cs.CV(2023-12-25)

📊 共 9 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九:具身大模型 (Embodied Foundation Models) (3 🔗2) 支柱三:空间感知与语义 (Perception & Semantics) (2) 支柱二:RL算法与架构 (RL & Architecture) (2 🔗1) 支柱六:视频提取与匹配 (Video Extraction) (2 🔗1)

🔬 支柱九:具身大模型 (Embodied Foundation Models) (3 篇)

#题目一句话要点标签🔗
1 WebVLN: Vision-and-Language Navigation on Websites 提出WebVLN任务与数据集,解决网页环境下的视觉语言导航问题。 VLN
2 UniRef++: Segment Every Reference Object in Spatial and Temporal Spaces UniRef++:统一框架解决基于参考的图像与视频对象分割任务 foundation model
3 Partial Fine-Tuning: A Successor to Full Fine-Tuning for Vision Transformers 提出Partial Fine-Tuning,提升Vision Transformer微调效率与性能 foundation model

🔬 支柱三:空间感知与语义 (Perception & Semantics) (2 篇)

#题目一句话要点标签🔗
4 Open-Vocabulary Video Relation Extraction 提出开放词汇视频关系抽取任务(OVRE),以提升视频动作理解的细粒度。 open-vocabulary open vocabulary
5 3DGR-CT: Sparse-View CT Reconstruction with a 3D Gaussian Representation 提出基于3D高斯表示的3DGR-CT方法,用于解决稀疏视角CT重建中的噪声和伪影问题。 3D gaussian splatting gaussian splatting splatting

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

#题目一句话要点标签🔗
6 A Target Detection Algorithm in Traffic Scenes Based on Deep Reinforcement Learning 提出基于深度强化学习的交通场景目标检测算法,提升检测精度。 reinforcement learning deep reinforcement learning
7 DI-V2X: Learning Domain-Invariant Representation for Vehicle-Infrastructure Collaborative 3D Object Detection 提出DI-V2X,通过领域不变表示学习解决V2X协同3D目标检测中的领域差异问题 distillation scene understanding

🔬 支柱六:视频提取与匹配 (Video Extraction) (2 篇)

#题目一句话要点标签🔗
8 Get a Grip: Reconstructing Hand-Object Stable Grasps in Egocentric Videos 提出HO-SGR任务,重建第一人称视频中手-物稳定抓取帧,并构建EPIC-Grasps数据集。 egocentric
9 Adaptive FSS: A Novel Few-Shot Segmentation Framework via Prototype Enhancement 提出Adaptive FSS,通过原型增强实现高效的小样本分割模型自适应。 feature matching

⬅️ 返回 cs.CV 首页 · 🏠 返回主页