点击上方
“
小白学视觉
”,选择加"
星标
"或“
置顶
”
重磅干货,第一时间送达![](http://mmbiz.qpic.cn/mmbiz_jpg/ow6przZuPIENb0m5iawutIf90N2Ub3dcPuP2KXHJvaR1Fv2FnicTuOy3KcHuIEJbd9lUyOibeXqW8tEhoJGL98qOw/640?wx_fmt=other&wxfrom=5&wx_lazy=1&wx_co=1&tp=webp)
扫描下方二维码,加入前沿学术论文交流星球
!
可以获得最新顶会/顶刊论文的idea解读、解读的PDF
和
CV从入门到精通资料,及最前沿应用
!
各位读者们,我们决定以后每周一为大家汇总每周在知识星球内更新的论文解读内容!方便有需求的读者使用,并且欢迎各位读者加入我们的知识星球。每天都有最新的顶会、顶刊论文的解读文章,并且提供中文解读的PDF版本,方便读者下载阅读和使用。
医学图像处理文章
1.【TMI 2024】Toward Enabling Cardiac Digital Twins of Myocardial Infarction Using Deep Computational Models for Inverse Inference
-
中文题目:利用深度计算模型实现心肌梗死心脏数字孪生
2.【TMI 2024】Semantic-Oriented Visual Prompt Learning for Diabetic Retinopathy Grading on Fundus Images
-
中文题目:基于语义导向视觉提示学习的糖尿病视网膜病变眼底图像分级
-
【MIA 2024】Vessel-promoted OCT to OCTA image translation by heuristic contextual constraints
-
中文题目:基于启发式上下文约束的血管促进OCT到OCTA图像翻译
-
【MIA 2024】MMGPL: Multimodal Medical Data Analysis with Graph Prompt Learning
-
中文题目:MMGPL:基于图提示学习的多模态医学数据分析
-
【MIA 2024】Cascaded Multi-path Shortcut Diffusion Model for Medical Image Translation
-
中文题目:级联多路径快捷扩散模型在医学图像翻译中的应用
-
【TMI 2024】Manifold Regularizer for High-Resolution fMRI Joint Reconstruction and Dynamic Quantification
-
中文题目:高分辨率fMRI联合重建与动态定量的流形正则化
-
【TMI 2024】Attention-Aware Non-Rigid Image Registration for Accelerated MR Imaging
-
中文题目:注意力感知的非刚性图像配准加速磁共振成像
TPAMI期刊文章
-
英文题目:On the Number of Linear Regions of Convolutional Neural Networks With Piecewise Linear Activations
-
中文题目:卷积神经网络中分段线性激活函数的线性区域数量研究
-
Animatable Implicit Neural Representations for Creating Realistic Avatars From Videos
-
中文题目:基于视频创建逼真化身的可动画隐式神经表示
-
Non-Smooth Trajectory Optimization for Wheeled Balancing Robots with Contact Switches and Impacts
-
中文题目:非光滑轨迹优化:用于具有接触切换和冲击的轮式平衡机器人
-
STMixer: A One-Stage Sparse Action Detector
-
中文题目:STMixer: 一种单阶段稀疏动作检测器
-
MotionDiffuse: Text-Driven Human Motion Generation With Diffusion Model
-
中文题目:MotionDiffuse:基于文本驱动的人体运动生成扩散模型
-
MixFormer: End-to-End Tracking With Iterative Mixed Attention
-
中文题目:MixFormer: 基于迭代混合注意力的端到端跟踪
-
MO-MIX: Multi-Objective Multi-Agent Cooperative Decision-Making With Deep Reinforcement Learning
-
中文题目:MO-MIX:基于深度强化学习的多目标多智能体协同决策
-
In-Domain GAN Inversion for Faithful Reconstruction and Editability
-
中文题目:领域内GAN反演:用于精确重建和可编辑性
-
Meta Invariance Defense Towards Generalizable Robustness to Unknown Adversarial Attacks
-
中文题目:面向对未知对抗性攻击具有泛化鲁棒性的元不变性防御
-
EvHandPose: Event-Based 3D Hand Pose Estimation With Sparse Supervision
-
Cross-Modal Federated Human Activity Recognition
-
CenterNet++ for Object Detection
-
Anti-UAV410: A Thermal Infrared Benchmark and Customized Scheme for Tracking Drones in the Wild
-
中文题目:Anti-UAV410: 一种用于野外追踪无人机的热红外基准测试与定制化方案
遥感图像处理
-
【TRGS 2024】A Double-Head Global Reasoning Network for Object Detection of Remote Sensing Images
-
【TRGS 2024】A DeNoising FPN With Transformer R-CNN for Tiny Object Detection
-
中文题目:用于微小目标检测的去噪特征金字塔网络与transformer区域卷积神经网络
-
【TRGS 2024】A Decoder-Focused Multitask Network for Semantic Change Detection
-
【TRGS 2024】4DST-BTMD: An Infrared Small Target Detection Method Based on 4-D Data-Sphered Space
-
中文题目:4DST-BTMD:基于4-D数据球面空间的红外小目标检测方法