当前位置:   article > 正文

计算机视觉/图像处理每日论文速递[02.26]_polygen 论文an autoregressive

polygen 论文an autoregressive

同步公众号(arXiv每日学术速递),欢迎关注,感谢支持哦~

[检测分类相关]:

【1】 PointAugment: an Auto-Augmentation Framework for Point Cloud Classification
PointAugment:一种自动增强的点云分类框架
作者: Ruihui Li, Chi-Wing Fu
备注:Accepted by CVPR 2020; code is this https URL
链接:https://arxiv.org/abs/2002.10876

【2】 Cross-layer Feature Pyramid Network for Salient Object Detection
用于凸起目标检测的跨层特征金字塔网络
作者: Zun Li, Jiashi Feng
链接:https://arxiv.org/abs/2002.10864

【3】 Fast Loop Closure Detection via Binary Content
基于二进制内容的快速环路闭合检测
作者: Han Wang, Lihua Xie
备注:IEEE International Conference on Control and Automation (ICCA) 2019
链接:https://arxiv.org/abs/2002.10622

【4】 Real-time Fusion Network for RGB-D Semantic Segmentation Incorporating Unexpected Obstacle Detection for Road-driving Images
实时融合网络的RGB-D语义分割结合道路驾驶图像的意外障碍物检测
作者: Lei Sun, Kaiwei Wang
备注:7 figures, 3 tables, submitted to RA-L with IROS2020
链接:https://arxiv.org/abs/2002.10570

【5】 Relevant-features based Auxiliary Cells for Energy Efficient Detection of Natural Errors
基于相关特征的自然误差能量高效检测辅助单元
作者: Sai Aparna Aketi, Kaushik Roy
链接:https://arxiv.org/abs/2002.11052

【6】 I Am Going MAD: Maximum Discrepancy Competition for Comparing Classifiers Adaptively
我要疯了:自适应比较分类器的最大差异竞争
作者: Haotao Wang, Kede Ma
备注:Accepted to ICLR 2020
链接:https://arxiv.org/abs/2002.10648

[分割/语义相关]:

【1】 MagnifierNet: Towards Semantic Regularization and Fusion for Person Re-identification
MagnifierNet:面向语义规则化和人名再识别的融合
作者: Yushi Lan, Hongsheng Zhou
链接:https://arxiv.org/abs/2002.10979

【2】 Online Semantic Exploration of Indoor Maps
室内地图的在线语义探索
作者: Ziyuan Liu, Georg von Wichert
备注:arXiv admin note: substantial text overlap with arXiv:2002.08348
链接:https://arxiv.org/abs/2002.10939

【3】 Applying Rule-Based Context Knowledge to Build Abstract Semantic Maps of Indoor Environments
应用基于规则的上下文知识构建室内环境抽象语义图
作者: Ziyuan Liu, Georg von Wichert
备注:arXiv admin note: text overlap with arXiv:2002.08402
链接:https://arxiv.org/abs/2002.10938

【4】 Fully Convolutional Neural Networks for Raw Eye Tracking Data Segmentation, Generation, and Reconstruction
用于原始眼球跟踪数据分割、生成和重建的全卷积神经网络
作者: Wolfgang Fuhl
链接:https://arxiv.org/abs/2002.10905

【5】 3D-MiniNet: Learning a 2D Representation from Point Clouds for Fast and Efficient 3D LIDAR Semantic Segmentation
3D-MiniNet:从点云中学习2D表示,用于快速高效的3D LIDAR语义分割
作者: Iñigo Alonso, Ana C. Murillo
链接:https://arxiv.org/abs/2002.10893

【6】 Fully-automated Body Composition Analysis in Routine CT Imaging Using 3D Semantic Segmentation Convolutional Neural Networks
三维语义分割卷积神经网络在常规CT成像中的全自动身体成分分析
作者: Sven Koitka, Felix Nensa
链接:https://arxiv.org/abs/2002.10776

