arXiv daily

计算机视觉每日论文速递[08.01]

2019-08-01  本文已影响39人  arXiv每日论文速递

同步wx订阅号(arXiv每日论文速递),支持后台回复'search 关键词'查询相关的最新论文。有些许帮助的话,麻烦关注一下哦(* ̄rǒ ̄)

cs.CV 方向,今日共计32篇

[检测分类相关]:

【1】 Synthetic Image Augmentation for Improved Classification using Generative Adversarial Networks
利用生成对抗性网络改进分类的合成图像增强
作者: Keval Doshi
链接:https://arxiv.org/abs/1907.13576

【2】 Competing Ratio Loss for Discriminative Multi-class Image Classification
区分多类图像分类的竞争比损失
作者: Ke Zhang, Tony X. Han
链接:https://arxiv.org/abs/1907.13349

【3】 Landmark Detection in Low Resolution Faces with Semi-Supervised Learning
基于半监督学习的低分辨率人脸地标检测
作者: Amit Kumar, Rama Chellappa
链接:https://arxiv.org/abs/1907.13255

[分割/语义相关]:

【1】 Expectation-Maximization Attention Networks for Semantic Segmentation
面向语义分割的期望最大化注意网络
作者: Xia Li, Hong Liu
备注:In Proceedings of International Conference in Computer Vision (ICCV), 2019. Oral
链接:https://arxiv.org/abs/1907.13426

【2】 Incremental Learning Techniques for Semantic Segmentation
用于语义切分的增量式学习技术
作者: Umberto Michieli, Pietro Zanuttigh
链接:https://arxiv.org/abs/1907.13372

【3】 The Best of Both Modes: Separately Leveraging RGB and Depth for Unseen Object Instance Segmentation
两种模式的最佳:分别利用RGB和Depth进行未见对象实例分割
作者: Christopher Xie, Dieter Fox
链接:https://arxiv.org/abs/1907.13236

【4】 Unsupervised Domain Adaptation via Disentangled Representations: Application to Cross-Modality Liver Segmentation
通过解缠表示的无监督域适应:在跨模态肝脏分割中的应用
作者: Junlin Yang, James S. Duncan
链接:https://arxiv.org/abs/1907.13590

【5】 Impact of Adversarial Examples on Deep Learning Models for Biomedical Image Segmentation
对抗性例子对生物医学图像分割深度学习模型的影响
作者: Utku Ozbulak, Wesley De Neve
备注:Accepted for the 22nd International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI-19)
链接:https://arxiv.org/abs/1907.13124

[GAN/对抗式/生成式相关]:

【1】 Dressing 3D Humans using a Conditional Mesh-VAE-GAN
使用条件网格-VAE-GaN对3D人体进行修整
作者: Qianli Ma, Michael J. Black
链接:https://arxiv.org/abs/1907.13615

【2】 Adversarial Test on Learnable Image Encryption
可学习图像加密的对抗性测试
作者: MaungMaung AprilPyone, Hitoshi Kiya
备注:To be appeared in 2019 IEEE 8th Global Conference on Consumer Electronics (GCCE 2019)
链接:https://arxiv.org/abs/1907.13342

[图像/视频检索]:

【1】 Use What You Have: Video Retrieval Using Representations From Collaborative Experts
使用您所拥有的:使用协作专家的表示进行视频检索
作者: Yang Liu, Andrew Zisserman
备注:BMVC 2019
链接:https://arxiv.org/abs/1907.13487

[行为/时空/光流/姿态/运动]:

【1】 Auto-labelling of Markers in Optical Motion Capture by Permutation Learning
基于排列学习的光学运动捕获中标记的自动标注
作者: Saeed Ghorbani, Nikolaus F. Troje
链接:https://arxiv.org/abs/1907.13580

【2】 Probabilistic Motion Modeling from Medical Image Sequences: Application to Cardiac Cine-MRI
医学图像序列的概率运动建模:在心脏电影MRI中的应用
作者: Julian Krebs, Hervé Delingette
链接:https://arxiv.org/abs/1907.13524

【3】 Deep Non-Rigid Structure from Motion
来自运动的深层非刚体结构
作者: Chen Kong, Simon Lucey
链接:https://arxiv.org/abs/1907.13123

[半/弱/无监督相关]:

【1】 Self-training with progressive augmentation for unsupervised cross-domain person re-identification
具有渐进式增强的自训练用于无监督的跨域人员重新识别
作者: Xinyu Zhang, Mingyu You
备注:Accepted to Proc. Int. Conf. Computer Vision, 2019. Code is available at: this https URL
链接:https://arxiv.org/abs/1907.13315

[跟踪相关]:

