关注上方“深度学习技术前沿”,选择“星标公众号”,
资源干货,第一时间送达!
[检测分类相关]:
【1】 Supervised and Unsupervised Detections for Multiple Object Tracking in Traffic Scenes: A Comparative Study
交通场景中多目标跟踪的有监督和无监督检测的比较研究
作者:Hui-Lee Ooi, Nicolas Saunier
备注:Accepted for ICIAR 2020
链接:https://arxiv.org/abs/2003.13644
【2】 Squeezed Deep 6DoF Object Detection Using Knowledge Distillation
利用知识精馏的压缩深6DoF目标检测
作者:Heitor Felix, Cleber Zanchettin
备注:This paper was accepted by IJCNN 2020 and will have few changes from the version that will be published
链接:https://arxiv.org/abs/2003.13586
【3】 SiTGRU: Single-Tunnelled Gated Recurrent Unit for Abnormality Detection
SiTGRU:用于异常检测的单隧道门控循环单元
作者:Habtamu Fanta, Lizhuang Ma
链接:https://arxiv.org/abs/2003.13528
【4】 A Comparison of Data Augmentation Techniques in Training Deep Neural Networks for Satellite Image Classification
用于卫星图像分类的深度神经网络训练中数据增强技术的比较
作者:Mohamed Abdelhack
链接:https://arxiv.org/abs/2003.13502
【5】 Computer Aided Detection for Pulmonary Embolism Challenge (CAD-PE)
肺栓塞挑战的计算机辅助检测(CAD-PE)
作者:Germán González, Maria J. Ledesma-Carbayo
链接:https://arxiv.org/abs/2003.13440
【6】 Learning Memory-guided Normality for Anomaly Detection
用于异常检测的学习记忆引导的正规性
作者:Hyunjong Park, Bumsub Ham
备注:Accepted to CVPR 2020
链接:https://arxiv.org/abs/2003.13228
【7】 Cross-Domain Document Object Detection: Benchmark Suite and Method
跨域文档对象检测:Benchmark Suite和Method
作者:Kai Li, Yun Fu
备注:To appear in CVPR 2020
链接:https://arxiv.org/abs/2003.13197
【8】 Detection of 3D Bounding Boxes of Vehicles Using Perspective Transformation for Accurate Speed Measurement
基于透视变换精确测速的车辆三维包围盒检测
作者:Viktor Kocur, Milan Ftáčnik
链接:https://arxiv.org/abs/2003.13137
【9】 Attentive CutMix: An Enhanced Data Augmentation Approach for Deep Learning Based Image Classification
Attentive CutMix:一种用于深度学习图像分类的增强数据增强方法
作者:Devesh Walawalkar, Marios Savvides
备注:Accepted as conference paper in ICASSP 2020
链接:https://arxiv.org/abs/2003.13048
【10】 Noise Modeling, Synthesis and Classification for Generic Object Anti-Spoofing
通用对象防欺骗的噪声建模、合成和分类
作者:Joel Stehouwer, Xiaoming Liu
备注:In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020
链接:https://arxiv.org/abs/2003.13043
【11】 Adaptive Object Detection with Dual Multi-Label Prediction
基于双多标签预测的自适应目标检测
作者:Zhen Zhao, Jieping Ye
链接:https://arxiv.org/abs/2003.12943
【12】 Refined Plane Segmentation for Cuboid-Shaped Objects by Leveraging Edge Detection
利用边缘检测的长方体物体精细化平面分割
作者:Alexander Naumann, Kai Furmans
链接:https://arxiv.org/abs/2003.12870
【13】 OCmst: One-class Novelty Detection using Convolutional Neural Network and Minimum Spanning Trees
OCmst:基于卷积神经网络和最小生成树的一类新颖性检测
作者:Riccardo La Grassa, Nicola Landro
链接:https://arxiv.org/abs/2003.13524
[分割/语义相关]:
【1】 Vox2Vox: 3D-GAN for Brain Tumour Segmentation
Vox2Vox:3D-GaN用于脑肿瘤分割
作者:Marco Domenico Cirillo, Anders Eklund
链接:https://arxiv.org/abs/2003.13653
【2】 Predicting Semantic Map Representations from Images using Pyramid Occupancy Networks
使用金字塔占有率网络从图像预测语义地图表示
作者:Thomas Roddick, Roberto Cipolla
链接:https://arxiv.org/abs/2003.13402
【3】 TapLab: A Fast Framework for Semantic Video Segmentation Tapping into Compressed-Domain Knowledge
TapLab:一种利用压缩域知识的快速语义视频分割框架
作者:Junyi Feng, Haibin Ling
链接:https://arxiv.org/abs/2003.13260
【4】 Memory Aggregation Networks for Efficient Interactive Video Object Segmentation
用于高效交互式视频对象分割的存储器聚合网络
作者:Jiaxu Miao, Yi Yang
备注:Accepted to CVPR 2020. 10 pages, 9 figures
