【今日CS 視覺論文速覽】 9 Jan 2019

今日CS.CV計算機視覺論文速覽

Wed, 9 Jan 2019

Totally 28 papers

Interesting:

• GILT,基于文本創造對應的圖像，可廣泛用于插圖、封面生成、菜單生成圖像等。

  

  Code：https://github.com/netanelyo/Recipe2ImageGAN

  圖像與文字描述資料集：recipe1M,Im2recipe

  related:HDGAN, AttnGAN,StackGAN++

• FakeCatcher,利用生物信号來檢測合成視訊與圖像，對抗deepfake等技術。研究人員利用面部區域生物信号的時空特征來檢測合成圖像。首先對于成對的分離使用一進制或者二進制信号轉換(photoplethysmography, rPPG or iPPG;head motion based ballistocardiogram, BCD)達到了99.39%的準确率，随後基于此建立了通用的分類器，通過分析特征圖和信号轉換後的特征來鑒别合成圖像。(from 伯明翰大學 facebook)

  

  合成資料Dataset: Face Forensics dataset， Deep Fakes dataset

  ref:導師http://www.cs.binghamton.edu/~lijun/

  web:http://filterfakers.com/catcher

  Face2Face vid2vid Deep Video Portraits

• 位姿引導的模特真實圖像生成模型,在粗糙位姿的引導下，身着服飾的模特照片可以通過模型的處理得到目标姿勢的新照片。研究人員提出端到端的網絡來對轉換的細節進行控制無需配對圖像。(from 蘇黎世理工 AIT Lab)

  

  網絡模型模型如下圖所示，其中推理的時候可以用衣着風格照片也可以用類别編碼來輸入目标風格：

  

  dataset：

  模特資料和衣着類别标簽來自于：https://www.zalando.ch/

  模特衣着和位姿資料：Chictopia10K dataset, Latent Sketch Module ,Conditional Sketch Module,Portray Module

  realted: A Generative Model of People in Clothing

  http://www.chictopia.com/

Daily Computer Vision Papers

[1] Title: Panoptic Feature Pyramid Networks

Authors:Alexander Kirillov, Ross Girshick, Kaiming He, Piotr Dollár

[2] Title: Unseen Object Segmentation in Videos via Transferable Representations

Authors:Yi-Wen Chen, Yi-Hsuan Tsai, Chu-Ya Yang, Yen-Yu Lin, Ming-Hsuan Yang

[3] Title: Stable Electromyographic Sequence Prediction During Movement Transitions using Temporal Convolutional Networks

Authors:Joseph L. Betthauser, John T. Krall, Rahul R. Kaliki, Matthew S. Fifer, Nitish V. Thakor

[4] Title: Richer and Deeper Supervision Network for Salient Object Detection

Authors:Sen Jia, Neil D. B. Bruce

[5] Title: Morphological Networks for Image De-raining

Authors:Ranjan Mondal, Pulak Purkait, Sanchayan Santra, Bhabatosh Chanda

[6] Title: GILT: Generating Images from Long Text

Authors:Ori Bar El, Ori Licht, Netanel Yosephian

[7] Title: Robust and High Performance Face Detector

Authors:Yundong Zhang, Xiang Xu, Xiaotao Liu

[8] Title: Unpaired Pose Guided Human Image Generation

Authors:Xu Chen, Jie Song, Otmar Hilliges

[9] Title: 3D Object Detection Using Scale Invariant and Feature Reweighting Networks

Authors:Xin Zhao, Zhe Liu, Ruolan Hu, Kaiqi Huang

[10] Title: Interpretable BoW Networks for Adversarial Example Detection

Authors:Krishna Kanth Nakka, Mathieu Salzmann

[11] Title: FakeCatcher: Detection of Synthetic Portrait Videos using Biological Signals

Authors:Umur Aybars Ciftci, Ilke Demir

[12] Title: Explaining AlphaGo: Interpreting Contextual Effects in Neural Networks

Authors:Zenan Ling, Haotian Ma, Yu Yang, Robert C. Qiu, Song-Chun Zhu, Quanshi Zhang

[13] Title: Ensembles of feedforward-designed convolutional neural networks

Authors:Yueru Chen, Yijing Yang, Wei Wang, C.-C. Jay Kuo

[14] Title: Spatial-Winograd Pruning Enabling Sparse Winograd Convolution

Authors:Jiecao Yu, Jongsoo Park, Maxim Naumov

[15] Title: Dynamics are Important for the Recognition of Equine Pain in Video

Authors:Sofia Broomé, Karina Bech Gleerup, Pia Haubro Andersen, Hedvig Kjellström

[16] Title: All Graphs Lead to Rome: Learning Geometric and Cycle-Consistent Representations with Graph Convolutional Networks

Authors:Stephen Phillips, Kostas Daniilidis

[17] Title: Convolutional Neural Networks on non-uniform geometrical signals using Euclidean spectral transformation

Authors:Chiyu “Max” Jiang, Dequan Wang, Jingwei Huang, Philip Marcus, Matthias Nießner

[18] Title: Reproducibility Evaluation of SLANT Whole Brain Segmentation Across Clinical Magnetic Resonance Imaging Protocols

Authors:Yunxi Xiong, Yuankai Huo, Jiachen Wang, L. Taylor Davis, Maureen McHugo, Bennett A. Landman

[19] Title: Spherical CNNs on Unstructured Grids

Authors:Chiyu “Max” Jiang, Jingwei Huang, Karthik Kashinath, Prabhat, Philip Marcus, Matthias Niessner

[20] Title: Self-Supervised Learning from Web Data for Multimodal Retrieval

Authors:Raul Gomez, Lluis Gomez, Jaume Gibert, Dimosthenis Karatzas

[21] Title: Forecasting People Trajectories and Head Poses by Jointly Reasoning on Tracklets and Vislets

Authors:Irtiza Hasan, Francesco Setti, Theodore Tsesmelis, Vasileios Belagiannis, Sikandar Amin, Alessio Del Bue, Marco Cristani, Fabio Galasso

[22] Title: Truncated nuclear norm regularization for low-rank tensor completion

Authors:Shengke Xue, Wenyuan Qiu, Fan Liu, Xinyu Jin

[23] Title: Fully-automatic segmentation of kidneys in clinical ultrasound images using a boundary distance regression network

Authors:Shi Yin, Zhengqiang Zhang, Hongming Li, Qinmu Peng, Xinge You, Susan L. Furth, Gregory E. Tasian, Yong Fan

[24] Title: Learning with Collaborative Neural Network Group by Reflection

Authors:Zehua Cheng, Liyao Gao

[25] Title: Interpretable CNNs

Authors:Quanshi Zhang, Ying Nian Wu, Song-Chun Zhu

[26] Title: Sparse One-Time Grab Sampling of Inliers

Authors:Maryam Jaberi, Marianna Pensky, Hassan Foroosh

[27] Title: FIGR: Few-shot Image Generation with Reptile

Authors:Louis Clouâtre, Marc Demers

[28] Title: On the Dimensionality of Embeddings for Sparse Features and Data

Authors:Maxim Naumov

Papers from arxiv.org

更多精彩請移步首頁

pic from pixels.com