phd文献阅读日志-博一下学期

博一下学期：

1.week1,2018.2.26

2006-Extreme learning machine: theory and applications

期刊来源：Huang G B, Zhu Q Y, Siew C K. Extreme learning machine: theory and applications[J]. Neurocomputing, 2006, 70(1-3): 489-501.

2.week2,2018.3.5

2017-3d-prnn: Generating shape primitives with recurrent neural networks

University of Illinois at Urbana-Champaign, Adobe Research(美国伊利诺伊大学厄巴纳 - 香槟分校，Adobe研究院)

期刊来源：Zou C, Yumer E, Yang J, et al. 3d-prnn: Generating shape primitives with recurrent neural networks[C]//The IEEE International Conference on Computer Vision (ICCV). 2017.

3.week3,2018.3.12;week7,2018.4.9;week8,2018.4.16;week9,2018.4.23

2017-3D object reconstruction from a single depth view with adversarial learning

University of Oxford,University of Warwick,Heriot-Watt University(英国牛津大学，华威大学，赫瑞瓦特大学)

期刊来源：Yang B, Wen H, Wang S, et al. 3D object reconstruction from a single depth view with adversarial learning[J]. ICCV, 2017.

2018-3D Object Dense Reconstruction from a Single Depth View

期刊来源:Yang B, Rosa S, Markham A, et al. 3D Object Dense Reconstruction from a Single Depth View[J]. arXiv preprint arXiv:1802.00411, 2018.

Improved training of wasserstein gans

Montreal Institute for Learning Algorithms,Courant Institute of Mathematical Sciences,CIFAR Fellow(美国科技巨头蒙特利尔学习算法研究所，库特数学科学研究所，CIFAR研究员)

Gulrajani I, Ahmed F, Arjovsky M, et al. Improved training of wasserstein gans[C]//Advances in Neural Information Processing Systems. 2017: 5769-5779.

Generative adversarial nets

期刊来源：Goodfellow I, Pouget-Abadie J, Mirza M, et al. Generative adversarial nets[C]//Advances in neural information processing systems. 2014: 2672-2680.

4.week4,2018.3.19

2017-Hierarchical surface prediction for 3d object reconstruction

University of California, Berkeley(美国加州大学伯克利分校)

期刊来源：Häne C, Tulsiani S, Malik J. Hierarchical surface prediction for 3d object reconstruction[J]. arXiv preprint arXiv:1704.00710, 2017.

2017-Octree generating networks: Efficient convolutional architectures for high-resolution 3d outputs

University of California, Berkeley(美国加州大学伯克利分校)

期刊来源：Tatarchenko M, Dosovitskiy A, Brox T. Octree generating networks: Efficient convolutional architectures for high-resolution 3d outputs[J]. CoRR, abs/1703.09438, 2017.

5.week5,2018.3.26

2017-3D shape reconstruction from sketches via multi-view convolutional networks

University of Massachusetts - Amherst(美国麻省大学阿默斯特分校)

期刊来源：Lun Z, Gadelha M, Kalogerakis E, et al. 3D shape reconstruction from sketches via multi-view convolutional networks[J]. arXiv preprint arXiv:1707.06375, 2017.

2016-3d shape induction from 2d views of multiple objects

University of Massachusetts - Amherst(美国麻省大学阿默斯特分校)

期刊来源：Gadelha M, Maji S, Wang R. 3d shape induction from 2d views of multiple objects[J]. arXiv preprint arXiv:1612.05872, 2016.

2017-Multi-view 3D face reconstruction with deep recurrent neural networks

Computational Biomedicine Lab，University of Houston(美国休斯顿大学,计算生物医学实验室)

期刊来源：Dou P, Kakadiaris I A. Multi-view 3D face reconstruction with deep recurrent neural networks[C]//Biometrics (IJCB), 2017 IEEE International Joint Conference on. IEEE, 2017: 483-492.

2017-End-to-end 3D face reconstruction with deep neural networks

Computational Biomedicine Lab，University of Houston(美国休斯顿大学,计算生物医学实验室)

期刊来源：Dou P, Shah S K, Kakadiaris I A. End-to-end 3D face reconstruction with deep neural networks[C]//Proc. IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, Hawaii. 2017, 5.

