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52篇
[检测分类相关]:
【1】 Matrix Nets: A New Deep Architecture for Object Detection
矩阵网:一种新的深层目标检测体系结构
作者: Abdulah Rashwan, Pascal Poupart
链接:https://arxiv.org/abs/1908.04646
【2】 Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data
重访点云分类:一种新的基准数据集和真实世界数据的分类模型
作者: Mikaela Angelina Uy, Sai-Kit Yeung
备注:ICCV 2019 Oral
链接:https://arxiv.org/abs/1908.04616
【3】 Three Branches: Detecting Actions With Richer Features
三个分支:检测具有更丰富特征的动作
作者: Jin Xia, Cewu Lu
链接:https://arxiv.org/abs/1908.04519
【4】 Fine-Tuning Models Comparisons on Garbage Classification for Recyclability
垃圾分类可回收性的微调模型比较
作者: Umut Ozkaya, Levent Seyfi
备注:published in ISAS 2018-Winter
链接:https://arxiv.org/abs/1908.04393
【5】 Deep Learning for Detecting Building Defects Using Convolutional Neural Networks
利用卷积神经网络进行深度学习检测建筑物缺陷
作者: Husein Perez, Amir Mosavi
链接:https://arxiv.org/abs/1908.04392
【6】 Difficulty Classification of Mountainbike Downhill Trails utilizing Deep Neural Networks
基于深度神经网络的山地自行车下坡路径难度分类
作者: Stefan Langer, Claudia Linnhoff-Popien
链接:https://arxiv.org/abs/1908.04390
【7】 Detecting semantic anomalies
检测语义异常
作者: Faruk Ahmed, Aaron Courville
备注:Submission to NeurIPS 2019
链接:https://arxiv.org/abs/1908.04388
【8】 Detection of the Group of Traffic Signs with Central Slice Theorem
利用中心切片定理检测交通标志群
作者: Koba Natroshvili
链接:https://arxiv.org/abs/1908.04386
【9】 OD-GCN object detection by knowledge graph with GCN
基于知识图和GCN的OD-GCN目标检测
作者: Zheng Liu, Feng Wei
链接:https://arxiv.org/abs/1908.04385
【10】 MULAN: Multitask Universal Lesion Analysis Network for Joint Lesion Detection, Tagging, and Segmentation
Mulan:用于联合病变检测、标记和分割的多任务通用病变分析网络
作者: Ke Yan, Ronald M. Summers
备注:MICCAI 2019, including appendix. code: this https URL
链接:https://arxiv.org/abs/1908.04373
【11】 Multi-timescale Trajectory Prediction for Abnormal Human Activity Detection
用于异常人体活动检测的多时间尺度轨迹预测
作者: Royston Rodrigues, Subhasis Chaudhuri
链接:https://arxiv.org/abs/1908.04321
【12】 Graph Embedding Using Infomax for ASD Classification and Brain Functional Difference Detection
利用Infomax嵌入图形进行ASD分类和脑功能差异检测
作者: Xiaoxiao Li, James Duncana
链接:https://arxiv.org/abs/1908.04769
【13】 Incorporating Task-Specific Structural Knowledge into CNNs for Brain Midline Shift Detection
将任务特定的结构知识融入CNN用于大脑中线移位检测
作者: Maxim Pisov, Mikhail Belyaev
链接:https://arxiv.org/abs/1908.04568
【14】 The Channel Attention based Context Encoder Network for Inner Limiting Membrane Detection
基于通道注意的内限膜检测上下文编码器网络
作者: Hao Qiu, Jun Cheng
链接:https://arxiv.org/abs/1908.04413
[分割/语义相关]:
【1】 Is This The Right Place? Geometric-Semantic Pose Verification for Indoor Visual Localization
是这个地方吗?面向室内视觉定位的几何语义姿态验证
作者: Hajime Taira, Akihiko Torii
链接:https://arxiv.org/abs/1908.04598
【2】 Boosted GAN with Semantically Interpretable Information for Image Inpainting
具有语义可解释信息的增强GaN用于图像修复
作者: Ang Li, Ramamohanarao Kotagiri
链接:https://arxiv.org/abs/1908.04503
【3】 Frame-to-Frame Aggregation of Active Regions in Web Videos for Weakly Supervised Semantic Segmentation
用于弱监督语义分割的Web视频中活动区域的帧到帧聚合
作者: Jungbeom Lee, Sungroh Yoon
备注:ICCV 2019
链接:https://arxiv.org/abs/1908.04501
【4】 Few Labeled Atlases are Necessary for Deep-Learning-Based Segmentation
基于深度学习的分割需要少数标记的Atlases
