cs.CV（2024-01-04）

📊 共 16 篇论文 | 🔗 9 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (6 🔗5) 支柱一：机器人控制 (Robot Control) (4 🔗2) 支柱三：空间感知与语义 (Perception & Semantics) (3 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (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 ChartAssisstant: A Universal Chart Multimodal Language Model via Chart-to-Table Pre-training and Multitask Instruction Tuning 提出ChartAssistant以解决通用图表理解与推理问题 multimodal instruction following ✅
2 SyCoCa: Symmetrizing Contrastive Captioners with Attentive Masking for Multimodal Alignment 提出SyCoCa以解决多模态对齐问题 multimodal
3 Learning to Prompt with Text Only Supervision for Vision-Language Models 提出仅用文本监督学习提示以提升视觉语言模型的泛化能力 large language model zero-shot transfer ✅
4 ClassWise-SAM-Adapter: Parameter Efficient Fine-tuning Adapts Segment Anything to SAR Domain for Semantic Segmentation 提出ClassWise-SAM-Adapter以解决SAR图像语义分割问题 foundation model ✅
5 Explore Human Parsing Modality for Action Recognition 提出EPP-Net以解决多模态动作识别中的噪声问题 multimodal ✅
6 Improved Zero-Shot Classification by Adapting VLMs with Text Descriptions 通过适应VLMs与文本描述改善零样本分类性能 large language model ✅

🔬 支柱一：机器人控制 (Robot Control) (4 篇)

#题目一句话要点标签🔗⭐
7 Demonstration of an Adversarial Attack Against a Multimodal Vision Language Model for Pathology Imaging 揭示多模态视觉语言模型在病理影像中的脆弱性 manipulation foundation model multimodal ✅
8 VASE: Object-Centric Appearance and Shape Manipulation of Real Videos 提出VASE框架以实现视频中对象外观与形状的精确操控 manipulation ✅
9 Learning the 3D Fauna of the Web 提出3D-Fauna以解决动物三维建模数据不足问题 quadruped
10 SuperEdge: Towards a Generalization Model for Self-Supervised Edge Detection 提出SuperEdge以解决自监督边缘检测中的标注依赖问题 biped

🔬 支柱三：空间感知与语义 (Perception & Semantics) (3 篇)

#题目一句话要点标签🔗⭐
11 PEGASUS: Physically Enhanced Gaussian Splatting Simulation System for 6DoF Object Pose Dataset Generation 提出PEGASUS以生成6DoF物体姿态数据集 3D gaussian splatting gaussian splatting splatting
12 OptFlow: Fast Optimization-based Scene Flow Estimation without Supervision 提出OptFlow以解决无监督场景流估计问题 scene flow
13 An Open and Comprehensive Pipeline for Unified Object Grounding and Detection 提出MM-Grounding-DINO以解决Grounding-DINO模型细节缺失问题 open-vocabulary open vocabulary ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
14 3D Open-Vocabulary Panoptic Segmentation with 2D-3D Vision-Language Distillation 提出一种新方法解决3D开放词汇全景分割问题 distillation open-vocabulary open vocabulary
15 Distillation-based fabric anomaly detection 提出基于蒸馏的织物异常检测方法以解决无监督检测问题 distillation

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
16 GUESS:GradUally Enriching SyntheSis for Text-Driven Human Motion Generation 提出GUESS以解决文本驱动的人体动作生成问题 motion synthesis motion generation human motion ✅

⬅️ 返回 cs.CV 首页 · 🏠 返回主页