【1】 Online Multi-Object Tracking Framework with the GMPHD Filter and Occlusion Group Management
具有GMPHD滤波器和遮挡组管理的在线多目标跟踪框架
作者: Young-min Song, Moongu Jeon
链接:https://arxiv.org/abs/1907.13347

【2】 Joint Group Feature Selection and Discriminative Filter Learning for Robust Visual Object Tracking
用于鲁棒视觉目标跟踪的联合组特征选择和判别滤波器学习
作者: Tianyang Xu, Josef Kittler
链接:https://arxiv.org/abs/1907.13242

[其他视频相关]:

【1】 Video Stitching for Linear Camera Arrays
线性摄像机阵列的视频拼接
作者: Wei-Sheng Lai, Jan Kautz
备注:This work is accepted in BMVC 2019. Project website: this http URL
链接:https://arxiv.org/abs/1907.13622

【2】 Multi-Agent Reinforcement Learning Based Frame Sampling for Effective Untrimmed Video Recognition
基于多Agent强化学习的帧采样非裁剪视频识别
作者: Wenhao Wu, Shilei Wen
备注:Accepted by ICCV 2019 (oral)
链接:https://arxiv.org/abs/1907.13369

[其他]:

【1】 On the difficulty of learning and predicting the long-term dynamics of bouncing objects
关于学习和预测弹跳物体的长期动力学的困难
作者: Alberto Cenzato, Marco Zorzi
链接:https://arxiv.org/abs/1907.13494

【2】 Rapid Light Field Depth Estimation with Semi-Global Matching
基于半全局匹配的快速光场深度估计
作者: Yuriy Anisimov, Didier Stricker
备注:IEEE 15th International Conference on Intelligent Computer Communication and Processing, Cluj-Napoca, September 5-7, 2019
链接:https://arxiv.org/abs/1907.13449

【3】 iCartoonFace: A Benchmark of Cartoon Person Recognition
iCartoonFace:卡通人物识别的基准
作者: Shichao Li, Bo Peng
链接:https://arxiv.org/abs/1907.13394

【4】 Learned Collaborative Stereo Refinement
学习的协作立体精化
作者: Patrick Knöbelreiter, Thomas Pock
备注:@German Conference on Pattern Recognition 2019
链接:https://arxiv.org/abs/1907.13391

【5】 Towards Digital Retina in Smart Cities: A Model Generation, Utilization and Communication Paradigm
走向智慧城市的数字视网膜:一种模式的产生、利用和传播范式
作者: Yihang Lou, Wen Gao
链接:https://arxiv.org/abs/1907.13368

【6】 Capsule Networks Need an Improved Routing Algorithm
胶囊网络需要一种改进的路由算法
作者: Inyoung Paik, Injung Kim
链接:https://arxiv.org/abs/1907.13327

【7】 Overcoming Catastrophic Forgetting by Neuron-level Plasticity Control
神经元可塑性控制克服灾难性遗忘
作者: Inyoung Paik, Injung Kim
链接:https://arxiv.org/abs/1907.13322

【8】 EMPNet: Neural Localisation and Mapping using Embedded Memory Points
EMPNet:使用嵌入式存储点的神经定位和映射
作者: Gil Avraham, Tom Drummond
备注:Accepted at ICCV 2019
链接:https://arxiv.org/abs/1907.13268

【9】 Degeneracy in Self-Calibration Revisited and a Deep Learning Solution for Uncalibrated SLAM
再论自标定中的简并性及未标定SLAM的深度学习解决方案
作者: Bingbing Zhuang, Manmohan Chandraker
备注:To appear at IROS 2019
链接:https://arxiv.org/abs/1907.13185

【10】 An Elastic Energy Minimization Framework for Mean Surface Calculation
一种用于平均表面计算的弹性能量最小化框架
作者: Jozsef Molnar, Peter Horvath
链接:https://arxiv.org/abs/1907.13557

【11】 Uncertainty Quantification in Deep Learning for Safer Neuroimage Enhancement
更安全的神经图像增强的深度学习不确定性量化
作者: Ryutaro Tanno, Daniel C. Alexander
链接:https://arxiv.org/abs/1907.13418

【12】 I-Keyboard: Fully Imaginary Keyboard on Touch Devices Empowered by Deep Neural Decoder
i-Keyboard:通过深度神经解码器实现的触控设备上的全虚拟键盘
作者: Ue-Hwan Kim, Jong-Hwan Kim
链接:https://arxiv.org/abs/1907.13285

【13】 Robust Autocalibrated Structured Low-Rank EPI Ghost Correction
健壮的自动校准结构化低等级EPI Ghost校正
作者: Rodrigo A. Lobos, Justin P. Haldar
链接:https://arxiv.org/abs/1907.13261

翻译:腾讯翻译君

上一篇下一篇

猜你喜欢

热点阅读