cs.CV(2024-05-02)

📊 共 11 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) (5 🔗1) 支柱二:RL算法与架构 (RL & Architecture) (4 🔗1) 支柱四:生成式动作 (Generative Motion) (1) 支柱六:视频提取与匹配 (Video Extraction) (1)

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

#题目一句话要点标签🔗
1 MiniGPT-3D: Efficiently Aligning 3D Point Clouds with Large Language Models using 2D Priors 提出MiniGPT-3D以高效对齐3D点云与大语言模型 large language model
2 Language-Enhanced Latent Representations for Out-of-Distribution Detection in Autonomous Driving 提出基于语言增强的潜在表征,用于自动驾驶中的OOD检测 foundation model multimodal
3 Transformer-Aided Semantic Communications 提出基于Transformer的语义通信框架,提升带宽受限场景下的图像传输质量。 large language model
4 MANTIS: Interleaved Multi-Image Instruction Tuning MANTIS:通过交错多图指令微调提升多模态大模型的多图理解能力 multimodal
5 Teaching Human Behavior Improves Content Understanding Abilities Of LLMs 利用人类行为反馈提升大语言模型的内容理解能力 large language model

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

#题目一句话要点标签🔗
6 SSUMamba: Spatial-Spectral Selective State Space Model for Hyperspectral Image Denoising 提出SSUMamba,用于高光谱图像去噪,兼顾长程依赖建模与计算效率。 Mamba SSM state space model
7 SOAR: Advancements in Small Body Object Detection for Aerial Imagery Using State Space Models and Programmable Gradients 提出基于状态空间模型和可编程梯度的SOAR方法,提升航空影像中小目标检测性能。 Mamba SSM state space model
8 ATOM: Attention Mixer for Efficient Dataset Distillation 提出ATOM:一种用于高效数据集蒸馏的注意力混合模块 distillation feature matching
9 Goal-conditioned reinforcement learning for ultrasound navigation guidance 提出基于对比学习的目标条件强化学习方法,用于超声导航引导。 reinforcement learning contrastive learning

🔬 支柱四:生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗
10 SATO: Stable Text-to-Motion Framework 提出SATO框架,解决文本到动作生成中语义相似文本输入导致动作不稳定的问题 text-to-motion

🔬 支柱六:视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗
11 Sparse multi-view hand-object reconstruction for unseen environments 提出SVHO模型,用于稀疏多视角下未见物体的三维手-物体重建 hand-object reconstruction

⬅️ 返回 cs.CV 首页 · 🏠 返回主页