6.week6,2018.4.2

2017-Weakly supervised generative adversarial networks for 3d reconstruction

Stanford University(美国斯坦福大学)

期刊来源：Gwak J Y, Choy C B, Garg A, et al. Weakly supervised generative adversarial networks for 3d reconstruction[J]. arXiv preprint arXiv:1705.10904, 2017.

2016-Unsupervised learning of 3d structure from images

NYU Multimedia and Visual Computing Lab(纽约大学,多媒体和视觉计算实验室)

Courant Institute of Mathematical Science(库兰特学院,数学科学研究所)

NYU Tandon School of Engineering, USA(纽约大学工学院)

期刊来源：Rezende D J, Eslami S M A, Mohamed S, et al. Unsupervised learning of 3d structure from images[C]//Advances In Neural Information Processing Systems. 2016: 4996-5004.

2017-Unsupervised 3D Reconstruction from a Single Image via Adversarial Learning

Google DeepMind

期刊来源：Wang L, Fang Y. Unsupervised 3D Reconstruction from a Single Image via Adversarial Learning[J]. arXiv preprint arXiv:1711.09312, 2017.

2017-Began: Boundary equilibrium generative adversarial networks

Google

期刊来源：Berthelot D, Schumm T, Metz L. Began: Boundary equilibrium generative adversarial networks[J]. arXiv preprint arXiv:1703.10717, 2017.

7.week9,2018.4.23

2016-Learning a predictable and generative vector representation for objects

Robotics Institute, Carnegie Mellon University, MITRE Corporation(卡内基梅隆大学,机器人研究所，MITRE公司)

期刊来源：Girdhar R, Fouhey D F, Rodriguez M, et al. Learning a predictable and generative vector representation for objects[C]//European Conference on Computer Vision. Springer, Cham, 2016: 484-499.

2017-Marrnet: 3d shape reconstruction via 2.5 d sketches

MIT CSAIL,ShanghaiTech University,Shanghai Jiao Tong University(麻省理工学院 计算机科学与人工智能实验室,上海科技大学,上海交通大学)

期刊来源：Wu J, Wang Y, Xue T, et al. Marrnet: 3d shape reconstruction via 2.5 d sketches[C]//Advances In Neural Information Processing Systems. 2017: 540-550.

2016-An efficient and effective convolutional auto-encoder extreme learning machine network for 3d feature learning

National University of DefenseTechnology(国防科技大学)

期刊来源：Wang Y, Xie Z, Xu K, et al. An efficient and effective convolutional auto-encoder extreme learning machine network for 3d feature learning[J]. Neurocomputing, 2016, 174: 988-998.

2018-On the convergence of adam and beyond

Google New York

期刊来源：Reddi S J, Kale S, Kumar S. On the convergence of adam and beyond[C]//International Conference on Learning Representations. 2018.

8.week13,2018.5.21

2018-Spherical CNNs

University of Amsterdam(荷兰阿姆斯特丹大学)

期刊来源：Cohen T S, Geiger M, Koehler J, et al. Spherical CNNs[J]. ICLR, 2018.

2016-Group equivariant convolutional networks

University of Amsterdam(荷兰阿姆斯特丹大学)

期刊来源：Cohen T, Welling M. Group equivariant convolutional networks[C]//International Conference on Machine Learning. 2016: 2990-2999.

2017-Learning SO(3) Equivariant Representations with Spherical CNNs

University of Pennsylvania,Google(美国宾夕法尼亚大学)

期刊来源：Esteves C, Allen-Blanchette C, Makadia A, et al. Learning SO(3) Equivariant Representations with Spherical CNNs[J]. 2017.

2018-HexaConv

University of Amsterdam(荷兰阿姆斯特丹大学)

期刊来源：Hoogeboom E, Peters J W T, Cohen T S, et al. HexaConv[J]. arXiv preprint arXiv:1803.02108, 2018.

9.week15,2018.6.4

2016-View synthesis by appearance flow

University of California, Berkeley(美国加州大学伯克利分校)

期刊来源：Zhou T, Tulsiani S, Sun W, et al. View synthesis by appearance flow[C]//European conference on computer vision. Springer, Cham, 2016: 286-301.