【7】 Towards Better Surgical Instrument Segmentation in Endoscopic Vision: Multi-Angle Feature Aggregation and Contour Supervision
内窥镜视觉中更好的手术器械分割:多角度特征聚合和轮廓监控
作者: Fangbo Qin, Blake Hannaford
链接:https://arxiv.org/abs/2002.10675

【8】 Technical report: Kidney tumor segmentation using a 2D U-Net followed by a statistical post-processing filter
技术报告:使用2D U-net和统计后处理过滤器对肾脏肿瘤进行分割
作者: Iwan Paolucci
备注:KiTS 2019 challenge
链接:https://arxiv.org/abs/2002.10727

[人脸相关]:

【1】 Copy and Paste GAN: Face Hallucination from Shaded Thumbnails
复制和粘贴GAN:来自着色缩略图的面部幻觉
作者: Yang Zhang, Xin Yu
链接:https://arxiv.org/abs/2002.10650

[GAN/对抗式/生成式相关]:

【1】 Freeze Discriminator: A Simple Baseline for Fine-tuning GANs
冻结判别器:微调GANS的简单基线
作者: Sangwoo Mo, Jinwoo Shin
链接:https://arxiv.org/abs/2002.10964

【2】 On Pruning Adversarially Robust Neural Networks
关于剪枝敌方鲁棒神经网络
作者: Vikash Sehwag, Suman Jana
备注:19 pages, 14 figures, 8 tables
链接:https://arxiv.org/abs/2002.10509

【3】 Gödel's Sentence Is An Adversarial Example But Unsolvable
哥德尔的判决是一个对抗性的例子,但无法解决
作者: Xiaodong Qi, Lansheng Han
链接:https://arxiv.org/abs/2002.10703

【4】 Co-VeGAN: Complex-Valued Generative Adversarial Network for Compressive Sensing MR Image Reconstruction
co-vegan:用于压缩传感MR图像重建的复值生成对抗网络
作者: Bhavya Vasudeva, Pyari Mohan Pradhan
链接:https://arxiv.org/abs/2002.10523

[行为/时空/光流/姿态/运动]:

【1】 Toward fast and accurate human pose estimation via soft-gated skip connections
通过软门控跳跃连接实现快速准确的人体姿势估计
作者: Adrian Bulat, Maja Pantic
备注:Accepted to FG 2020 (oral)
链接:https://arxiv.org/abs/2002.11098

【2】 ScopeFlow: Dynamic Scene Scoping for Optical Flow
ScopeFlow:光流的动态场景范围
作者: Aviram Bar-Haim, Lior Wolf
链接:https://arxiv.org/abs/2002.10770

【3】 MPM: Joint Representation of Motion and Position Map for Cell Tracking
MPM:用于细胞跟踪的运动和位置图的联合表示
作者: Junya Hayashida, Ryoma Bise
备注:8 pages, 11 figures, Accepted in CVPR 2020
链接:https://arxiv.org/abs/2002.10749

【4】 Globally Optimal Contrast Maximisation for Event-based Motion Estimation
基于事件的运动估计的全局最优对比度最大化
作者: Daqi Liu, Tat-Jun Chin
链接:https://arxiv.org/abs/2002.10686

[跟踪相关]:

【1】 AutoFoley: Artificial Synthesis of Synchronized Sound Tracks for Silent Videos with Deep Learning
AutoFoley:深度学习的无声视频同步声道的人工合成
作者: Sanchita Ghose, John J. Prevost
链接:https://arxiv.org/abs/2002.10981

[裁剪/量化/加速相关]:

【1】 Searching for Winograd-aware Quantized Networks
搜索Winograd感知的量化网络
作者: Javier Fernandez-Marques, Matthew Mattina
备注:Published as a conference paper at MLSys 2020
链接:https://arxiv.org/abs/2002.10711

[Re-id相关]:

