今日CS.CV 计算机视觉论文速览
Thu, 2 May 2019
Totally 22 papers
?上期速览✈更多精彩请移步主页
Interesting:
?3DFaceGAN, 基于对抗网络的三维人脸表示、生成和迁移。利用GANs对3D人脸表面的分布进行建模,保持了3D外形的高频细节。(from 帝国理工)
首先使用非刚体的表示,并将xyz顶点转到了UV空间中去,最后在UV空间中进行插值、实现三位重建。
架构图:
与现有的几种方法作比较:
?Learn to synthesize and synthesize to learn, 基于单模型的属性引导人脸生产,将输入人脸通过属性迁移到多个不同域中去。(from 洛桑理工)
属性引导的面部图像合成以及位姿归一化模型:
code:https://github.com/CreativePapers/Learn-to-Synthesize-and-Synthesize-to-Learn
?快速数据增强算法Fast AutoAugment, (from kakaobrain kr)
code:https://github.com/kakaobrain/fast-autoaugment
web:https://www.kakaobrain.com/
?基于神经网络检测干豆开裂比例, (from 密歇根州立)
dataset:https://www.egr.msu.edu/drybeans/
?基于多层自编码器的图像修复, (from IIT Gandhinagar)
模型中包含的不同组件:
最后的结果,在缺失10%后依然可以有效恢复:
![在这里插入图片描述](https://img-blog.csdnimg.cn/20190502213734721.png =600X)
?基于计算机视觉的动态恶意软件检测和解释, (from 因特尔,佐治亚理工)
Daily Computer Vision Papers
[1] Title: Pushing the Boundaries of View Extrapolation with Multiplane Images
Authors:Pratul P. Srinivasan, Richard Tucker, Jonathan T. Barron, Ravi Ramamoorthi, Ren Ng, Noah Snavely
[2] Title: Learn Stereo, Infer Mono: Siamese Networks for Self-Supervised, Monocular, Depth Estimation
Authors:Matan Goldman, Tal Hassner, Shai Avidan
[3] Title: Sex-Prediction from Periocular Images across Multiple Sensors and Spectra
Authors:Juan Tapia, Christian Rathgeb, Christoph Busch
[4] Title: Estimation of Tissue Oxygen Saturation from RGB images and Sparse Hyperspectral Signals based on Conditional Generative Adversarial Network
Authors:Qingbiao Li, Jianyu Lin, Neil T.Clancy, Daniel S. Elson
[5] Title: Gender Classification from Iris Texture Images Using a New Set of Binary Statistical Image Features
Authors:Juan Tapia, Claudia Arellano
[6] Title: Bean Split Ratio for Dry Bean Canning Quality and Variety Analysis
Authors:Yunfei Long, Amber Bassett, Karen Cichy, Addie Thompson, Daniel Morris
[7] Title: Towards computer vision powered color-nutrient assessment of pureed food
Authors:Kaylen J. Pfisterer, Robert Amelard, Braeden Syrnyk, Alexander Wong
[8] Title: 3DFaceGAN: Adversarial Nets for 3D Face Representation, Generation, and Translation
Authors:Stylianos Moschoglou, Stylianos Ploumpis, Mihalis Nicolaou, Stefanos Zafeiriou
[9] Title: AdaCos: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representations
Authors:Xiao Zhang, Rui Zhao, Yu Qiao, Xiaogang Wang, Hongsheng Li
[10] Title: Learn to synthesize and synthesize to learn
Authors:Behzad Bozorgtabar, Mohammad Saeed Rad, Hazım Kemal Ekenel, Jean-Philippe Thiran
[11] Title: Automatic Dataset Augmentation Using Virtual Human Simulation
Authors:Marcelo C. Ghilardi, Leandro Dihl, Estevão Testa, Pedro Braga, João P. Pianta, Isabel H. Manssour, Soraia R. Musse
[12] Title: Unsupervised Temperature Scaling: Post-Processing Unsupervised Calibration of Deep Models Decisions
Authors:Azadeh Sadat Mozafari, Hugo Siqueira Gomes, Wilson Leão, Christian Gagné
[13] Title: Precise Synthetic Image and LiDAR (PreSIL) Dataset for Autonomous Vehicle Perception
Authors:Braden Hurl, Krzysztof Czarnecki, Steven Waslander
[14] Title: Self-Supervised Convolutional Subspace Clustering Network
Authors:Junjian Zhang, Chun-Guang Li, Chong You, Xianbiao Qi, Honggang Zhang, Jun Guo, Zhouchen Lin
[15] Title: Harmonic Networks with Limited Training Samples
Authors:Matej Ulicny, Vladimir A. Krylov, Rozenn Dahyot
[16] Title: Predicting How to Distribute Work Between Algorithms and Humans to Segment an Image Batch
Authors:Danna Gurari, Yinan Zhao, Suyog Dutt Jain, Margrit Betke, Kristen Grauman
[17] Title: Attentive Spatio-Temporal Representation Learning for Diving Classification
Authors:Gagan Kanojia, Sudhakar Kumawat, Shanmuganathan Raman
[18] Title: Appearance and Pose-Conditioned Human Image Generation using Deformable GANs
Authors:Aliaksandr Siarohin, Stéphane Lathuilière, Enver Sangineto, Nicu Sebe
[19] Title: Cross Domain Knowledge Learning with Dual-branch Adversarial Network for Vehicle Re-identification
Authors:Jinjia Peng, Huibing Wang, Xianping Fu
[20] Title: Fast AutoAugment
Authors:Sungbin Lim, Ildoo Kim, Taesup Kim, Chiheon Kim, Sungwoong Kim
[21] Title: Multi-level Encoder-Decoder Architectures for Image Restoration
Authors:Indra Deep Mastan, Shanmuganathan Raman
[22] Title: To believe or not to believe: Validating explanation fidelity for dynamic malware analysis
Authors:Li Chen, Carter Yagemann, Evan Downing