计算机视觉论文

[1] Temporal Cluster Matching for Change Detection of Structures from Satellite Imagery
标题 | 时态聚类匹配用于卫星影像结构变化检测
链接 | https://arxiv.org/abs/2103.09787

[2] ALADIN: All Layer Adaptive Instance Normalization for Fine-grained Style Similarity
标题 | 细粒度样式相似的全层自适应实例规范化
链接 | https://arxiv.org/abs/2103.09776

[3] HAMIL: Hierarchical Aggregation-Based Multi-Instance Learning for Microscopy Image Classification
标题 | 基于分层聚合的显微图像分类多实例学习
链接 | https://arxiv.org/abs/2103.09764

[4] Few-Shot Visual Grounding for Natural Human-Robot Interaction
标题 | 少见的人机交互视觉基础
链接 | https://arxiv.org/abs/2103.09720

[5] Quantitative Effectiveness Assessment and Role Categorization of Individual Units in Convolutional Neural Networks
标题 | 卷积神经网络中各个单元的定量有效性评估和角色分类
链接 | https://arxiv.org/abs/2103.09716

[6] Trans-SVNet: Accurate Phase Recognition from Surgical Videos via Hybrid Embedding Aggregation Transformer
标题 |作者 | 通过混合嵌入聚合变压器从手术视频中准确识别相位
链接 | https://arxiv.org/abs/2103.09712

[7] ShipSRDet: An End-to-End Remote Sensing Ship Detector Using Super-Resolved Feature Representation
标题 | 使用超分辨特征表示的端到端遥感船探测器
链接 | https://arxiv.org/abs/2103.09699

[8] Fourier Transform of Percoll Gradients Boosts CNN Classification of Hereditary Hemolytic Anemias
标题 | Percoll梯度的傅立叶变换增强了遗传性溶血性贫血的CNN分类
链接 | https://arxiv.org/abs/2103.09671

[9] The Invertible U-Net for Optical-Flow-free Video Interframe Generation
标题 | 用于无光流视频帧间生成的可逆U-Net
链接 | https://arxiv.org/abs/2103.09576

[10] Hierarchical Random Walker Segmentation for Large Volumetric Biomedical Data
标题 |大容量生物医学数据的分层随机Walker分割
链接 | https://arxiv.org/abs/2103.09564

[11] Multi-channel Deep Supervision for Crowd Counting
标题 | 多渠道深度监控的人群计数
链接 | https://arxiv.org/abs/2103.09553

[12] CNN Model & Tuning for Global Road Damage Detection
标题 | CNN模型和针对全球道路损坏检测的调整
链接 | https://arxiv.org/abs/2103.09512

[13] Virtual Dress Swap Using Landmark Detection
标题 | 使用地标检测进行虚拟着装交换
链接 | https://arxiv.org/abs/2103.09475

[14] You Only Look One-level Feature
标题 | 您只看一级功能
链接 | https://arxiv.org/abs/2103.09460

[15] Learning Discriminative Prototypes with Dynamic Time Warping
标题 | 通过动态时间扭曲学习判别性原型
链接 | https://arxiv.org/abs/2103.09458

[16] Adversarial Attacks on Camera-LiDAR Models for 3D Car Detection
标题 | 用于3D汽车检测的Camera-LiDAR模型的对抗性攻击
链接 | https://arxiv.org/abs/2103.09448

[17] Pose-GNN : Camera Pose Estimation System Using Graph Neural Networks
标题 | 图神经网络的摄像机姿态估计系统
链接 | https://arxiv.org/abs/2103.09435

[18] WheatNet: A Lightweight Convolutional Neural Network for High-throughput Image-based Wheat Head Detection and Counting
标题 | 基于高通量图像的小麦头检测和计数的轻型卷积神经网络
链接 | https://arxiv.org/abs/2103.09408 ​

[19] SPICE: Semantic Pseudo-labeling for Image Clustering
标题 | 图像聚类的语义伪标记
链接 | https://arxiv.org/abs/2103.09382

[20] Semi-Supervised Learning for Eye Image Segmentation
标题 | 半监督学习的眼图像分割
链接 | https://arxiv.org/abs/2103.09369

[21] Digital Peter: Dataset, Competition and Handwriting Recognition Methods
标题 | 数据集，竞赛和笔迹识别方法
链接 | https://arxiv.org/abs/2103.09354

[22] Co-Generation and Segmentation for Generalized Surgical Instrument Segmentation on Unlabelled Data
标题 | 共生成和分段，用于对未标记数据进行广义的手术器械分割
链接 | https://arxiv.org/abs/2103.09276

[23] Bio-inspired Robustness: A Review
标题 | 受生物启发的坚固性：综述
链接 | https://arxiv.org/abs/2103.09265

[24] Training GANs with Stronger Augmentations via Contrastive Discriminator
标题 | 通过对比鉴别器训练具有更强增强能力的GAN
链接 | https://arxiv.org/abs/2103.09742

[25] Generating Annotated Training Data for 6D Object Pose Estimation in Operational Environments with Minimal User Interaction
标题 | 在操作环境中以最小的用户交互生成带注释的训练数据以进行6D对象姿势估计
链接 | https://arxiv.org/abs/2103.09696

[26] Automatic Generation of Contrast Sets from Scene Graphs: Probing the Compositional Consistency of GQA
标题 | 从场景图自动生成对比度集：探究GQA的成分一致性
链接 | https://arxiv.org/abs/2103.09591

[27] PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning
标题 | 时空预测学习的递归神经网络
链接 | https://arxiv.org/abs/2103.09504

[28] Pros and Cons of GAN Evaluation Measures: New Developments
标题 | GAN评估措施的优缺点：新进展
链接 | https://arxiv.org/abs/2103.09396

[29] Colorectal Cancer Segmentation using Atrous Convolution and Residual Enhanced UNet
标题 | 使用Atrous卷积和残差增强UNet进行结直肠癌分割
链接 | https://arxiv.org/abs/2103.09289

[30] Semi-Supervised Learning for Eye Image Segmentation
标题：半监督学习在眼睛图像分割中的应用
链接：https://arxiv.org/abs/2103.09369

[31] Co-Generation and Segmentation for Generalized Surgical Instrument Segmentation on Unlabelled Data
标题：基于无标签数据的通用手术器械分割的联合生成与分割
链接：https://arxiv.org/abs/2103.09276

[32] Colorectal Cancer Segmentation using Atrous Convolution and Residual Enhanced UNet
标题：基于Atrus卷积和残余增强UNET的大肠癌分割
链接：https://arxiv.org/abs/2103.09289

[33] Aggregated Multi-GANs for Controlled 3D Human Motion Prediction
标题：用于受控三维人体运动预测的聚合多GAN算法
链接：https://arxiv.org/abs/2103.09755

[34] Training GANs with Stronger Augmentations via Contrastive Discriminator
标题：用对比判别器训练具有较强增强能力的GAN
链接：https://arxiv.org/abs/2103.09742

[35] Generating Annotated Training Data for 6D Object Pose Estimation in Operational Environments with Minimal User Interaction
标题：在用户交互最少的操作环境中生成用于6D对象位姿估计的带注释的训练数据
链接：https://arxiv.org/abs/2103.09696

[36] ​ Pros and Cons of GAN Evaluation Measures: New Developments
标题：GaN评估方法的利弊：新进展
链接：https://arxiv.org/abs/2103.09396