【1】 Triplet Online Instance Matching Loss for Person Re-identification
用于人员重新识别的三元组在线实例匹配丢失
作者: Ye Li, Zhiguo Wang
链接:https://arxiv.org/abs/2002.10560

[超分辨率]:

【1】 DDet: Dual-path Dynamic Enhancement Network for Real-World Image Super-Resolution
dDet:用于真实图像超分辨率的双路径动态增强网络
作者: Yukai Shi, Liang Lin
链接:https://arxiv.org/abs/2002.11079

[3D/3D重建等相关]:

【1】 Fault Diagnosis in Microelectronics Attachment via Deep Learning Analysis of 3D Laser Scans
基于三维激光扫描深度学习分析的微电子附件故障诊断
作者: Nikolaos Dimitriou, Dimitrios Tzovaras
备注:10 pages, 12 figures. in IEEE Transactions on Industrial Electronics, 2019 (early access)
链接:https://arxiv.org/abs/2002.10974

【2】 PolyGen: An Autoregressive Generative Model of 3D Meshes
Polygen:一种三维网格的自回归生成模型
作者: Charlie Nash, Peter W. Battaglia
链接:https://arxiv.org/abs/2002.10880

[其他视频相关]:

【1】 Hierarchical Conditional Relation Networks for Video Question Answering
分层条件关系网络在视频问答中的应用
作者: Thao Minh Le, Truyen Tran
链接:https://arxiv.org/abs/2002.10698

【2】 A Comparative Evaluation of Temporal Pooling Methods for Blind Video Quality Assessment
用于盲目视频质量评估的时间池方法的比较评价
作者: Zhengzhong Tu, Alan C. Bovik
链接:https://arxiv.org/abs/2002.10651

[其他]:

【1】 Model Watermarking for Image Processing Networks
用于图像处理网络的模型水印
作者: Jie Zhang, Nenghai Yu
备注:AAAI 2020
链接:https://arxiv.org/abs/2002.11088

【2】 Ground Texture Based Localization Using Compact Binary Descriptors
使用紧凑二进制描述符的基于地面纹理的定位
作者: Jan Fabian Schmid, Rudolf Mester
备注:Accepted for 2020 IEEE International Conference on Robotics and Automation (ICRA)
链接:https://arxiv.org/abs/2002.11061

【3】 See, Attend and Brake: An Attention-based Saliency Map Prediction Model for End-to-End Driving
查看、出席和制动:用于端到端驾驶的基于注意的显著图预测模型
作者: Ekrem Aksoy, Mahmut Kasap
链接:https://arxiv.org/abs/2002.11020

【4】 A Deep Learning Framework for Simulation and Defect Prediction Applied in Microelectronics
一种用于微电子仿真和缺陷预测的深度学习框架
作者: Nikolaos Dimitriou, Dimitrios Tzovaras
备注:21 pages, 5 figures
链接:https://arxiv.org/abs/2002.10986

【5】 Circle Loss: A Unified Perspective of Pair Similarity Optimization
圆损失:配对相似性优化的统一视角
作者: Yifan Sun, Yichen Wei
链接:https://arxiv.org/abs/2002.10857

【6】 Optimal least-squares solution to the hand-eye calibration problem
手眼标定问题的最优最小二乘解
作者: Amit Dekel, Sergio Caccamo
链接:https://arxiv.org/abs/2002.10838

【7】 Deep Representation Learning on Long-tailed Data: A Learnable Embedding Augmentation Perspective
基于长尾数据的深度表征学习:可学习的嵌入增强视角
作者: Jialun Liu, Wenhui Li
链接:https://arxiv.org/abs/2002.10826

【8】 Exploring Learning Dynamics of DNNs via Layerwise Conditioning Analysis
基于层次化条件分析的DNNs学习动力学探索
作者: Lei Huang, Ling Shao
链接:https://arxiv.org/abs/2002.10801

【9】 FPConv: Learning Local Flattening for Point Convolution
FPConv:学习点卷积的局部展平
作者: Yiqun Lin, Xiaoguang Han
链接:https://arxiv.org/abs/2002.10701

