference on Computer Vision Workshops (ICCVw), 2013. [66] TorstenSattler,MichalHavlena,KonradSchindler,andMarcPollefeys.Large-scale location recognition and the geometric burstiness problem. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. [67] Torsten Sattler, Will Maddern, Carl Toft, Akihiko Torii, Lars Hammarstrand, Erik Stenborg, Daniel Safari, Masatoshi Okutomi, Marc Pollefeys, Josef Sivic, et al. Benchmarking 6dof outdoor visual localization in changing conditions. In Proceed- ings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018. [68] Torsten Sattler, Akihiko Torii, Josef Sivic, Marc Pollefeys, Hajime Taira, Masatoshi Okutomi, and Tomas Pajdla. Are large-scale 3d models really necessary for accurate visual localization? In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. [69] Karen Simonyan and Andrew Zisserman. Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556, 2014. [70] YiSun,XiaogangWang,andXiaoouTang.Deepconvolutionalnetworkcascadefor facial point detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013. [71] Hajime Taira, Masatoshi Okutomi, Torsten Sattler, Mircea Cimpoi, Marc Pollefeys, Josef Sivic, Tomas Pajdla, and Akihiko Torii. Inloc: Indoor visual localization with dense matching and view synthesis. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018. [72] Zichang Tan, Jun Wan, Zhen Lei, Ruicong Zhi, Guodong Guo, and Stan ZQ Li. Ef- ficient group-n encoding and decoding for facial age estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2018. [73] CarlToft,ErikStenborg,LarsHammarstrand,LucasBrynte,MarcPollefeys,Torsten Sattler, and Fredrik Kahl. Semantic match consistency for long-term visual localization. In Proceedings of the European Conference on Computer Vision (ECCV), 2018. [74] Akihiko Torii, Relja Arandjelovic, Josef Sivic, Masatoshi Okutomi, and Tomas Pa- jdla. 24/7 place recognition by view synthesis. In Proceedings of the IEEE Confer- ence on Computer Vision and Pattern Recognition, 2015. [75] Akihiko Torii, Josef Sivic, Tomas Pajdla, and Masatoshi Okutomi. Visual place recognition with repetitive structures. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013. [76] Luan Tran, Xi Yin, and Xiaoming Liu. Disentangled representation learning GAN for pose-invariant face recognition. In Proceedings of the IEEE Conference on Com- puter Vision and Pattern Recognition (CVPR), 2017. [77] Florian Walch, Caner Hazirbas, Laura Leal-Taixe, Torsten Sattler, Sebastian Hilsen- beck, and Daniel Cremers. Image-based localization using lstms for structured fea- ture correlation. In Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017. [78] Xuehan Xiong and Fernando De la Torre. Supervised descent method and its ap- plications to face alignment. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013. [79] Xuehan Xiong and Fernando De la Torre. Global supervised descent method. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015. [80] Tsun-Yi Yang, Jo-Han Hsu, Yen-Yu Lin, and Yung-Yu Chuang. DeepCD: Learning deep complementary descriptors for patch representations. In Proceedings of the IEEE Conference on International Conference on Computer Vision (ICCV), 2017. [81] Tsun-YiYang,Yi-HsuanHuang,Yen-YuLin,Pi-ChengHsiu,andYung-YuChuang. SSR-Net: A compact soft stagewise regression network for age estimation. In Proceeding of the IEEE International Joint Conference on Artificial Intelligence (IJCAI), 2018. [82] Feifei Zhang, Tianzhu Zhang, Qirong Mao, and Changsheng Xu. Joint pose and expression modeling for facial expression recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018. [83] KaipengZhang,ZhanpengZhang,ZhifengLi,andYuQiao.Jointfacedetectionand alignment using multitask cascaded convolutional networks. IEEE Signal Process- ing Letters, 23(10):1499–1503, 2016. [84] Yunxuan Zhang, Li Liu, Cheng Li, and Chen Change Loy. Quantifying facial age by posterior of age comparisons. Proceedings of British Machine Vision Conference (BMVC), 2017. [85] Xiangxin Zhu and Deva Ramanan. Face detection, pose estimation, and landmark localization in the wild. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012. [86] Xiangyu Zhu, Zhen Lei, Xiaoming Liu, Hailin Shi, and Stan Z Li. Face alignment across large poses: A 3D solution. In Proceedings of the IEEE Conference on Com- puter Vision and Pattern Recognition (CVPR), 2016. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/74641 | - |
