cs.CV（2023-11-25）

📊 共 10 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (5 🔗2) 支柱一：机器人控制 (Robot Control) (1) 支柱二：RL算法与架构 (RL & Architecture) (1) 支柱五：交互与反应 (Interaction & Reaction) (1 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)

#题目一句话要点标签🔗⭐
1 Can SAM recognize crops? Quantifying the zero-shot performance of a semantic segmentation foundation model on generating crop-type maps using satellite imagery for precision agriculture 利用SAM模型实现精准农业中的作物类型地图生成 foundation model
2 Parkinson's Disease Classification Using Contrastive Graph Cross-View Learning with Multimodal Fusion of SPECT Images and Clinical Features 提出多模态融合方法以提高帕金森病分类精度 multimodal
3 Mug-STAN: Adapting Image-Language Pretrained Models for General Video Understanding 提出Mug-STAN以解决视频理解中的图像语言模型适应性问题 multimodal ✅
4 VSCode: General Visual Salient and Camouflaged Object Detection with 2D Prompt Learning 提出VSCode以解决显著与伪装物体检测问题 foundation model ✅
5 LANS: A Layout-Aware Neural Solver for Plane Geometry Problem 提出LANS以解决平面几何问题的挑战 multimodal

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
6 GPT4Video: A Unified Multimodal Large Language Model for lnstruction-Followed Understanding and Safety-Aware Generation 提出GPT4Video以解决多模态内容生成不足问题 humanoid large language model multimodal

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#题目一句话要点标签🔗⭐
7 Elucidating and Overcoming the Challenges of Label Noise in Supervised Contrastive Learning 提出D-SCL以解决监督对比学习中的标签噪声问题 representation learning contrastive learning

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#题目一句话要点标签🔗⭐
8 Automatic Synthetic Data and Fine-grained Adaptive Feature Alignment for Composed Person Retrieval 提出合成数据与细粒度自适应特征对齐以解决组合人检索问题 ReMoS multimodal ✅

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
9 Multi-task Planar Reconstruction with Feature Warping Guidance 提出SOLOPlanes以解决实时平面重建与语义预测问题 3D reconstruction scene understanding

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
10 View-Based Luminance Mapping in Open Workplace 提出一种新方法以优化开放工作场所的日光表现 penetration

⬅️ 返回 cs.CV 首页 · 🏠 返回主页