cs.CV（2024-04-26）

📊 共 13 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (6 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱三：空间感知与语义 (Perception & Semantics) (2 🔗1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (6 篇)

#题目一句话要点标签🔗⭐
1 FashionSD-X: Multimodal Fashion Garment Synthesis using Latent Diffusion 提出FashionSD-X以解决时尚设计过程中的多模态生成问题 multimodal
2 Dense Road Surface Grip Map Prediction from Multimodal Image Data 提出多模态传感器数据预测道路表面抓地力图以解决滑行风险问题 multimodal
3 Low-Rank Knowledge Decomposition for Medical Foundation Models 提出低秩知识分解以提升医学基础模型在特定任务中的表现 foundation model
4 MovieChat+: Question-aware Sparse Memory for Long Video Question Answering 提出MovieChat+以解决长视频问答中的稀疏记忆问题 large language model foundation model ✅
5 Exploring the Distinctiveness and Fidelity of the Descriptions Generated by Large Vision-Language Models 提出TRAC框架以提升大型视觉语言模型的描述生成能力 multimodal
6 UniRGB-IR: A Unified Framework for Visible-Infrared Semantic Tasks via Adapter Tuning 提出UniRGB-IR以解决RGB-IR语义任务的可扩展性问题 foundation model

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
7 A Novel Spike Transformer Network for Depth Estimation from Event Cameras via Cross-modality Knowledge Distillation 提出Spike-Driven Transformer网络以解决事件相机深度估计问题 distillation depth estimation foundation model
8 Optimizing Universal Lesion Segmentation: State Space Model-Guided Hierarchical Networks with Feature Importance Adjustment 提出Mamba-Ahnet以解决医学影像语义分割中的特征重要性动态调整问题 Mamba SSM state space model
9 Sparse Reconstruction of Optical Doppler Tomography with Alternative State Space Model and Attention 提出稀疏ODT重建框架以解决扫描时间和存储需求问题 SSM state space model
10 Generative Dataset Distillation: Balancing Global Structure and Local Details 提出一种新型数据集蒸馏方法以平衡全局结构与局部细节 distillation

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

#题目一句话要点标签🔗⭐
11 Camera Motion Estimation from RGB-D-Inertial Scene Flow 提出一种新方法通过场景流融合RGB-D与惯性数据进行相机运动估计 scene flow motion estimation
12 Geometry-aware Reconstruction and Fusion-refined Rendering for Generalizable Neural Radiance Fields 提出几何感知重建与融合精细渲染以解决神经辐射场的泛化问题 NeRF neural radiance field ✅

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
13 MCSDNet: Mesoscale Convective System Detection Network via Multi-scale Spatiotemporal Information 提出MCSDNet以解决中尺度对流系统检测问题 spatiotemporal

⬅️ 返回 cs.CV 首页 · 🏠 返回主页