cs.CV（2023-10-17）

📊 共 11 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (5 🔗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) (3 🔗2)

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

#	题目	一句话要点	标签	🔗	⭐
1	Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V	提出Set-of-Mark方法以提升GPT-4V的视觉定位能力	multimodal visual grounding	✅
2	Towards Training-free Open-world Segmentation via Image Prompt Foundation Models	提出无训练开放世界分割方法以解决灵活性不足问题	large language model foundation model
3	Towards Automatic Satellite Images Captions Generation Using Large Language Models	提出自动遥感图像字幕生成方法以解决数据集不足问题	large language model
4	EvalCrafter: Benchmarking and Evaluating Large Video Generation Models	提出EvalCrafter以解决视频生成模型评估不足问题	large language model
5	NICE: Improving Panoptic Narrative Detection and Segmentation with Cascading Collaborative Learning	提出NICE框架以解决全景叙事检测与分割问题	visual grounding	✅

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

#	题目	一句话要点	标签	🔗	⭐
6	Self-Supervised 3D Scene Flow Estimation and Motion Prediction using Local Rigidity Prior	提出自监督学习方法以解决3D场景流估计与运动预测问题	scene flow motion estimation motion prediction
7	FocDepthFormer: Transformer with latent LSTM for Depth Estimation from Focal Stack	提出FocDepthFormer以解决深度估计中焦点堆栈的局限性问题	depth estimation
8	Learning Neural Implicit through Volume Rendering with Attentive Depth Fusion Priors	提出注意力深度融合先验以解决神经隐式表示的深度缺失问题	3D reconstruction implicit representation	✅

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

#	题目	一句话要点	标签	🔗	⭐
9	Unsupervised Pre-Training Using Masked Autoencoders for ECG Analysis	提出无监督预训练方法以提升心电图分析精度	masked autoencoder MAE
10	MonoSKD: General Distillation Framework for Monocular 3D Object Detection via Spearman Correlation Coefficient	提出MonoSKD框架以解决单目3D目标检测中的知识蒸馏问题	distillation	✅
11	Enhancing Plasticity for First Session Adaptation Continual Learning	提出PLASTIC以解决异构任务分布下的持续学习问题	teacher-student distillation	✅

⬅️ 返回 cs.CV 首页 · 🏠 返回主页