cs.CV（2024-02-08）

📊 共 14 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱三：空间感知与语义 (Perception & Semantics) (5 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (4 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱一：机器人控制 (Robot Control) (1 🔗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 CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion 提出CREMA以解决多模态视频推理的灵活性与效率问题 optical flow multimodal
2 InstaGen: Enhancing Object Detection by Training on Synthetic Dataset 提出InstaGen以通过合成数据集增强目标检测能力 open-vocabulary open vocabulary ✅
3 NCRF: Neural Contact Radiance Fields for Free-Viewpoint Rendering of Hand-Object Interaction 提出NCRF以解决手与物体交互的渲染质量问题 neural radiance field hand-object reconstruction
4 Adaptive Surface Normal Constraint for Geometric Estimation from Monocular Images 提出自适应表面法线约束以解决单目图像几何估计问题 depth estimation
5 Extending 6D Object Pose Estimators for Stereo Vision 提出基于立体视觉的6D物体姿态估计方法以解决姿态模糊问题 6D pose estimation

🔬 支柱九：具身大模型 (Embodied Foundation Models) (4 篇)

#题目一句话要点标签🔗⭐
6 SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Models 提出SPHINX-X以提升多模态大语言模型的效率与性能 large language model multimodal ✅
7 Question Aware Vision Transformer for Multimodal Reasoning 提出QA-ViT以解决视觉编码与用户查询脱节问题 large language model multimodal
8 Text Role Classification in Scientific Charts Using Multimodal Transformers 提出多模态变换器以解决科学图表中的文本角色分类问题 multimodal ✅
9 Enhancing Zero-shot Counting via Language-guided Exemplar Learning 提出ExpressCount以解决零-shot计数问题 large language model

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

#题目一句话要点标签🔗⭐
10 Mamba-ND: Selective State Space Modeling for Multi-Dimensional Data 提出Mamba-ND以解决多维数据建模的计算复杂性问题 Mamba state space model
11 Task-customized Masked AutoEncoder via Mixture of Cluster-conditional Experts 提出基于混合聚类条件专家的MAE以解决下游任务定制问题 masked autoencoder MAE
12 Joint End-to-End Image Compression and Denoising: Leveraging Contrastive Learning and Multi-Scale Self-ONNs 提出多尺度自组织神经网络以解决图像压缩与去噪问题 contrastive learning

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
13 Real-time Holistic Robot Pose Estimation with Unknown States 提出实时机器人姿态估计方法以解决未知状态问题 sim-to-real ✅

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

#题目一句话要点标签🔗⭐
14 MTSA-SNN: A Multi-modal Time Series Analysis Model Based on Spiking Neural Network 提出MTSA-SNN以解决复杂时间序列分析问题 PULSE ✅

⬅️ 返回 cs.CV 首页 · 🏠 返回主页