链接:https://arxiv.org/abs/2003.13246
【5】 Learning a Weakly-Supervised Video Actor-Action Segmentation Model with a Wise Selection
具有明智选择的弱监督视频演员-动作分割模型的学习
作者:Jie Chen, Chenliang Xu
备注:11 pages, 8 figures, cvpr-2020 supplementary video: this https URL
链接:https://arxiv.org/abs/2003.13141
【6】 Defect segmentation: Mapping tunnel lining internal defects with ground penetrating radar data using a convolutional neural network
缺陷分割:使用卷积神经网络将隧道衬砌内部缺陷与探地雷达数据映射
作者:Senlin Yang, Qingmei Sui
链接:https://arxiv.org/abs/2003.13120
【7】 Multi-Path Region Mining For Weakly Supervised 3D Semantic Segmentation on Point Clouds
点云上弱监督三维语义分割的多路径区域挖掘
作者:Jiacheng Wei, Lihua Xie
备注:Accepted by CVPR2020
链接:https://arxiv.org/abs/2003.13035
[NAS相关]:
【1】 NPENAS: Neural Predictor Guided Evolution for Neural Architecture Search
NPENAS:神经结构搜索的神经预测器引导进化
作者:Chen Wei, Jimin Liang
链接:https://arxiv.org/abs/2003.12857
[人脸相关]:
【1】 Deep Face Super-Resolution with Iterative Collaboration between Attentive Recovery and Landmark Estimation
基于注意恢复和界标估计迭代协作的深脸超分辨率
作者:Cheng Ma, Jie Zhou
备注:Accepted to CVPR 2020
链接:https://arxiv.org/abs/2003.13063
【2】 Realistic Face Reenactment via Self-Supervised Disentangling of Identity and Pose
通过自我监督解开身份和姿势再现逼真的人脸
作者:Xianfang Zeng, Yong Liu
链接:https://arxiv.org/abs/2003.12957
【3】 One-Shot Domain Adaptation For Face Generation
一次区域自适应人脸生成算法
作者:Chao Yang, Ser-Nam Lim
备注:Accepted to CVPR 2020
链接:https://arxiv.org/abs/2003.12869
[GAN/对抗式/生成式相关]:
【1】 Improved Gradient based Adversarial Attacks for Quantized Networks
一种改进的基于梯度的量化网络对抗攻击
作者:Kartik Gupta, Thalaiyasingam Ajanthan
链接:https://arxiv.org/abs/2003.13511
【2】 Adversarial Feature Hallucination Networks for Few-Shot Learning
面向少发学习的对抗性特征幻觉网络
作者:Kai Li, Yun Fu
备注:To appear in CVPR 2020
链接:https://arxiv.org/abs/2003.13193
【3】 Gradually Vanishing Bridge for Adversarial Domain Adaptation
逐渐消失的对抗性领域适应之桥
作者:Shuhao Cui, Qi Tian
备注:CVPR2020
链接:https://arxiv.org/abs/2003.13183
【4】 Adversarial Robustness: From Self-Supervised Pre-Training to Fine-Tuning
对抗鲁棒性:从自我监督预训练到微调
作者:Tianlong Chen, Zhangyang Wang
备注:CVPR 2020
链接:https://arxiv.org/abs/2003.12862
【5】 Adversarial Imitation Attack
对抗性模仿攻击
作者:Mingyi Zhou, Ce Zhu
链接:https://arxiv.org/abs/2003.12760
【6】 DaST: Data-free Substitute Training for Adversarial Attacks
DAST:对抗攻击的无数据替代训练
作者:Mingyi Zhou, Ce Zhu
备注:Accepted by CVPR2020
链接:https://arxiv.org/abs/2003.12703
[行为/时空/光流/姿态/运动]:
【1】 Speech2Action: Cross-modal Supervision for Action Recognition
Speech2Action:用于动作识别的跨模式监督
作者:Arsha Nagrani, Andrew Zisserman
备注:Accepted to CVPR 2020
链接:https://arxiv.org/abs/2003.13594
【2】 Context Based Emotion Recognition using EMOTIC Dataset
使用EMOTIC数据集的基于上下文的情感识别
作者:Ronak Kosti, Agata Lapedriza
链接:https://arxiv.org/abs/2003.13401
【3】 MetaFuse: A Pre-trained Fusion Model for Human Pose Estimation
MetaFuse:一种用于人体姿态估计的预训练融合模型
作者:Rongchang Xie, Yizhou Wang
备注:Accepted to CVPR2020
链接:https://arxiv.org/abs/2003.13239
【4】 Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation
类比学习:无监督光流估计变换的可靠监督
作者:Liang Liu, Feiyue Huang
备注:Accepted to CVPR 2020
链接:https://arxiv.org/abs/2003.13045
【5】 AutoTrack: Towards High-Performance Visual Tracking for UAV with Automatic Spatio-Temporal Regularization
自动跟踪:实现自动时空正则化的无人机高性能视觉跟踪
作者:Yiming Li, Geng Lu
备注:2020 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
链接:https://arxiv.org/abs/2003.12949
[迁移学习/domain/主动学习/自适应]:
