cs.CV（2023-10-06）

📊 共 11 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

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

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
1 Module-wise Adaptive Distillation for Multimodality Foundation Models 提出模块自适应蒸馏方法以优化多模态基础模型 distillation foundation model multimodal
2 URLOST: Unsupervised Representation Learning without Stationarity or Topology 提出URLOST框架以解决无监督表示学习中的非平稳性与拓扑依赖问题 representation learning masked autoencoder MAE
3 Self-Supervised Neuron Segmentation with Multi-Agent Reinforcement Learning 提出基于多智能体强化学习的自监督神经元分割方法 reinforcement learning ✅

🔬 支柱三：空间感知与语义 (Perception & Semantics) (3 篇)

#题目一句话要点标签🔗⭐
4 MeSa: Masked, Geometric, and Supervised Pre-training for Monocular Depth Estimation 提出MeSa框架以解决单目深度估计中的特征不匹配问题 depth estimation monocular depth
5 Improving Neural Radiance Field using Near-Surface Sampling with Point Cloud Generation 提出近表面采样框架以提升NeRF渲染质量 NeRF neural radiance field
6 Sub-token ViT Embedding via Stochastic Resonance Transformers 提出随机共振变换器以解决ViT空间细节缺失问题 depth estimation

🔬 支柱九：具身大模型 (Embodied Foundation Models) (2 篇)

#题目一句话要点标签🔗⭐
7 Multimodal Identification of Alzheimer's Disease: A Review 综述多模态技术以提升阿尔茨海默病早期诊断效果 multimodal
8 Robust Multimodal Learning with Missing Modalities via Parameter-Efficient Adaptation 提出一种参数高效的适应方法以解决多模态缺失问题 multimodal

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
9 Universal Humanoid Motion Representations for Physics-Based Control 提出通用人形运动表示以解决物理基础控制问题 humanoid humanoid control motion tracking

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
10 Bridging the Gap between Human Motion and Action Semantics via Kinematic Phrases 提出运动理解框架以解决动作语义映射问题 motion generation human motion ✅

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
11 SwimXYZ: A large-scale dataset of synthetic swimming motions and videos 提出SwimXYZ以解决游泳视频数据集不足问题 SMPL

⬅️ 返回 cs.CV 首页 · 🏠 返回主页