dc.description.abstract | 在深度學習茁壯的近十年來,硬體和軟體都為了卷積神經網路 (CNN) 快速地發展,而在大尺度應用上,只追求效能的神經網路會產 生無法負荷且過大的計算成本,導致快速且有效率的研究題目是非常 迫切的。我們先就特徵描述子 (feature descriptor) 到神經網路的演進討 論起,並在本論文中特別討論迴歸問題 (regression) 在深度學習中的應 用。迴歸問題的本質可以分為多種,像是連續性 (continuity)、分群或 量化 (grouping or quanitzation)、分佈性 (distribution) 等等。過去的方法 也曾對這些問題著手,但是卻沒辦法將快速高效和這些面向做有效的 結合。我們討論了在不同的電腦視覺應用下,如何讓過去運算或儲存 的負荷降低到百倍甚至千倍以下,而且仍然維持足夠好的效能和訓練 穩定度。其中我們以臉部年齡估計 (facial age estimation)、頭部角度估 計 (head pose estimation) 作為主題,來表現我們方法的強健程度。 | zh_TW |
dc.description.abstract | In the past few decades, deep learning is growing as fast as it could, and both of the hardware and the software are rapidly developing for the convolutional neural network (CNN). However, in large scale scenario, purely performance driven network will consume too much computational power. Therefore, it is crucial to study fast and efficient neural network. At first, we introduce the process from using feature descriptor to CNN, and we discuss the regression problems in this thesis specifically. The nature of the regression has several aspects such as continuity, grouping or quantization, distribution and so on. Previous research also targets on such problems, but they failed on combining them into an efficient framework. We discuss different computer vision applications with 100× or even 1000× smaller computational cost or memory overhead while maintaining excellent performance and training stability. More specifically, we use facial age estimation and head pose estimation as concrete examples to show the robustness of the pro- posed methods. | en |
dc.description.provenance | Made available in DSpace on 2021-06-17T08:47:22Z (GMT). No. of bitstreams: 1 ntu-108-D03922016-1.pdf: 8360756 bytes, checksum: 1358d1991d7b68c366d8308f079ab495 (MD5) Previous issue date: 2019 | en |
dc.description.tableofcontents | 誌謝 iii
Acknowledgements v 摘要 vii Abstract ix 1 Introduction 1 1.1 Thesis Overview 2 1.1.1 Facial Age Estimation 3 1.1.2 Head Pose Estimation 5 2 Facial Age Estimation 9 2.1 LiteratureReview 9 2.1.1 Regression 9 2.1.2 Multi-Class Classification and Age Grouping 10 2.1.3 Distribution Learning 10 2.1.4 Ordinal Information 10 2.2 Soft Stagewise Regression Network 10 2.2.1 Problem Formulation 11 2.2.2 Stagewise Regression 11 2.2.3 Dynamic Range 13 2.2.4 Network Structure 14 2.2.5 Soft Stagewise Regression 14 2.3 Experiments 15 2.3.1 Preprocessing and Experimental Setting 15 2.3.2 Competing Methods 16 2.3.3 Experimentson IMDB-WIKI 17 2.3.4 Experimentson MORPH2 18 2.3.5 Experimentson MegaAge-Asian 19 2.3.6 Ablation Study on Hyper-parameters 21 2.4 Conclusion 21 3 Head Pose Estimation 23 3.1 Literature Review 23 3.1.1 Landmark-based methods 23 3.1.2 Methods with different modalities 24 3.1.3 Multi-task methods 25 3.2 Fine-grained Structure Aggregation Network 25 3.2.1 Problem formulation 25 3.2.2 SSR-Net-MD 26 3.2.3 Overview of FSA-Net 27 3.2.4 Scoring function 28 3.2.5 Fine-grained structure mapping 29 3.2.6 Details of the architecture 30 3.3 Experiments 31 3.3.1 Implementation 31 3.3.2 Datasets and evaluation protocols 31 3.3.3 Competing methods 33 3.3.4 Results with protocol1 35 3.3.5 Results with protocol2 35 3.3.6 Visualization 36 3.3.7 Ablation study 39 3.3.8 Robustness test 40 3.4 Conclusion 40 4 Summary and Future Work 43 | |
dc.language.iso | en | |
dc.title | 學習高速且高效率的深度學習的迴歸應用 | zh_TW |
dc.title | Deep Feature Learning for Fast and Efficient Regression Application | en |
dc.type | Thesis | |
dc.date.schoolyear | 107-2 | |
dc.description.degree | 博士 | |
dc.contributor.oralexamcommittee | 陳祝嵩(Chu-song Chen),王鈺強(Yu-Chiang Wang),孫民(Min Sun),陳煥宗(Hwann-Tzong Chen),邱維辰(Wei-Chen Chiu) | |
dc.subject.keyword | 卷積神經網路,迴歸,高效率,緊實,快速,年齡,頭部,角度, | zh_TW |
dc.subject.keyword | Convolutional neural networks,regression,efficient,compact,fast,age,head,pose, | en |
dc.relation.page | 55 | |
dc.identifier.doi | 10.6342/NTU201902521 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2019-08-06 | |
dc.contributor.author-college | 電機資訊學院 | zh_TW |
dc.contributor.author-dept | 資訊工程學研究所 | zh_TW |
顯示於系所單位: | 資訊工程學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-108-1.pdf 目前未授權公開取用 | 8.16 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。