cs.CV（2023-11-23）

📊 共 13 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (5) 支柱九：具身大模型 (Embodied Foundation Models) (3) 支柱三：空间感知与语义 (Perception & Semantics) (2 🔗1) 支柱一：机器人控制 (Robot Control) (2) 支柱七：动作重定向 (Motion Retargeting) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
1 Towards Transferable Multi-modal Perception Representation Learning for Autonomy: NeRF-Supervised Masked AutoEncoder 提出NeRF监督的掩码自编码器以解决多模态感知表示学习问题 representation learning masked autoencoder MAE
2 Posterior Distillation Sampling 提出后验蒸馏采样方法以优化图像编辑 distillation neural radiance field
3 Robustness-Reinforced Knowledge Distillation with Correlation Distance and Network Pruning 提出鲁棒性增强知识蒸馏方法以解决现有蒸馏技术的局限性 distillation
4 Periodically Exchange Teacher-Student for Source-Free Object Detection 提出周期性教师-学生模型交换以解决源无关目标检测不稳定问题 teacher-student
5 Attribute-Aware Representation Rectification for Generalized Zero-Shot Learning 提出属性感知表示修正框架以解决广义零样本学习问题 representation learning distillation

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

#题目一句话要点标签🔗⭐
6 Compositional Zero-shot Learning via Progressive Language-based Observations 提出渐进式语言观察以解决组合零-shot学习问题 large language model
7 Perceptual Image Compression with Cooperative Cross-Modal Side Information 提出文本引导的图像压缩方法以提升感知质量 multimodal
8 GS-Pose: Category-Level Object Pose Estimation via Geometric and Semantic Correspondence 提出GS-Pose以解决类别级物体姿态估计问题 foundation model

🔬 支柱三：空间感知与语义 (Perception & Semantics) (2 篇)

#题目一句话要点标签🔗⭐
9 ECRF: Entropy-Constrained Neural Radiance Fields Compression with Frequency Domain Optimization 提出ECRF以解决NeRF模型数据压缩问题 NeRF neural radiance field
10 GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondence 提出GigaPose以解决CAD模型基础的新物体姿态估计问题 3D reconstruction ✅

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
11 A New Benchmark and Model for Challenging Image Manipulation Detection 提出新的基准和模型以解决图像篡改检测问题 manipulation
12 Appearance-based gaze estimation enhanced with synthetic images using deep neural networks 提出基于外观的注视估计方法以解决人机交互问题 humanoid humanoid robot

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

#题目一句话要点标签🔗⭐
13 Dynamic Compositional Graph Convolutional Network for Efficient Composite Human Motion Prediction 提出动态组合图卷积网络以解决复合人类动作预测问题 human motion human motion prediction motion prediction

⬅️ 返回 cs.CV 首页 · 🏠 返回主页