arXiv daily

计算机视觉每日论文速递[08.16]

2019-08-16  本文已影响16人  arXiv每日论文速递

同步公众号(arXiv每日论文速递),回复'search 关键词'查询相关最新论文。(* ̄rǒ ̄)

cs.CV 方向,今日共计29篇

[检测分类相关]:

【1】 IoU-balanced Loss Functions for Single-stage Object Detection
用于单级目标检测的IOU平衡损失函数
作者: Shengkai Wu, Xiaoping Li
链接:https://arxiv.org/abs/1908.05641

【2】 Deep learning for Plankton and Coral Classification
浮游生物和珊瑚分类的深度学习
作者: Alessandra Lumini, Gianluca Maguolo
链接:https://arxiv.org/abs/1908.05489

【3】 Distinction Maximization Loss: Fast, Scalable, Turnkey, and Native Neural Networks Out-of-Distribution Detection simply by Replacing the SoftMax Loss
差异化最大化损耗:快速、可扩展、交钥匙和本机神经网络分布外检测,只需更换SoftMax损耗即可
作者: David Macêdo
链接:https://arxiv.org/abs/1908.05569

【4】 Automated Rib Fracture Detection of Postmortem Computed Tomography Images Using Machine Learning Techniques
基于机器学习技术的身体CT图像肋骨骨折自动检测
作者: Samuel Gunz, Akos Dobay
链接:https://arxiv.org/abs/1908.05467

【5】 Multimodal Volume-Aware Detection and Segmentation for Brain Metastases Radiosurgery
脑转移瘤放射外科的多模态体积感知检测与分割
作者: Szu-Yeu Hu, Jen-Tang Lu
备注:Accepted to 2019 MICCAI AIRT
链接:https://arxiv.org/abs/1908.05418

[分割/语义相关]:

【1】 PS^2-Net: A Locally and Globally Aware Network for Point-Based Semantic Segmentation
PS^2-NET:一个局部和全局感知的基于点的语义切分网络
作者: Na Zhao, Gim Hee Lee
链接:https://arxiv.org/abs/1908.05425

【2】 Conv-MCD: A Plug-and-Play Multi-task Module for Medical Image Segmentation
Conv-MCD:一种即插即用的医学图像分割多任务模块
作者: Balamurali Murugesan, Mohanasankar Sivaprakasam
备注:Accepted in MLMI 2019
链接:https://arxiv.org/abs/1908.05311

【3】 A deep learning model for segmentation of geographic atrophy to study its long-term natural history
一种用于地理萎缩分割的深度学习模型,用于研究其长期自然历史
作者: Bart Liefers, Clara I. Sánchez
链接:https://arxiv.org/abs/1908.05621

【4】 SHREWD: Semantic Hierarchy-based Relational Embeddings for Weakly-supervised Deep Hashing
SHREWD:弱监督深度散列的基于语义层次的关系嵌入
作者: Heikki Arponen, Tom E Bishop
链接:https://arxiv.org/abs/1908.05602

【5】 Bayesian Generative Models for Knowledge Transfer in MRI Semantic Segmentation Problems
MRI语义分割问题中知识转移的贝叶斯生成模型
作者: Anna Kuzina, Evgeny Burnaev
链接:https://arxiv.org/abs/1908.05480

【6】 Graph Convolutional Networks for Coronary Artery Segmentation in Cardiac CT Angiography
心脏CT血管造影中冠状动脉分割的图形卷积网络
作者: Jelmer M. Wolterink, Ivana Išgum
备注:MICCAI 2019 Workshop on Graph Learning in Medical Image (GLMI)
链接:https://arxiv.org/abs/1908.05343

[GAN/对抗式/生成式相关]:

【1】 Dual Adversarial Inference for Text-to-Image Synthesis
用于文本到图像合成的对偶推理
作者: Qicheng Lao, Thomas Fevens
备注:Accepted to ICCV 2019
链接:https://arxiv.org/abs/1908.05324

[行为/时空/光流/姿态/运动]:

【1】 FastPose: Towards Real-time Pose Estimation and Tracking via Scale-normalized Multi-task Networks
FastPose:基于尺度归一化多任务网络的实时姿态估计与跟踪
作者: Jiabin Zhang, Guan Huang
链接:https://arxiv.org/abs/1908.05593

【2】 Learning Trajectory Dependencies for Human Motion Prediction
人体运动预测的学习轨迹依赖关系
作者: Wei Mao, Hongdong Li
备注:It will appear in ICCV2019
链接:https://arxiv.org/abs/1908.05436

