cs.CV（2024-08-10）

📊 共 10 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (3 🔗2) 支柱三：空间感知与语义 (Perception & Semantics) (2 🔗1) 支柱八：物理动画 (Physics-based Animation) (2 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (2) 支柱七：动作重定向 (Motion Retargeting) (1)

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

#题目一句话要点标签🔗⭐
1 Scene123: One Prompt to 3D Scene Generation via Video-Assisted and Consistency-Enhanced MAE Scene123：通过视频辅助和一致性增强的MAE实现单提示3D场景生成 masked autoencoder MAE neural radiance field ✅
2 UrFound: Towards Universal Retinal Foundation Models via Knowledge-Guided Masked Modeling UrFound：通过知识引导的掩码建模实现通用视网膜基础模型 representation learning foundation model multimodal ✅
3 Multimodal generative semantic communication based on latent diffusion model 提出基于潜在扩散模型的多模态生成语义通信框架，提升恶劣环境下决策精度。 contrastive learning semantic map multimodal

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

#题目一句话要点标签🔗⭐
4 Visual SLAM with 3D Gaussian Primitives and Depth Priors Enabling Novel View Synthesis 提出基于3D高斯基元和深度先验的视觉SLAM，实现新视角合成。 visual SLAM 3D gaussian splatting 3DGS
5 Radiance Field Learners As UAV First-Person Viewers 提出FPV-NeRF，解决无人机第一视角视频NeRF重建中视角有限和尺度变化问题 NeRF neural radiance field first-person view ✅

🔬 支柱八：物理动画 (Physics-based Animation) (2 篇)

#题目一句话要点标签🔗⭐
6 EPAM-Net: An Efficient Pose-driven Attention-guided Multimodal Network for Video Action Recognition 提出EPAM-Net，一种高效的姿态驱动注意力引导多模态网络，用于视频动作识别。 spatiotemporal multimodal ✅
7 A Methodological and Structural Review of Hand Gesture Recognition Across Diverse Data Modalities 综述性研究：对手势识别中不同数据模态的方法与结构进行回顾分析。 spatiotemporal multimodal

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

#题目一句话要点标签🔗⭐
8 DeepFace-Attention: Multimodal Face Biometrics for Attention Estimation with Application to e-Learning 提出DeepFace-Attention，利用多模态面部生物特征进行注意力估计，应用于在线学习。 multimodal
9 How Does Audio Influence Visual Attention in Omnidirectional Videos? Database and Model 提出OmniAVS模型和AVS-ODV数据库，用于全景视频中音视频联合显著性预测。 multimodal

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

#题目一句话要点标签🔗⭐
10 ReToMe-VA: Recursive Token Merging for Video Diffusion-based Unrestricted Adversarial Attack 提出ReToMe-VA，用于视频扩散模型对抗攻击，提升迁移性和不可感知性。 latent optimization

⬅️ 返回 cs.CV 首页 · 🏠 返回主页