cs.CV（2024-05-04）

📊 共 6 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (2) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Large Language Models estimate fine-grained human color-concept associations	利用大型语言模型GPT-4评估细粒度的人类颜色-概念关联	large language model multimodal
2	Enhancing Vision-Language Models Generalization via Diversity-Driven Novel Feature Synthesis	提出LDFS，通过多样性驱动的新特征合成增强视觉-语言模型泛化能力	foundation model

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

#	题目	一句话要点	标签	🔗	⭐
3	Hand-Object Interaction Controller (HOIC): Deep Reinforcement Learning for Reconstructing Interactions with Physics	提出HOIC，利用深度强化学习和物理引擎重建手-物交互	reinforcement learning deep reinforcement learning	✅
4	MMEarth: Exploring Multi-Modal Pretext Tasks For Geospatial Representation Learning	MMEarth：面向地理空间表征学习的多模态预训练任务探索	representation learning masked autoencoder MAE

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
5	UnSAMFlow: Unsupervised Optical Flow Guided by Segment Anything Model	UnSAMFlow：利用SAM引导的无监督光流估计，提升运动边界精度	optical flow foundation model

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
6	Deep Pulse-Signal Magnification for remote Heart Rate Estimation in Compressed Videos	提出脉冲信号放大方法，提升压缩视频中远程心率估计的准确性	PULSE

⬅️ 返回 cs.CV 首页 · 🏠 返回主页