作者: Hyeon Woo Lee, Adrian V. Dalca
链接:https://arxiv.org/abs/1908.04466
【5】 Generalizing Deep Whole Brain Segmentation for Pediatric and Post-Contrast MRI with Augmented Transfer Learning
基于增强转移学习的儿科及增强MRI增强扫描全脑深度分割
作者: Camilo Bermudez, Bennett A. Landman
链接:https://arxiv.org/abs/1908.04702
【6】 Collaborative Multi-agent Learning for MR Knee Articular Cartilage Segmentation
多智能体协同学习在MR膝关节软骨分割中的应用
作者: Chaowei Tan, Dimitris N. Metaxas
链接:https://arxiv.org/abs/1908.04469
[GAN/对抗式/生成式相关]:
【1】 Enforcing Perceptual Consistency on Generative Adversarial Networks by Using the Normalised Laplacian Pyramid Distance
利用归一化拉普拉斯金字塔距离增强生成对抗性网络的知觉一致性
作者: Alexander Hepburn, Raul Santos-Rodriguez
链接:https://arxiv.org/abs/1908.04347
【2】 SkrGAN: Sketching-rendering Unconditional Generative Adversarial Networks for Medical Image Synthesis
SkrGAN:用于医学图像合成的素描-渲染无条件生成对抗网络
作者: Tianyang Zhang, Jiang Liu
备注:Accepted to MICCAI 2019
链接:https://arxiv.org/abs/1908.04346
【3】 Super-resolution of Omnidirectional Images Using Adversarial Learning
利用对抗性学习实现全方位图像的超分辨率
作者: Cagri Ozcinar, Aljosa Smolic
链接:https://arxiv.org/abs/1908.04297
【4】 Adversarial Neural Pruning
对抗性神经修剪
作者: Divyam Madaan, Sung Ju Hwang
链接:https://arxiv.org/abs/1908.04355
[行为/时空/光流/姿态/运动]:
【1】 Action Recognition in Untrimmed Videos with Composite Self-Attention Two-Stream Framework
基于复合自注意双流框架的未裁剪视频动作识别
作者: Dong Cao, HaiBo Chen
备注:Submitted to ACPR 2019
链接:https://arxiv.org/abs/1908.04353
[半/弱/无监督相关]:
【1】 An Unsupervised, Iterative N-Dimensional Point-Set Registration Algorithm
一种无监督的迭代N维点集配准算法
作者: A. Pasha Hosseinbor, A. Ushveridze
备注:arXiv admin note: text overlap with arXiv:1702.01870
链接:https://arxiv.org/abs/1908.04384
【2】 Repetitive Reprediction Deep Decipher for Semi-Supervised Learning
半监督学习的重复预测深度译码算法
作者: Guo-Hua Wang, Jianxin Wu
链接:https://arxiv.org/abs/1908.04345
[跟踪相关]:
【1】 Learning Target-oriented Dual Attention for Robust RGB-T Tracking
针对鲁棒RGB-T跟踪的学习目标定向双重注意
作者: Rui Yang, Jin Tang
备注:Accepted by IEEE ICIP 2019
链接:https://arxiv.org/abs/1908.04441
【2】 A fast multi-object tracking system using an object detector ensemble
一种使用目标检测器集成的快速多目标跟踪系统
作者: Richard Cobos, Andres G. Abad
备注:5 pages, 4 figures, 1 table, published in 2019 IEEE Colombian Conference on Applications in Computational Intelligence (ColCACI)
链接:https://arxiv.org/abs/1908.04349
[裁剪/量化/加速相关]:
【1】 Effective Training of Convolutional Neural Networks with Low-bitwidth Weights and Activations
具有低位宽权重和激活的卷积神经网络的有效训练
作者: Bohan Zhuang, Chunhua Shen
备注:12 pages. Extended version of B. Zhuang, C. Shen, M. Tan, L. Liu, and I. Reid, 'Towards effective low-bitwidth convolutional neural networks,' in Proc. IEEE Conf. Comp. Vis. Patt. Recogn., 2018. arXiv admin note: text overlap with arXiv:1711.00205
链接:https://arxiv.org/abs/1908.04680
【2】 Apache Spark Accelerated Deep Learning Inference for Large Scale Satellite Image Analytics
Apache Spark加速深度学习推理在大规模卫星图像分析中的应用
作者: Dalton Lunga, Robert Stewart
链接:https://arxiv.org/abs/1908.04383
【3】 Convolutional Analysis Operator Learning: Acceleration and Convergence
卷积分析算子学习:加速与收敛
作者: Il Yong Chun, Jeffrey A. Fessler
链接:https://arxiv.org/abs/1802.05584
[点云]:
【1】 Interpolated Convolutional Networks for 3D Point Cloud Understanding
用于三维点云理解的插值卷积网络
