cs.CV（2024-03-08）

📊 共 27 篇论文 | 🔗 14 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (7 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (7 🔗3) 支柱三：空间感知与语义 (Perception & Semantics) (6 🔗3) 支柱一：机器人控制 (Robot Control) (3 🔗2) 支柱六：视频提取与匹配 (Video Extraction) (2 🔗1) 支柱七：动作重定向 (Motion Retargeting) (1 🔗1) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (7 篇)

#题目一句话要点标签🔗⭐
1 Debiasing Multimodal Large Language Models via Penalization of Language Priors 提出后处理去偏见方法以解决多模态大语言模型的偏见问题 large language model multimodal
2 FedFMS: Exploring Federated Foundation Models for Medical Image Segmentation 提出FedFMS以解决医疗图像分割中的隐私与效率问题 foundation model ✅
3 Med3DInsight: Enhancing 3D Medical Image Understanding with 2D Multi-Modal Large Language Models 提出Med3DInsight以解决3D医学图像理解问题 large language model
4 XPSR: Cross-modal Priors for Diffusion-based Image Super-Resolution 提出XPSR框架以解决图像超分辨率中的语义感知问题 large language model multimodal ✅
5 The R2D2 deep neural network series paradigm for fast precision imaging in radio astronomy 提出R2D2深度神经网络系列以解决射电天文学中的高精度成像问题 VLA
6 Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance 提出LoRAT以解决视觉跟踪中的参数高效微调问题 large language model ✅
7 Learning to Rematch Mismatched Pairs for Robust Cross-Modal Retrieval 提出L2RM框架以解决跨模态检索中的部分不匹配对问题 multimodal ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)

#题目一句话要点标签🔗⭐
8 Synthetic Privileged Information Enhances Medical Image Representation Learning 通过合成特权信息提升医学图像表示学习的效果 representation learning privileged information multimodal
9 Enhancing Multimodal Unified Representations for Cross Modal Generalization 提出TOC与FCID以解决多模态统一表示的泛化问题 contrastive learning multimodal ✅
10 LightM-UNet: Mamba Assists in Lightweight UNet for Medical Image Segmentation 提出LightM-UNet以解决医疗图像分割中的计算资源限制问题 Mamba SSM state space model ✅
11 MamMIL: Multiple Instance Learning for Whole Slide Images with State Space Models 提出MamMIL框架以解决WSI分析中的实例依赖问题 Mamba state space model linear attention ✅
12 Generalized Correspondence Matching via Flexible Hierarchical Refinement and Patch Descriptor Distillation 提出灵活层次化精炼与补丁描述符蒸馏以解决对应匹配问题 distillation feature matching
13 Attention-guided Feature Distillation for Semantic Segmentation 提出注意力引导特征蒸馏以解决语义分割问题 distillation
14 RadarDistill: Boosting Radar-based Object Detection Performance via Knowledge Distillation from LiDAR Features 提出RadarDistill以提升雷达物体检测性能 distillation

🔬 支柱三：空间感知与语义 (Perception & Semantics) (6 篇)

#题目一句话要点标签🔗⭐
15 GSEdit: Efficient Text-Guided Editing of 3D Objects via Gaussian Splatting 提出GSEdit以实现高效的文本引导3D对象编辑 gaussian splatting splatting NeRF
16 Stealing Stable Diffusion Prior for Robust Monocular Depth Estimation 提出Stealing Stable Diffusion以解决单目深度估计在复杂环境中的问题 depth estimation monocular depth scene understanding ✅
17 OccFusion: Depth Estimation Free Multi-sensor Fusion for 3D Occupancy Prediction 提出OccFusion以解决深度估计依赖问题 depth estimation
18 DiffSF: Diffusion Models for Scene Flow Estimation 提出DiffSF以解决场景流估计中的不确定性问题 scene flow ✅
19 DITTO: Dual and Integrated Latent Topologies for Implicit 3D Reconstruction 提出DITTO以解决稀疏点云的隐式3D重建问题 3D reconstruction
20 OmniCount: Multi-label Object Counting with Semantic-Geometric Priors 提出OmniCount以解决多标签物体计数问题 open-vocabulary open vocabulary ✅

🔬 支柱一：机器人控制 (Robot Control) (3 篇)

#题目一句话要点标签🔗⭐
21 Motion-Guided Dual-Camera Tracker for Endoscope Tracking and Motion Analysis in a Mechanical Gastric Simulator 提出运动引导双摄像头跟踪器以解决内窥镜跟踪问题 motion tracking Mamba ✅
22 Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds 提出HiT-ADV以解决3D点云分类中的对抗攻击问题 manipulation ✅
23 Learning Expressive And Generalizable Motion Features For Face Forgery Detection 提出基于运动特征的面部伪造检测方法以提升检测效果 manipulation

🔬 支柱六：视频提取与匹配 (Video Extraction) (2 篇)

#题目一句话要点标签🔗⭐
24 ERASOR++: Height Coding Plus Egocentric Ratio Based Dynamic Object Removal for Static Point Cloud Mapping 提出ERASOR++以解决动态物体对静态点云映射的干扰问题 egocentric
25 MUC: Mixture of Uncalibrated Cameras for Robust 3D Human Body Reconstruction 提出无标定相机混合方法以解决3D人体重建问题 SMPL SMPL-X ✅

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
26 JointMotion: Joint Self-Supervision for Joint Motion Prediction 提出JointMotion以解决自驾车关节运动预测问题 motion prediction multimodal ✅

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
27 DiffClass: Diffusion-Based Class Incremental Learning 提出DiffClass以解决增量学习中的灾难性遗忘问题 MDM

⬅️ 返回 cs.CV 首页 · 🏠 返回主页