【1】 Domain-aware Visual Bias Eliminating for Generalized Zero-Shot Learning
用于广义零发射学习的领域感知视觉偏差消除
作者:Shaobo Min, Yongdong Zhang
备注:Accepted by CVPR2020
链接:https://arxiv.org/abs/2003.13261
【2】 Learning to Learn Single Domain Generalization
学会学习单域概括
作者:Fengchun Qiao, Xi Peng
备注:In CVPR 2020 (13 pages including supplementary material). The source code and pre-trained models are publicly available at: this https URL
链接:https://arxiv.org/abs/2003.13216
【3】 Diagnosis of Breast Cancer using Hybrid Transfer Learning
混合转移学习在乳腺癌诊断中的应用
作者:Subrato Bharati, Prajoy Podder
链接:https://arxiv.org/abs/2003.13503
【4】 Mutual Learning Network for Multi-Source Domain Adaptation
用于多源域自适应的互学习网络
作者:Zhenpeng Li, Jieping Ye
链接:https://arxiv.org/abs/2003.12944
[压缩/量化/剪枝加速相关]:
【1】 DHP: Differentiable Meta Pruning via HyperNetworks
DHP:通过超网络的可微分元剪枝
作者:Yawei Li, Radu Timofte
链接:https://arxiv.org/abs/2003.13683
【2】 Plug-and-Play Algorithms for Large-scale Snapshot Compressive Imaging
大规模快照压缩成像的即插即用算法
作者:Xin Yuan, Qionghai Dai
备注:CVPR 2020
链接:https://arxiv.org/abs/2003.13654
【3】 Faster than FAST: GPU-Accelerated Frontend for High-Speed VIO
比快速更快:GPU加速的高速VIO前端
作者:Balazs Nagy, Davide Scaramuzza
备注:Submitted to IEEE International Conference on Intelligent Robots and Systems (IROS), 2020. Open-source implementation available at this https URL
链接:https://arxiv.org/abs/2003.13493
【4】 Acceleration of Convolutional Neural Network Using FFT-Based Split Convolutions
用基于FFT的分裂卷积加速卷积神经网络
作者:Kamran Chitsaz, Shahram Shirani
链接:https://arxiv.org/abs/2003.12621
【5】 How Not to Give a FLOP: Combining Regularization and Pruning for Efficient Inference
如何避免失败:结合正则化和修剪以实现有效的推理
作者:Tai Vu, Roy Nehoran
链接:https://arxiv.org/abs/2003.13593
【6】 BVI-DVC: A Training Database for Deep Video Compression
BVI-DVC:一个深度视频压缩训练数据库
作者:Di Ma, David R. Bull
链接:https://arxiv.org/abs/2003.13552
【7】 Optimizing Geometry Compression using Quantum Annealing
利用量子退火优化几何压缩
作者:Sebastian Feld, Claudia Linnhoff-Popien
链接:https://arxiv.org/abs/2003.13253
【8】 Image compression optimized for 3D reconstruction by utilizing deep neural networks
利用深层神经网络优化三维重建的图像压缩
作者:Alex Golts, Yoav Y. Schechner
链接:https://arxiv.org/abs/2003.12618
[超分辨率]:
【1】 Super Resolution for Root Imaging
根成像的超分辨率
作者:Jose F. Ruiz-Munoz, James E. Baciak
链接:https://arxiv.org/abs/2003.13537
【2】 High-Order Residual Network for Light Field Super-Resolution
用于光场超分辨的高阶残差网络
作者:Nan Meng, Edmund Y. Lam
链接:https://arxiv.org/abs/2003.13094
【3】 Structure-Preserving Super Resolution with Gradient Guidance
梯度导向的结构保持超分辨率
作者:Cheng Ma, Jie Zhou
备注:Accepted to CVPR 2020
链接:https://arxiv.org/abs/2003.13081
[点云]:
【1】 PointGMM: a Neural GMM Network for Point Clouds
PointGMM:一种用于点云的神经GMM网络
作者:Amir Hertz, Daniel Cohen-Or
备注:CVPR 2020 -- final version
链接:https://arxiv.org/abs/2003.13326
【2】 A Benchmark for Point Clouds Registration Algorithms
点云配准算法的基准
作者:Simone Fontana, Domenico Giorgio Sorrenti
链接:https://arxiv.org/abs/2003.12841
[深度depth相关]:
【1】 Rethinking Depthwise Separable Convolutions: How Intra-Kernel Correlations Lead to Improved MobileNets
重新思考深度可分卷积:核内相关如何导致改进的MobileNets
作者:Daniel Haase, Manuel Amthor
备注:Accepted by CVPR 2020
链接:https://arxiv.org/abs/2003.13549
重磅!计算机视觉交流群已成立!
欢迎各位Cver加入计算机视觉微信交流大群,本群旨在交流图像分类、目标检测、点云/语义分割、目标跟踪、机器视觉、GAN、超分辨率、人脸检测与识别、动作行为/时空/光流/姿态/运动、模型压缩/量化/剪枝、NAS、迁移学习、人体姿态估计等内容。
进群请备注:研究方向+地点+学校/公司+昵称(如图像分类+上海+上交+小明)
广告商、博主请绕道!
???? 长按识别,即可进群!