【10】 Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training
通过预培训学习用于视觉和语言导航的通用Agent
作者: Weituo Hao, Jianfeng Gao
备注:To appear at CVPR 2020. The first two authors contributed equally to this manuscript. Code: this https URL
链接:https://arxiv.org/abs/2002.10638

【11】 Deep learning predicts total knee replacement from magnetic resonance images
深度学习从磁共振图像预测全膝关节置换
作者: Aniket A. Tolpadi, Sharmila Majumdar
链接:https://arxiv.org/abs/2002.10591

【12】 Revisiting Saliency Metrics: Farthest-Neighbor Area Under Curve
重访显著性度量:曲线下最远邻域
作者: Sen Jia, Neil D.B. Bruce
备注:Accepted to CVPR 2020
链接:https://arxiv.org/abs/2002.10540

【13】 Evaluating Registration Without Ground Truth
无地面事实的配准评估
作者: Carole J. Twining, Christopher J. Taylor
链接:https://arxiv.org/abs/2002.10534

【14】 On Feature Normalization and Data Augmentation
特征归一化与数据增强
作者: Boyi Li, Kilian Q. Weinberger
链接:https://arxiv.org/abs/2002.11102

【15】 Beyond Dropout: Feature Map Distortion to Regularize Deep Neural Networks
超越Dropout:特征图失真对深层神经网络的正则化
作者: Yehui Tang, Chang Xu
链接:https://arxiv.org/abs/2002.11022

【16】 Image Stylization: From Predefined to Personalized
图像风格化:从预定义到个性化
作者: Ignacio Garcia-Dorado, Peyman Milanfar
链接:https://arxiv.org/abs/2002.10945

【17】 Gesture recognition with 60GHz 802.11 waveforms
60 GHz 802.11波形的手势识别
作者: Eran Hof, Evyatar Hemo
链接:https://arxiv.org/abs/2002.10836

【18】 BERT Can See Out of the Box: On the Cross-modal Transferability of Text Representations
伯特可以看到开箱即用:论文本表征的跨模态可转移性
作者: Thomas Scialom, Patrick Gallinari
链接:https://arxiv.org/abs/2002.10832

【19】 (De)Randomized Smoothing for Certifiable Defense against Patch Attacks
(De)针对补丁攻击的可证明防御的随机平滑
作者: Alexander Levine, Soheil Feizi
链接:https://arxiv.org/abs/2002.10733

【20】 Multimodal Transformer with Pointer Network for the DSTC8 AVSD Challenge
带指针网络的多模式变压器用于DSTC8 AVSD挑战
作者: Hung Le, Nancy F. Chen
备注:Accepted at DSTC Workshop at AAAI 2020
链接:https://arxiv.org/abs/2002.10695

【21】 Coherent Gradients: An Approach to Understanding Generalization in Gradient Descent-based Optimization
相干梯度:基于梯度下降优化中理解泛化的一种方法
作者: Satrajit Chatterjee
备注:To appear in ICLR 2020
链接:https://arxiv.org/abs/2002.10657

【22】 Batch norm with entropic regularization turns deterministic autoencoders into generative models
具有熵正则化的批处理范数将确定性自动编码器转换为生成模型
作者: Amur Ghose, Pascal Poupart
链接:https://arxiv.org/abs/2002.10631

【23】 Progressive Learning and Disentanglement of Hierarchical Representations
递进学习与分层表征的解缠
作者: Zhiyuan Li, Linwei Wang
链接:https://arxiv.org/abs/2002.10549

机器翻译,仅供参考

声明:本文内容由网友自发贡献,不代表【wpsshop博客】立场,版权归原作者所有,本站不承担相应法律责任。如您发现有侵权的内容,请联系我们。转载请注明出处:https://www.wpsshop.cn/w/我家自动化/article/detail/214901?site
推荐阅读
相关标签
  

闽ICP备14008679号