cs.CV（2024-09-05）

📊 共 18 篇论文 | 🔗 6 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (6 🔗2) 支柱三：空间感知与语义 (Perception & Semantics) (5 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1) 支柱一：机器人控制 (Robot Control) (2) 支柱四：生成式动作 (Generative Motion) (1 🔗1)

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

#题目一句话要点标签🔗⭐
1 Foundation Model or Finetune? Evaluation of few-shot semantic segmentation for river pollution 针对河流污染语义分割，研究表明微调模型优于Foundation Model foundation model
2 Tissue Concepts: supervised foundation models in computational pathology 提出Tissue Concepts：一种基于监督学习的病理计算领域预训练模型 foundation model
3 Few-shot Adaptation of Medical Vision-Language Models 针对医学视觉-语言模型，提出一种高效的少样本自适应基准与方法。 foundation model zero-shot transfer ✅
4 TC-LLaVA: Rethinking the Transfer from Image to Video Understanding with Temporal Considerations TC-LLaVA：通过时序建模增强LLM，提升图像到视频理解的迁移能力 large language model multimodal
5 MVTN: A Multiscale Video Transformer Network for Hand Gesture Recognition 提出多尺度视频Transformer网络MVTN，用于提升动态手势识别精度。 multimodal ✅
6 Have Large Vision-Language Models Mastered Art History? 评估大型视觉-语言模型在艺术史领域的掌握程度 multimodal

🔬 支柱三：空间感知与语义 (Perception & Semantics) (5 篇)

#题目一句话要点标签🔗⭐
7 LM-Gaussian: Boost Sparse-view 3D Gaussian Splatting with Large Model Priors LM-Gaussian：利用大模型先验提升稀疏视角3D高斯溅射重建效果 3D gaussian splatting 3DGS gaussian splatting
8 FrozenSeg: Harmonizing Frozen Foundation Models for Open-Vocabulary Segmentation FrozenSeg：融合冻结的预训练模型，实现开放词汇分割 open-vocabulary open vocabulary foundation model ✅
9 Lexicon3D: Probing Visual Foundation Models for Complex 3D Scene Understanding Lexicon3D：探究视觉基础模型在复杂3D场景理解中的能力与局限性 scene understanding foundation model visual grounding ✅
10 Weight Conditioning for Smooth Optimization of Neural Networks 提出权重调节方法，通过平滑神经网络优化过程提升模型性能 NeRF neural radiance field
11 Estimating Indoor Scene Depth Maps from Ultrasonic Echoes 提出一种利用可听声辅助训练的超声回声室内场景深度估计方法 depth estimation

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

#题目一句话要点标签🔗⭐
12 Optimizing 3D Gaussian Splatting for Sparse Viewpoint Scene Reconstruction 提出SVS-GS框架，优化3D高斯溅射在稀疏视角下的场景重建 distillation 3D gaussian splatting 3DGS
13 UV-Mamba: A DCN-Enhanced State Space Model for Urban Village Boundary Identification in High-Resolution Remote Sensing Images UV-Mamba：一种DCN增强的状态空间模型，用于高分辨率遥感影像中城中村边界识别 Mamba state space model ✅
14 Data-Efficient Generation for Dataset Distillation 提出基于条件潜在扩散模型的数据集蒸馏方法，提升合成图像质量与蒸馏效率。 distillation
15 Granular-ball Representation Learning for Deep CNN on Learning with Label Noise 提出基于粒球表示学习的深度CNN模型，提升含噪声标签数据下的模型鲁棒性。 representation learning

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
16 OccLLaMA: An Occupancy-Language-Action Generative World Model for Autonomous Driving OccLLaMA：面向自动驾驶的Occupancy-Language-Action生成式世界模型 motion planning world model VQ-VAE
17 Non-Uniform Illumination Attack for Fooling Convolutional Neural Networks 提出非均匀光照攻击（NUI）方法，评估并提升CNN在图像分类任务中的鲁棒性。 manipulation

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
18 HUMOS: Human Motion Model Conditioned on Body Shape 提出HUMOS，基于身体形状生成更真实的人体运动模型，解决现有方法忽略体型差异的问题。 physically plausible ✅

⬅️ 返回 cs.CV 首页 · 🏠 返回主页