作者: Jiageng Mao, Hongsheng Li
备注:ICCV2019 oral. Code will be released soon
链接:https://arxiv.org/abs/1908.04512
[人脸相关]:
【1】 Face Recognition in Unconstrained Conditions: A Systematic Review
无约束条件下的人脸识别系统综述
作者: Andrew Jason Shepley
链接:https://arxiv.org/abs/1908.04404
[3D/3D重建等相关]:
【1】 Predicting 3D Human Dynamics from Video
从视频中预测三维人体动力学
作者: Jason Y. Zhang, Jitendra Malik
备注:To Appear in ICCV 2019
链接:https://arxiv.org/abs/1908.04781
【2】 Learning elementary structures for 3D shape generation and matching
学习三维形状生成和匹配的基本结构
作者: Theo Deprelle, Mathieu Aubry
链接:https://arxiv.org/abs/1908.04725
[其他]:
【1】 Construction of efficient detectors for character information recognition
用于字符信息识别的高效检测器的构造
作者: A.A. Telnykh, Yu.R. Samorodova
链接:https://arxiv.org/abs/1908.04634
【2】 Point-Based Multi-View Stereo Network
基于点的多视点立体网络
作者: Rui Chen, Hao Su
备注:Accepted as ICCV 2019 oral presentation
链接:https://arxiv.org/abs/1908.04422
【3】 Challenge of Spatial Cognition for Deep Learning
空间认知对深度学习的挑战
作者: Xiaolin Wu, Jun Du
链接:https://arxiv.org/abs/1908.04396
【4】 Local Supports Global: Deep Camera Relocalization with Sequence Enhancement
本地支持全局:深度摄像机重新定位,具有序列增强功能
作者: Fei Xue, Hongbin Zha
备注:Accept to ICCV 2019
链接:https://arxiv.org/abs/1908.04391
【5】 NeuroMask: Explaining Predictions of Deep Neural Networks through Mask Learning
神经掩模:通过掩模学习解释深层神经网络的预测
作者: Moustafa Alzantot, Mani Srivastava
链接:https://arxiv.org/abs/1908.04389
【6】 Mass Estimation from Images using Deep Neural Network and Sparse Ground Truth
基于深层神经网络和稀疏地面真值的图像质量估计
作者: Muhammad K A Hamdan, John Just
备注:9 pages, 19 figures, pre-print NIPS2019
链接:https://arxiv.org/abs/1908.04387
【7】 Explaining Convolutional Neural Networks using Softmax Gradient Layer-wise Relevance Propagation
用Softmax梯度分层相关传播解释卷积神经网络
作者: Brian Kenji Iwana, Seiichi Uchida
链接:https://arxiv.org/abs/1908.04351
【8】 What's in the box? Explaining the black-box model through an evaluation of its interpretable features
这盒子里是什么?通过评估黑盒模型的可解释特性来解释它
作者: Francesco Ventura, Tania Cerquitelli
链接:https://arxiv.org/abs/1908.04348
【9】 AI Décor
艾德科尔
作者: Sharmin Pathan
链接:https://arxiv.org/abs/1908.04344
【10】 Why Does a Visual Question Have Different Answers?
为什么视觉问题有不同的答案?
作者: Nilavra Bhattacharya, Danna Gurari
链接:https://arxiv.org/abs/1908.04342
【11】 Multi-modality Latent Interaction Network for Visual Question Answering
面向视觉问答的多模态潜在交互网络
作者: Peng Gao, Hongsheng Li
链接:https://arxiv.org/abs/1908.04289
【12】 Deep Learning-Based Quantification of Pulmonary Hemosiderophages in Cytology Slides
基于深度学习的细胞学切片中肺血铁噬菌体的定量
作者: Christian Marzahl, Andreas Maier
链接:https://arxiv.org/abs/1908.04767
【13】 Channel Decomposition on Generative Networks
生成网络上的信道分解
作者: Shih-Chieh Su
链接:https://arxiv.org/abs/1908.04694
【14】 SDM-NET: Deep Generative Network for Structured Deformable Mesh
SDM-NET:结构化变形网格的深度生成网络
作者: Lin Gao, Hao Zhang
备注:Conditionally Accepted to Siggraph Asia 2019
链接:https://arxiv.org/abs/1908.04520
【15】 Feature Partitioning for Efficient Multi-Task Architectures
高效多任务体系结构的特征划分
作者: Alejandro Newell, Jia Deng
链接:https://arxiv.org/abs/1908.04339
【16】 Deep Dexterous Grasping of Novel Objects from a Single View
从单一视角对新奇物体的深度灵巧把握
作者: Umit Rusen Aktas, Jeremy L. Wyatt
链接:https://arxiv.org/abs/1908.04293
翻译:腾讯翻译君
网友评论