【3】 3D Human Pose Estimation under limited supervision using Metric Learning
有限监督下基于度量学习的三维人体姿态估计
作者: Rahul Mitra, Arjun Jain
链接:https://arxiv.org/abs/1908.05293

【4】 Multimodal Emotion Recognition Using Deep Canonical Correlation Analysis
基于深度典型相关分析的多模态情感识别
作者: Wei Liu, Bao-Liang Lu
链接:https://arxiv.org/abs/1908.05349

[半/弱/无监督相关]:

【1】 Unpaired Cross-lingual Image Caption Generation with Self-Supervised Rewards
基于自监督奖励的非配对跨语言图片字幕生成
作者: Yuqing Song, Qin Jin
备注:Accepted by ACMMM 2019
链接:https://arxiv.org/abs/1908.05407

[裁剪/量化/加速相关]:
【1】 Accelerated CNN Training Through Gradient Approximation
通过梯度逼近加速CNN训练
作者: Ziheng Wang, Sree Harsha Nelaturu
备注:An abridged version was presented at EMC^2 : Workshop On Energy Efficient Machine Learning And Cognitive Computing For Embedded Applications at ISCA 2019
链接:https://arxiv.org/abs/1908.05460

[数据集dataset]:
【1】 Recognition of Ischaemia and Infection in Diabetic Foot Ulcers: Dataset and Techniques
糖尿病足溃疡缺血和感染的识别:数据集和技术
作者: Manu Goyal, Moi Hoon Yap
链接:https://arxiv.org/abs/1908.05317

[超分辨率]:
【1】 Deep Slice Interpolation via Marginal Super-Resolution, Fusion and Refinement
基于边缘超分辨、融合和精化的深层切片插值
作者: Cheng Peng, S. Kevin Zhou
链接:https://arxiv.org/abs/1908.05599

[深度depth相关]:
【1】 To complete or to estimate, that is the question: A Multi-Task Approach to Depth Completion and Monocular Depth Estimation
完成还是估计,这就是问题:深度完成和单目深度估计的多任务方法
作者: Amir Atapour-Abarghouei, Toby P. Breckon
备注:International Conference on 3D Vision (3DV) 2019
链接:https://arxiv.org/abs/1908.05540

[3D/3D重建等相关]:
【1】 R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object
R3Det:用于旋转对象的具有特征精化功能的精化单级检测器
作者: Xue Yang, Ang Li
链接:https://arxiv.org/abs/1908.05612

[其他]:
【1】 Beyond Cartesian Representations for Local Descriptors
局部描述符的超越笛卡尔表示
作者: Patrick Ebel, Eduard Trulls
链接:https://arxiv.org/abs/1908.05547

【2】 A Single-Shot Arbitrarily-Shaped Text Detector based on Context Attended Multi-Task Learning
基于上下文参与多任务学习的单镜头任意形状文本检测器
作者: Pengfei Wang, Guangming Shi
备注:9 pages, 6 figures, 7 tables, To appear in ACM Multimedia 2019
链接:https://arxiv.org/abs/1908.05498

【3】 Improved Mix-up with KL-Entropy for Learning From Noisy Labels
改进的KL-熵混合学习噪声标签
作者: Qian Zhang, Qiu Chen
链接:https://arxiv.org/abs/1908.05488

【4】 SFSegNet: Parse Freehand Sketches using Deep Fully Convolutional Networks
SFSegNet:使用深度完全卷积网络解析徒手草图
作者: Junkun Jiang, Fei Wang
备注:Accepted for the 2019 International Joint Conference on Neural Networks (IJCNN-19)
链接:https://arxiv.org/abs/1908.05389

【5】 A Multimodal Vision Sensor for Autonomous Driving
一种用于自主驾驶的多模态视觉传感器
作者: Dongming Sun, Kailun Yang
链接:https://arxiv.org/abs/1908.05649

【6】 Towards multi-sequence MR image recovery from undersampled k-space data
从欠采样k空间数据中恢复多序列MR图像
作者: Cheng Peng, S. Kevin Zhou
链接:https://arxiv.org/abs/1908.05615

【7】 Robust parametric modeling of Alzheimer's disease progression
阿尔茨海默病进展的稳健参数建模
作者: Mostafa Mehdipour Ghazi, Lauge Sørensen
链接:https://arxiv.org/abs/1908.05338

翻译:腾讯翻译君

上一篇 下一篇

猜你喜欢

热点阅读