cs.CV(2023-12-29)

📊 共 7 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱三:空间感知与语义 (Perception & Semantics) (4 🔗1) 支柱二:RL算法与架构 (RL & Architecture) (1) 支柱八:物理动画 (Physics-based Animation) (1 🔗1) 支柱九:具身大模型 (Embodied Foundation Models) (1 🔗1)

🔬 支柱三:空间感知与语义 (Perception & Semantics) (4 篇)

#题目一句话要点标签🔗
1 Leveraging Open-Vocabulary Diffusion to Camouflaged Instance Segmentation 利用开放词汇扩散模型解决伪装实例分割问题 open-vocabulary open vocabulary
2 Informative Rays Selection for Few-Shot Neural Radiance Fields KeyNeRF:通过选择关键信息光线,实现NeRF的少样本学习 NeRF neural radiance field
3 Generating Enhanced Negatives for Training Language-Based Object Detectors 提出利用生成模型增强负样本,提升基于语言的开放词汇目标检测器性能 open-vocabulary open vocabulary large language model
4 FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis FlowVid:利用不完美光流实现一致的视频到视频合成 optical flow

🔬 支柱二:RL算法与架构 (RL & Architecture) (1 篇)

#题目一句话要点标签🔗
5 Bridging Modality Gap for Visual Grounding with Effecitve Cross-modal Distillation 提出EpmVG框架,通过跨模态蒸馏弥合视觉定位中的模态差异。 distillation multimodal visual grounding

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

#题目一句话要点标签🔗
6 Video Understanding with Large Language Models: A Survey 综述:利用大型语言模型进行视频理解的研究进展与未来方向 spatiotemporal large language model multimodal

🔬 支柱九:具身大模型 (Embodied Foundation Models) (1 篇)

#题目一句话要点标签🔗
7 P2M2-Net: Part-Aware Prompt-Guided Multimodal Point Cloud Completion P2M2-Net:提出Part-Aware Prompt引导的多模态点云补全框架 multimodal

⬅️ 返回 cs.CV 首页 · 🏠 返回主页