cs.CV（2024-01-08）
📊 共 14 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) (6 🔗3)
支柱九：具身大模型 (Embodied Foundation Models) (5 🔗1)
支柱三：空间感知与语义 (Perception & Semantics) (3)
🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | Efficient Multiscale Multimodal Bottleneck Transformer for Audio-Video Classification | 提出多尺度多模态瓶颈变换器以解决音视频分类问题 | representation learning multimodal | ||
| 2 | Efficient Selective Audio Masked Multimodal Bottleneck Transformer for Audio-Video Classification | 提出音频视频瓶颈变换器以提升多模态分类精度 | contrastive learning multimodal | ||
| 3 | AGG: Amortized Generative 3D Gaussians for Single Image to 3D | 提出AGG框架以解决单图像生成3D高斯模型的优化挑战 | distillation 3D gaussian splatting 3D reconstruction | ✅ | |
| 4 | Slot Structured World Models | 提出Slot结构化世界模型以解决对象中心表示不足问题 | world model world models | ✅ | |
| 5 | FMA-Net: Flow-Guided Dynamic Filtering and Iterative Feature Refinement with Multi-Attention for Joint Video Super-Resolution and Deblurring | 提出FMA-Net以解决视频超分辨率与去模糊联合恢复问题 | representation learning motion representation | ✅ | |
| 6 | Two-stream joint matching method based on contrastive learning for few-shot action recognition | 提出基于对比学习的双流联合匹配方法以解决少样本动作识别问题 | contrastive learning |
🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 7 | RudolfV: A Foundation Model by Pathologists for Pathologists | 提出RudolfV以解决病理学AI模型的泛化与应用问题 | foundation model | ||
| 8 | A multimodal gesture recognition dataset for desktop human-computer interaction | 提出GR4DHCI数据集以解决桌面级手势识别数据匮乏问题 | multimodal | ||
| 9 | FM-AE: Frequency-masked Multimodal Autoencoder for Zinc Electrolysis Plate Contact Abnormality Detection | 提出FM-AE以解决锌电解板接触异常检测问题 | multimodal | ||
| 10 | Aligned with LLM: a new multi-modal training paradigm for encoding fMRI activity in visual cortex | 提出多模态训练范式以增强视觉皮层fMRI活动编码 | large language model | ||
| 11 | Low-light Image Enhancement via CLIP-Fourier Guided Wavelet Diffusion | 提出CLIP-傅里叶引导小波扩散以解决低光照图像增强问题 | multimodal | ✅ |
🔬 支柱三：空间感知与语义 (Perception & Semantics) (3 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 12 | A Survey on 3D Gaussian Splatting | 提出3D高斯点云技术以解决实时渲染与可编辑性问题 | 3D gaussian splatting 3D reconstruction gaussian splatting | ||
| 13 | NeRFmentation: NeRF-based Augmentation for Monocular Depth Estimation | 提出NeRFmentation以解决单目深度估计数据不足问题 | depth estimation monocular depth NeRF | ||
| 14 | FunnyNet-W: Multimodal Learning of Funny Moments in Videos in the Wild | 提出FunnyNet-W以解决视频中幽默时刻自动识别问题 | scene understanding large language model multimodal |