cs.CV（2024-02-21）

📊 共 11 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱三：空间感知与语义 (Perception & Semantics) (4) 支柱九：具身大模型 (Embodied Foundation Models) (3 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱七：动作重定向 (Motion Retargeting) (1 🔗1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱三：空间感知与语义 (Perception & Semantics) (4 篇)

#题目一句话要点标签🔗⭐
1 Identifying Unnecessary 3D Gaussians using Clustering for Fast Rendering of 3D Gaussian Splatting 提出基于聚类的技术以快速识别不必要的3D高斯以优化渲染 3D gaussian splatting gaussian splatting splatting
2 A Feature Matching Method Based on Multi-Level Refinement Strategy 提出KTGP-ORB以解决视觉SLAM中的特征匹配精度问题 visual SLAM feature matching
3 Zero-BEV: Zero-shot Projection of Any First-Person Modality to BEV Maps 提出Zero-BEV以解决第一人称模态到BEV地图的投影问题 depth estimation monocular depth first-person view
4 Generalizable Semantic Vision Query Generation for Zero-shot Panoptic and Semantic Segmentation 提出CONCAT以解决零-shot全景分割问题 open-vocabulary open vocabulary

🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)

#题目一句话要点标签🔗⭐
5 CODIS: Benchmarking Context-Dependent Visual Comprehension for Multimodal Large Language Models 提出CODIS基准以解决多模态大语言模型的视觉理解问题 large language model multimodal ✅
6 Hybrid Reasoning Based on Large Language Models for Autonomous Car Driving 基于大语言模型的混合推理提升自动驾驶决策能力 large language model
7 On Large Visual Language Models for Medical Imaging Analysis: An Empirical Study 研究大型视觉语言模型在医学影像分析中的应用 large language model multimodal

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
8 SealD-NeRF: Interactive Pixel-Level Editing for Dynamic Scenes by Neural Radiance Fields 提出SealD-NeRF以解决动态场景下的像素级编辑问题 teacher-student NeRF neural radiance field
9 Unsupervised learning based object detection using Contrastive Learning 提出无监督学习方法以解决目标检测问题 contrastive learning

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

#题目一句话要点标签🔗⭐
10 Context-based Interpretable Spatio-Temporal Graph Convolutional Network for Human Motion Forecasting 提出基于上下文的可解释时空图卷积网络以解决人类动作预测问题 human motion human motion prediction motion prediction ✅

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
11 VL-Trojan: Multimodal Instruction Backdoor Attacks against Autoregressive Visual Language Models 提出VL-Trojan以解决自回归视觉语言模型的后门攻击问题 manipulation multimodal instruction following

⬅️ 返回 cs.CV 首页 · 🏠 返回主页