图像分割，图像识别，图像分类 | 计算机视觉论文速递

[1] Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentation
标题 | 弱和半监督语义分割的反专业操作归因
链接 | https://arxiv.org/abs/2103.08896

[2] Spatial Dependency Networks: Neural Layers for Improved Generative Image Modeling
标题 | 空间依赖网络：用于改进的生成图像建模的神经层
链接 | https://arxiv.org/abs/2103.08877

[3] Super-Resolving Cross-Domain Face Miniatures by Peeking at One-Shot Exemplar
标题 | 偷看一枪示例超分辨跨域脸部缩影
链接 | https://arxiv.org/abs/2103.08863

[4] Adversarial YOLO: Defense Human Detection Patch Attacks via Detecting Adversarial Patches
标题 | 对抗性YOLO：通过检测对抗性补丁来防御人体检测补丁攻击
链接 | https://arxiv.org/abs/2103.08860

[5] Lite-HDSeg: LiDAR Semantic Segmentation Using Lite Harmonic Dense Convolutions
标题 | Lite-HDSeg：使用Lite Harmonic Dense卷积的LiDAR语义分割
链接 | https://arxiv.org/abs/2103.08852

[6] Multilingual Multimodal Pre-training for Zero-Shot Cross-Lingual Transfer of Vision-Language Models
标题 | 视觉语言模型的零射跨语言转移的多语言多模式预训练
链接 | https://arxiv.org/abs/2103.08849

[7] GSVNet: Guided Spatially-Varying Convolution for Fast Semantic Segmentation on Video
标题 | GSVNet：用于视频的快速语义分割的引导空间变化卷积
链接 | https://arxiv.org/abs/2103.08834

[8] Skeleton Based Sign Language Recognition Using Whole-body Keypoints
标题 | 基于全身关键点的基于骨架的手语识别
链接 | https://arxiv.org/abs/2103.08833

[9] Towards Indirect Top-Down Road Transport Emissions Estimation
标题 | 迈向间接的自上而下的道路运输排放估算
链接 | https://arxiv.org/abs/2103.08829

[10] Track to Detect and Segment: An Online Multi-Object Tracker
标题 | 跟踪检测和分段：在线多对象跟踪器
链接 | https://arxiv.org/abs/2103.08808

[11] A Computer Vision System to Help Prevent the Transmission of COVID-19
标题 |有助于防止COVID-19传播的计算机视觉系统
链接 | https://arxiv.org/abs/2103.08773

[12] A LiDAR-Guided Framework for Video Enhancement
标题 | LiDAR指导的视频增强框架
链接 | https://arxiv.org/abs/2103.08764

[13] Revisiting Dynamic Convolution via Matrix Decomposition
标题 | Y通过矩阵分解重新探究动态卷积
链接 | https://arxiv.org/abs/2103.08756

[14] S3Net: 3D LiDAR Sparse Semantic Segmentation Network
标题 |S3Net：3D LiDAR稀疏语义分割网络
链接 | https://arxiv.org/abs/2103.08745

[15] UPANets: Learning from the Universal Pixel Attention Networks
标题 | UPANets：向通用像素注意网络学习
链接 | https://arxiv.org/abs/2103.08640

[16] Domain-Incremental Continual Learning for Mitigating Bias in Facial Expression and Action Unit Recognition
标题 |领域增量式持续学习，以缓解面部表情和动作单元识别中的偏见
链接 | https://arxiv.org/abs/2103.08637

[17] Design and Development of Autonomous Delivery Robot
标题 | 自主配送机器人的设计与开发
链接 | https://arxiv.org/abs/2103.09229

[18] Sparse Curriculum Reinforcement Learning for End-to-End Driving
标题 | 端到端驾驶的稀疏课程强化学习
链接 | https://arxiv.org/abs/2103.09189

[19] Unsupervised Anomaly Segmentation using Image-Semantic Cycle Translation
标题 | 使用图像语义循环转换的无监督异常分割
链接 | https://arxiv.org/abs/2103.09094

[20] Invertible Residual Network with Regularization for Effective Medical Image Segmentation
标题 | 带正则化的可逆残差网络，用于有效的医学图像分割
链接 | https://arxiv.org/abs/2103.09042

[21] Repurposing Pretrained Models for Robust Out-of-domain Few-Shot Learning
标题 | 重新利用预训练的模型进行鲁棒的域外少量学习
链接 | https://arxiv.org/abs/2103.09027

[22] Unsupervised Missing Cone Deep Learning in Optical Diffraction Tomography
标题 | 光学衍射层析成像中无监督的锥深度学习
链接 | https://arxiv.org/abs/2103.09022

[23] Unsupervised anomaly detection in digital pathology using GANs
标题 | 使用GAN在数字病理学中进行无监督异常检测
链接 | https://arxiv.org/abs/2103.08945

[24] Deep Reinforcement Learning for Band Selection in Hyperspectral Image Classification
标题 | 深度强化学习在高光谱图像分类中的波段选择
链接 | https://arxiv.org/abs/2103.08741

25] Deep Learning for Chest X-ray Analysis: A Survey
标题 | 胸部X射线分析的深度学习：一项调查
链接 | https://arxiv.org/abs/2103.08700

[26] Towards New Multiwavelets: Associated Filters and Algorithms. Part I: Theoretical Framework and Investigation of Biomedical Signals, ECG and Coronavirus Cases
标题 | 迈向新的多小波：相关滤波器和算法。 第一部分：生物医学信号，心电图和冠状病毒病例的理论框架和研究
链接 | https://arxiv.org/abs/2103.08657