cs.CV(2024-12-01)

📊 共 5 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱二:RL算法与架构 (RL & Architecture) (3 🔗2) 支柱四:生成式动作 (Generative Motion) (1) 支柱三:空间感知与语义 (Perception & Semantics) (1)

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

#题目一句话要点标签🔗
1 MambaNUT: Nighttime UAV Tracking via Mamba-based Adaptive Curriculum Learning 提出基于Mamba的自适应课程学习框架MambaNUT,用于夜间无人机跟踪。 Mamba state space model curriculum learning
2 Towards Unified Molecule-Enhanced Pathology Image Representation Learning via Integrating Spatial Transcriptomics UMPIRE:融合空间转录组学,提升病理图像分子增强表示学习 representation learning multimodal
3 VideoSAVi: Self-Aligned Video Language Models without Human Supervision 提出VideoSAVi,无需人工标注实现视频语言模型的自对齐训练 DPO direct preference optimization large language model

🔬 支柱四:生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗
4 Sketch-Guided Motion Diffusion for Stylized Cinemagraph Synthesis 提出Sketch2Cinemagraph,通过草图引导的运动扩散生成风格化电影图 motion diffusion model motion diffusion

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

#题目一句话要点标签🔗
5 A Lesson in Splats: Teacher-Guided Diffusion for 3D Gaussian Splats Generation with 2D Supervision 提出一种教师引导的扩散模型,仅用2D监督生成3D高斯溅射,提升生成质量。 3DGS

⬅️ 返回 cs.CV 首页 · 🏠 返回主页