【今日CS 视觉论文速览】 11 Jan 2019
今日CS.CV计算机视觉论文速览
Fri, 11 Jan 2019
Totally 25 papers
Interesting:
Multi-Granularity Reasoning framework,用于从图像中推理出人物间的社会关系。这一方法主要依赖于从图像场景和物体的相对位置抽取出全局知识和中间层次的信息，并加上细粒度人体关键点信息和人、物之间的相互作用来判断人物关系。具体来说，研究人员建立了位姿引导的Person-Object Graph 和Person-Pose Graph来为人与物间的行为关系建模，并基于此推理出图像中人物之间的社会关系。（from 北邮 jd）
网络框架如下所示：
一些结果样例：
related methods:
Two stream CNN, Union-CNN, Dual-glance, Graph Reasoning Model, Multi-Granularity Reasoning
数据集：
People in Social Context (PISC), paper
People in Photo Album (PIPA)
一个数据集库
tips:似乎可以利用影视作品中已知社会关系的图像来制作数据集
三维点云分类器的对抗攻击与防御，提出了一种应对三维点云对抗攻击的评价方法，在2维图像的启发下，通过同时评价 white-box and blackbox 对抗攻击来减少对抗样本带来的扰动。研究方向，3D 网络比较容易受到对抗攻击的影响但也容易用简单的方法来防御。（from TPHS、UCSD）
对抗效果热力图，可以发现，laptop和guitar是最容易被攻击的对象：
dataset： ModelNet-40
八卦，本文一作又是一名高中生：
ref:http://ratgenes.org/rehu-2017/
http://2018.igem.org/Team:TPHS_San_Diego/Team
Daily Computer Vision Papers
[1] Title: Multispectral and Hyperspectral Image Fusion by MS/HS Fusion Net
Authors:Qi Xie, Minghao Zhou, Qian Zhao, Deyu Meng, Wangmeng Zuo, Zongben Xu
[2] Title: Region Proposal by Guided Anchoring
Authors:Jiaqi Wang, Kai Chen, Shuo Yang, Chen Change Loy, Dahua Lin
[3] Title: Early recurrence enables figure border ownership
Authors:Paria Mehrani, John K. Tsotsos
[4] Title: On Finding Gray Pixels
Authors:Yanlin Qian, Jarno Nikkanen, Joni-Kristian Kämäräinen, Jiri Matas
[5] Title: Cricket stroke extraction: Towards creation of a large-scale cricket actions dataset
Authors:Arpan Gupta, Sakthi Balan M
[6] Title: Fast GPU-Enabled Color Normalization for Digital Pathology
Authors:Goutham Ramakrishnan, Deepak Anand, Amit Sethi
[7] Title: New Radon Transform Based Texture Features of Handwritten Document
Authors:Rustam Latypov, Evgeni Stolov
[8] Title: Multi-Granularity Reasoning for Social Relation Recognition from Images
Authors:Meng Zhang, Xinchen Liu, Wu Liu, Anfu Zhou, Huadong Ma, Tao Mei
[9] Title: PVSS: A Progressive Vehicle Search System for Video Surveillance Networks
Authors:Xinchen Liu, Wu Liu, Huadong Ma, Shuangqun Li
[10] Title: Hierarchy Neighborhood Discriminative Hashing for An Unified View of Single-Label and Multi-Label Image retrieval
Authors:Lei Ma, Hongliang Li, Qingbo Wu, Fanman Meng, King Ngi Ngan
[11] Title: Image Transformation can make Neural Networks more robust against Adversarial Examples
Authors:Dang Duy Thang, Toshihiro Matsui
[12] Title: Multi-feature Distance Metric Learning for Non-rigid 3D Shape Retrieval
Authors:Huibing Wang, Haohao Li, Xianping Fu
[13] Title: Extending Adversarial Attacks and Defenses to Deep 3D Point Cloud Classifiers
Authors:Daniel Liu, Ronald Yu, Hao Su
[14] Title: A Multi-Object Rectified Attention Network for Scene Text Recognition
Authors:Canjie Luo, Lianwen Jin, Zenghui Sun
[15] Title: Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation
Authors:Chenxi Liu, Liang-Chieh Chen, Florian Schroff, Hartwig Adam, Wei Hua, Alan Yuille, Li Fei-Fei
[16] Title: Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation
Authors:He Wang, Srinath Sridhar, Jingwei Huang, Julien Valentin, Shuran Song, Leonidas J. Guibas
[17] Title: Composite Shape Modeling via Latent Space Factorization
Authors:Anastasia Dubrovina, Fei Xia, Panos Achlioptas, Mira Shalah, Leonidas Guibas
[18] Title: DASPS: A Database for Anxious States based on a Psychological Stimulation
Authors:Asma Baghdadi, Yassine Aribi, Rahma Fourati, Najla Halouani, Patrick Siarry, Adel M. Alimi
[19] Title: SalSi: A new seismic attribute for salt dome detection
Authors:Muhammad Amir Shafiq, Tariq Alshawi, Zhiling Long, Ghassan AlRegib
[20] Title: Trace-back Along Capsules and Its Application on Semantic Segmentation
Authors:Tao Sun, Zhewei Wang, C. D. Smith, Jundong Liu
[21] Title: Myocardial Infarction Quantification From Late Gadolinium Enhancement MRI Using Top-hat Transforms and Neural Networks
Authors:Ezequiel de la Rosa, Désiré Sidibé, Thomas Decourselle, Thibault Leclercq, Alexandre Cochet, Alain Lalande
[22] Title: Motion Perception in Reinforcement Learning with Dynamic Objects
Authors:Artemij Amiranashvili, Alexey Dosovitskiy, Vladlen Koltun, Thomas Brox
[23] Title: Self-Monitoring Navigation Agent via Auxiliary Progress Estimation
Authors:Chih-Yao Ma, Jiasen Lu, Zuxuan Wu, Ghassan AlRegib, Zsolt Kira, Richard Socher, Caiming Xiong
[24] Title: Revealing interpretable object representations from human behavior
Authors:Charles Y. Zheng, Francisco Pereira, Chris I. Baker, Martin N. Hebart
[25] Title: Deep Learning for Human Affect Recognition: Insights and New Developments
Authors:Philipp V. Rouast, Marc T. P. Adam, Raymond Chiong
Papers from arxiv.org
更多精彩请移步主页
TODO
Aca：
用于文字检测的多目标矫正检测方法：https://arxiv.org/pdf/1901.03003.pdf
Int:
多光谱融合：https://arxiv.org/pdf/1901.03281
候选区推举：https://arxiv.org/pdf/1901.03278
寻找灰度像素（R=G=B）：https://arxiv.org/pdf/1901.03198
利用GPU进行颜色归一化：https://arxiv.org/pdf/1901.03088.pdf
分级神经架构检索语义分割：https://arxiv.org/pdf/1901.02985.pdf
强化学习过程中动力学物体的运动感知：https://arxiv.org/pdf/1901.03162.pdf
人类情感检测综述：https://arxiv.org/pdf/1901.02884.pdf
pic from pixels.com