cs.CV(2024-04-13)
📊 共 11 篇论文 | 🔗 1 篇有代码
🎯 兴趣领域导航
支柱九:具身大模型 (Embodied Foundation Models) (4)
支柱三:空间感知与语义 (Perception & Semantics) (3 🔗1)
支柱八:物理动画 (Physics-based Animation) (3)
支柱二:RL算法与架构 (RL & Architecture) (1)
🔬 支柱九:具身大模型 (Embodied Foundation Models) (4 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | MMA-DFER: MultiModal Adaptation of unimodal models for Dynamic Facial Expression Recognition in-the-wild | 提出多模态适应方法以提升动态面部表情识别性能 | multimodal | ||
| 2 | Understanding Multimodal Deep Neural Networks: A Concept Selection View | 提出概念选择模型以解决多模态深度神经网络可解释性问题 | multimodal | ||
| 3 | Trustworthy Multimodal Fusion for Sentiment Analysis in Ordinal Sentiment Space | 提出可信多模态融合网络以解决情感分析中的不确定性问题 | multimodal | ||
| 4 | EIVEN: Efficient Implicit Attribute Value Extraction using Multimodal LLM | 提出EIVEN以解决多模态隐式属性值提取问题 | multimodal |
🔬 支柱三:空间感知与语义 (Perception & Semantics) (3 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 5 | LoopGaussian: Creating 3D Cinemagraph with Multi-view Images via Eulerian Motion Field | 提出LoopGaussian以解决2D图像空间限制问题 | 3D gaussian splatting gaussian splatting splatting | ✅ | |
| 6 | Probabilistic Directed Distance Fields for Ray-Based Shape Representations | 提出概率导向距离场以解决3D形状表示的渲染效率问题 | 3D reconstruction implicit representation | ||
| 7 | Rethinking Iterative Stereo Matching from Diffusion Bridge Model Perspective | 提出扩散桥模型视角下的迭代立体匹配方法以解决信息损失问题 | scene flow |
🔬 支柱八:物理动画 (Physics-based Animation) (3 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 8 | A Lightweight Spatiotemporal Network for Online Eye Tracking with Event Camera | 提出轻量级时空网络以解决在线眼动追踪问题 | spatiotemporal | ||
| 9 | Exploring Explainability in Video Action Recognition | 提出Video-TCAV以解决视频动作识别的可解释性问题 | spatiotemporal | ||
| 10 | PNeRV: Enhancing Spatial Consistency via Pyramidal Neural Representation for Videos | 提出PNeRV以解决视频空间一致性问题 | spatiotemporal |
🔬 支柱二:RL算法与架构 (RL & Architecture) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 11 | PracticalDG: Perturbation Distillation on Vision-Language Models for Hybrid Domain Generalization | 提出Perturbation Distillation以解决视觉语言模型在混合领域泛化中的不足问题 | distillation |