cs.CV（2024-04-12）

📊 共 25 篇论文 | 🔗 10 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (10 🔗6) 支柱三：空间感知与语义 (Perception & Semantics) (9 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1) 支柱一：机器人控制 (Robot Control) (1) 支柱六：视频提取与匹配 (Video Extraction) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (10 篇)

#题目一句话要点标签🔗⭐
1 LLM-Seg: Bridging Image Segmentation and Large Language Model Reasoning 提出LLM-Seg以解决图像分割与大语言模型推理的结合问题 large language model ✅
2 Probing the 3D Awareness of Visual Foundation Models 分析视觉基础模型的三维感知能力 foundation model ✅
3 Pathological Primitive Segmentation Based on Visual Foundation Model with Zero-Shot Mask Generation 提出基于视觉基础模型的病理原始分割以解决病理图像处理问题 foundation model ✅
4 Vision-Aware Text Features in Referring Image Segmentation: From Object Understanding to Context Understanding 提出视觉感知文本特征以提升图像分割任务的理解能力 multimodal
5 FashionFail: Addressing Failure Cases in Fashion Object Detection and Segmentation 提出FashionFail以解决时尚物体检测与分割中的失败案例问题 foundation model ✅
6 Lossy Image Compression with Foundation Diffusion Models 提出基于扩散模型的有损图像压缩方法以解决低比特率重建问题 foundation model
7 ChatGPT and general-purpose AI count fruits in pictures surprisingly well 利用基础模型与ChatGPT解决水果计数问题 foundation model
8 LaSagnA: Language-based Segmentation Assistant for Complex Queries 提出LaSagnA以解决复杂查询的语义分割问题 large language model ✅
9 Adapting the Segment Anything Model During Usage in Novel Situations 提出一种框架以适应SAM在新场景中的交互分割问题 foundation model
10 OmniSat: Self-Supervised Modality Fusion for Earth Observation 提出OmniSat以解决地球观测多模态融合问题 multimodal ✅

🔬 支柱三：空间感知与语义 (Perception & Semantics) (9 篇)

#题目一句话要点标签🔗⭐
11 EventEgo3D: 3D Human Motion Capture from Egocentric Event Streams 提出EventEgo3D以解决单目事件相机下的3D人类动作捕捉问题 3D reconstruction egocentric human motion
12 OccGaussian: 3D Gaussian Splatting for Occluded Human Rendering 提出OccGaussian以解决动态3D人类渲染中的遮挡问题 3D gaussian splatting gaussian splatting splatting
13 Pay Attention to Your Neighbours: Training-Free Open-Vocabulary Semantic Segmentation 提出Neighbour-Aware CLIP以解决开放词汇语义分割问题 open-vocabulary open vocabulary foundation model ✅
14 Training-free Boost for Open-Vocabulary Object Detection with Confidence Aggregation 提出无训练增益方法以解决开放词汇目标检测中的置信度聚合问题 open-vocabulary open vocabulary
15 On the Robustness of Language Guidance for Low-Level Vision Tasks: Findings from Depth Estimation 量化语言指导对单目深度估计的影响以提升鲁棒性 depth estimation monocular depth spatial relationship
16 MonoPatchNeRF: Improving Neural Radiance Fields with Patch-based Monocular Guidance 提出MonoPatchNeRF以解决大规模稀疏视图场景的几何精度问题 monocular depth NeRF neural radiance field
17 GPN: Generative Point-based NeRF 提出生成点云NeRF以解决不完整点云重建问题 NeRF
18 Into the Fog: Evaluating Robustness of Multiple Object Tracking 提出物理基础的雾模拟方法以解决多目标跟踪的鲁棒性问题 depth estimation monocular depth
19 Let-It-Flow: Simultaneous Optimization of 3D Flow and Object Clustering 提出一种新型聚类方法以优化3D流动和物体聚类问题 scene flow ✅

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

#题目一句话要点标签🔗⭐
20 TDANet: Target-Directed Attention Network For Object-Goal Visual Navigation With Zero-Shot Ability 提出TDANet以解决物体目标视觉导航的零-shot能力问题 reinforcement learning deep reinforcement learning DRL
21 SpectralMamba: Efficient Mamba for Hyperspectral Image Classification 提出SpectralMamba以解决高光谱图像分类效率问题 Mamba state space model representation learning
22 Generalized Contrastive Learning for Multi-Modal Retrieval and Ranking 提出广义对比学习以解决多模态检索与排序问题 contrastive learning ✅
23 Guided Masked Self-Distillation Modeling for Distributed Multimedia Sensor Event Analysis 提出Guided-MELD以解决分布式传感器事件分析问题 distillation

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
24 Towards Sim-to-Real Industrial Parts Classification with Synthetic Dataset 提出合成数据集以解决工业零件分类中的域间差距问题 sim-to-real domain randomization

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

#题目一句话要点标签🔗⭐
25 3D Human Scan With A Moving Event Camera 提出基于事件相机的3D人体扫描方法以解决动态范围限制问题 human mesh recovery ✅

⬅️ 返回 cs.CV 首页 · 🏠 返回主页