【今日CS 视觉论文速览】Mon, 18 Feb 2019
今日CS.CV计算机视觉论文速览
Mon, 18 Feb 2019
Totally 18 papers
Interesting:
?LFFN用于单图超分辨的轻量级特征融合网络, 研究探索了多尺度内容特征并基于最大化SISR极大减少了网络参数。网络模型建立在纺锤单元和特征融合模块上，其中纺锤快由扩维单元、特征探索单元和特征精炼单元组成。扩维层探索了低维到高维的适用于下一阶段的特征图、特征探索单元在不同特征图上进行了线性和非线性的特征探索、最后特征融合精炼各级特征。SFFM（softmax feature fusion module）基于自适应学习融合不同特征将各层级的信息用少量参数充分利用起来。(from 清华深研院)
模型架构：
纺锤快构造：
融合模块的构造：
结果：
相关方法：
相关数据集：Set5 [21], Manga109[22], BSD100 [23], Urban100 [24].
?生物医学图像领域的三个问题，通过交互式机器学习提高体渲染的质量和效率、通过迁移学习实现更好的预处理并在阿尔茨海默症上得到更好的训练结果、利用Tversky损失有效解决了分割问题中的数据不平衡问题。（from 加拿大瑞尔森大学多媒体实验室）
- Case Study I:https://github.com/naimulkhan/SOMVolRen
- Case Study II: https://github.com/marciahon29/AlzheimersProject/
- Case Study III: https://github.com/nabsabraham/focal-tversky-unet
阿尔茨海默数据集：http://adni.loni.usc.edu/
?街景数据集Street Scene与异常检测，(from 北卡州立大学 剑桥)
常见的街景数据集和异常行为：
两种算法：
Track-Based Detection Criterion
Region-Based Detection Criterion
?用于遥感图像检索的三元网络,(from 诺丁汉宁波)
dataset:PatternNet
?基于多模态注意力迁移嵌入的视觉关系网络,在低维度空间中探索了物体间的空间-语言关系。(from 雅典技术大学)
VDR数据集
模型架构：
相关工作：
一些结果：
Daily Computer Vision Papers
[1] **Title: Machine Learning on Biomedical Images: Interactive Learning, Transfer Learning, Class Imbalance, and Beyond
Authors:Naimul Mefraz Khan, Nabila Abraham, Ling Guan
[2] **Title: Street Scene: A new dataset and evaluation protocol for video anomaly detection
Authors:Barathkumar Ramachandra, Michael Jones
[3] *Title: Deeply Supervised Multimodal Attentional Translation Embeddings for Visual Relationship Detection
Authors:Nikolaos Gkanatsios, Vassilis Pitsikalis, Petros Koutras, Athanasia Zlatintsi, Petros Maragos
[4] Title: Enhancing Remote Sensing Image Retrieval with Triplet Deep Metric Learning Network
Authors:Rui Cao, Qian Zhang, Jiasong Zhu, Qing Li, Qingquan Li, Bozhi Liu, Guoping Qiu
[5] *Title: Unsupervised shape and motion analysis of 3822 cardiac 4D MRIs of UK Biobank
Authors:Qiao Zheng, Hervé Delingette, Kenneth Fung, Steffen E. Petersen, Nicholas Ayache
[6] **Title: Lightweight Feature Fusion Network for Single Image Super-Resolution
Authors:Wenming Yang, Wei Wang, Xuechen Zhang, Shuifa Sun, Qingmin Liao
[7] *Title: Breaking the Spatio-Angular Trade-off for Light Field Super-Resolution via LSTM Modelling on Epipolar Plane Images
Authors:Hao Zhu, Mantang Guo, Hongdong Li, Qing Wang, Antonio Robles-Kelly
[8] Title: Cycle-Consistency for Robust Visual Question Answering
Authors:Meet Shah, Xinlei Chen, Marcus Rohrbach, Devi Parikh
[9] Title: Massively Parallel Benders Decomposition for Correlation Clustering
Authors:Margret Keuper, Maneesh Singh, Julian Yarkony
[10] *Title: TMAV: Temporal Motionless Analysis of Video using CNN in MPSoC
Authors:Somdip Dey, Amit K. Singh, Dilip K. Prasad, Klaus D. McDonald-Maier
[11] **Title: Going Deep in Medical Image Analysis: Concepts, Methods, Challenges and Future Directions
Authors:Fouzia Altaf, Syed M. S. Islam, Naveed Akhtar, Naeem K. Janjua
[12] **Title: GeoGAN: A Conditional GAN with Reconstruction and Style Loss to Generate Standard Layer of Maps from Satellite Images
Authors:Swetava Ganguli, Pedro Garzon, Noa Glaser
[13] Title: Improving Catheter Segmentation & Localization in 3D Cardiac Ultrasound Using Direction-Fused FCN
Authors:Hongxu Yang, Caifeng Shan, Alexander F. Kolen, Peter H.N. de With
[14] **Title: Estimation of blood oxygenation with learned spectral decoloring for quantitative photoacoustic imaging (LSD-qPAI)
Authors:Janek Gröhl, Thomas Kirchner, Tim Adler, Lena Maier-Hein
[15] Title: Network Offloading Policies for Cloud Robotics: a Learning-based Approach
Authors:Sandeep Chinchali, Apoorva Sharma, James Harrison, Amine Elhafsi, Daniel Kang, Evgenya Pergament, Eyal Cidon, Sachin Katti, Marco Pavone
[16] **Title: Lipschitz Generative Adversarial Nets
Authors:Zhiming Zhou, Jiadong Liang, Yuxuan Song, Lantao Yu, Hongwei Wang, Weinan Zhang, Yong Yu, Zhihua Zhang
[17] Title: Can Intelligent Hyperparameter Selection Improve Resistance to Adversarial Examples?
Authors:Cody Burkard, Brent Lagesse
[18] *Title: Adversarially Approximated Autoencoder for Image Generation and Manipulation
Authors:Wenju Xu, Shawn Keshmiri, Guanghui Wang
Papers from arxiv.org
更多精彩请移步主页
pic from pixels.com