cs.CV(2024-01-20)

📊 共 9 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九:具身大模型 (Embodied Foundation Models) (3) 支柱二:RL算法与架构 (RL & Architecture) (3 🔗1) 支柱三:空间感知与语义 (Perception & Semantics) (2 🔗1) 支柱四:生成式动作 (Generative Motion) (1 🔗1)

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

#题目一句话要点标签🔗
1 A Novel Benchmark for Few-Shot Semantic Segmentation in the Era of Foundation Models 提出新基准以解决少样本语义分割问题 foundation model
2 Toward Robust Multimodal Learning using Multimodal Foundational Models 提出TRML框架以解决多模态数据缺失问题 multimodal
3 Prompting Large Vision-Language Models for Compositional Reasoning 提出生成方法以解决视觉语言模型的组合推理问题 multimodal

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

#题目一句话要点标签🔗
4 Unifying Visual and Vision-Language Tracking via Contrastive Learning 提出UVLTrack以统一视觉与视觉语言跟踪问题 contrastive learning visual grounding
5 DengueNet: Dengue Prediction using Spatiotemporal Satellite Imagery for Resource-Limited Countries 提出DengueNet以利用卫星影像预测登革热疫情 MAE spatiotemporal
6 Adaptive Global-Local Representation Learning and Selection for Cross-Domain Facial Expression Recognition 提出自适应全局-局部表示学习与选择框架以解决跨域人脸表情识别问题 representation learning

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

#题目一句话要点标签🔗
7 Pixel-Wise Recognition for Holistic Surgical Scene Understanding 提出GraSP数据集与TAPIS模型以解决外科手术场景理解问题 scene understanding
8 VONet: Unsupervised Video Object Learning With Parallel U-Net Attention and Object-wise Sequential VAE 提出VONet以解决无监督视频对象学习问题 optical flow

🔬 支柱四:生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗
9 MotionMix: Weakly-Supervised Diffusion for Controllable Motion Generation 提出MotionMix以解决高质量动作生成的资源依赖问题 text-to-motion motion generation human motion

⬅️ 返回 cs.CV 首页 · 🏠 返回主页