cs.CV（2024-04-14）
📊 共 15 篇论文 | 🔗 2 篇有代码
🎯 兴趣领域导航
支柱三：空间感知与语义 (Perception & Semantics) (5)
支柱二：RL算法与架构 (RL & Architecture) (4 🔗1)
支柱九：具身大模型 (Embodied Foundation Models) (3)
支柱六：视频提取与匹配 (Video Extraction) (1)
支柱一：机器人控制 (Robot Control) (1)
支柱八：物理动画 (Physics-based Animation) (1 🔗1)
🔬 支柱三：空间感知与语义 (Perception & Semantics) (5 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | DetCLIPv3: Towards Versatile Generative Open-vocabulary Object Detection | 提出DetCLIPv3以解决开放词汇物体检测的局限性 | open-vocabulary open vocabulary large language model | ||
| 2 | EGGS: Edge Guided Gaussian Splatting for Radiance Fields | 提出EGGS方法以增强高斯点云渲染中的边缘信息 | 3D reconstruction gaussian splatting splatting | ||
| 3 | VRS-NeRF: Visual Relocalization with Sparse Neural Radiance Field | 提出VRS-NeRF以解决视觉重定位效率与准确性问题 | NeRF neural radiance field | ||
| 4 | DreamScape: 3D Scene Creation via Gaussian Splatting joint Correlation Modeling | 提出DreamScape以解决3D场景生成中的多对象挑战 | gaussian splatting splatting | ||
| 5 | In My Perspective, In My Hands: Accurate Egocentric 2D Hand Pose and Action Recognition | 提出EffHandNet和EffHandEgoNet以解决2D手势识别问题 | depth estimation egocentric |
🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 6 | A Novel State Space Model with Local Enhancement and State Sharing for Image Fusion | 提出LE-Mamba以解决图像融合中的信息建模问题 | Mamba state space model | ✅ | |
| 7 | VideoSAGE: Video Summarization with Graph Representation Learning | 提出基于图表示学习的视频摘要方法以提升效率 | representation learning | ||
| 8 | Fusion-Mamba for Cross-modality Object Detection | 提出Fusion-Mamba以解决跨模态目标检测中的融合性能问题 | Mamba | ||
| 9 | GCC: Generative Calibration Clustering | 提出生成校准聚类方法以解决样本不足问题 | representation learning contrastive learning |
🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 10 | TextHawk: Exploring Efficient Fine-Grained Perception of Multimodal Large Language Models | 提出TextHawk以解决文档导向任务中的细粒度感知问题 | large language model multimodal | ||
| 11 | Face-voice Association in Multilingual Environments (FAME) Challenge 2024 Evaluation Plan | 提出FAME挑战以解决多语言环境下的人脸与声音关联问题 | multimodal | ||
| 12 | Arena: A Patch-of-Interest ViT Inference Acceleration System for Edge-Assisted Video Analytics | 提出Arena系统以加速边缘辅助视频分析中的ViT推理 | foundation model |
🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 13 | TEXT2TASTE: A Versatile Egocentric Vision System for Intelligent Reading Assistance Using Large Language Model | 提出智能阅读助手以解决视力障碍者的信息获取问题 | egocentric egocentric vision large language model |
🔬 支柱一：机器人控制 (Robot Control) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 14 | Exploring Generative AI for Sim2Real in Driving Data Synthesis | 探索生成式AI以解决驾驶数据合成中的Sim2Real问题 | sim2real |
🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 15 | Orientation-conditioned Facial Texture Mapping for Video-based Facial Remote Photoplethysmography Estimation | 提出基于方向条件的面部纹理映射以解决视频rPPG估计中的运动干扰问题 | PULSE | ✅ |