cs.CV(2024-10-05)

📊 共 6 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱二:RL算法与架构 (RL & Architecture) (2 🔗1) 支柱九:具身大模型 (Embodied Foundation Models) (2) 支柱三:空间感知与语义 (Perception & Semantics) (1) 支柱一:机器人控制 (Robot Control) (1)

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

#题目一句话要点标签🔗
1 Gap Preserving Distillation by Building Bidirectional Mappings with A Dynamic Teacher 提出Gap Preserving Distillation,通过动态教师模型和双向映射缩小师生差距,提升知识蒸馏效果。 distillation
2 Mamba Capsule Routing Towards Part-Whole Relational Camouflaged Object Detection 提出基于Mamba胶囊路由的伪装目标检测方法,有效提升分割完整性。 Mamba

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

#题目一句话要点标签🔗
3 Transformers Utilization in Chart Understanding: A Review of Recent Advances & Future Trends 综述Transformer在图表理解中的应用:回顾最新进展与未来趋势 multimodal
4 Solution for OOD-CV UNICORN Challenge 2024 Object Detection Assistance LLM Counting Ability Improvement 提出ODAC框架,利用目标检测辅助LLM提升OOD场景下的计数能力 large language model

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

#题目一句话要点标签🔗
5 EndoPerfect: High-Accuracy Monocular Depth Estimation and 3D Reconstruction for Endoscopic Surgery via NeRF-Stereo Fusion EndoPerfect:基于NeRF-Stereo融合的高精度单目内窥镜深度估计与3D重建 depth estimation monocular depth NeRF

🔬 支柱一:机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗
6 ForgeryTTT: Zero-Shot Image Manipulation Localization with Test-Time Training ForgeryTTT:利用测试时训练的零样本图像篡改定位方法 manipulation

⬅️ 返回 cs.CV 首页 · 🏠 返回主页