cs.CV（2024-01-06）

📊 共 12 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) (4 🔗2) 支柱三：空间感知与语义 (Perception & Semantics) (4 🔗1) 支柱八：物理动画 (Physics-based Animation) (2) 支柱二：RL算法与架构 (RL & Architecture) (1) 支柱六：视频提取与匹配 (Video Extraction) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (4 篇)

#题目一句话要点标签🔗⭐
1 Incorporating Visual Experts to Resolve the Information Loss in Multimodal Large Language Models 提出混合专家机制以解决多模态大语言模型的信息损失问题 large language model multimodal instruction following
2 Multimodal Informative ViT: Information Aggregation and Distribution for Hyperspectral and LiDAR Classification 提出多模态信息聚合分配机制以解决土地覆盖分类中的冗余问题 multimodal ✅
3 CaMML: Context-Aware Multimodal Learner for Large Models 提出CaMML以提升大规模多模态模型的上下文理解能力 multimodal ✅
4 VLLaVO: Mitigating Visual Gap through LLMs 提出VLLaVO以解决视觉领域跨域学习问题 large language model

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

#题目一句话要点标签🔗⭐
5 3DMIT: 3D Multi-modal Instruction Tuning for Scene Understanding 提出3DMIT以解决3D场景理解中的多模态指令调优问题 scene understanding large language model ✅
6 RustNeRF: Robust Neural Radiance Field with Low-Quality Images 提出RustNeRF以解决低质量图像下的NeRF鲁棒性问题 NeRF neural radiance field
7 Hi-Map: Hierarchical Factorized Radiance Field for High-Fidelity Monocular Dense Mapping 提出Hi-Map以解决单目高保真密集映射问题 depth estimation NeRF neural radiance field
8 Group Activity Recognition using Unreliable Tracked Pose 提出RePGARS以解决群体活动识别中的跟踪不可靠问题 optical flow

🔬 支柱八：物理动画 (Physics-based Animation) (2 篇)

#题目一句话要点标签🔗⭐
9 Spatiotemporally adaptive compression for scientific dataset with feature preservation -- a case study on simulation data with extreme climate events analysis 提出时空自适应压缩以解决科学数据存储与分析问题 spatiotemporal
10 An Event-Oriented Diffusion-Refinement Method for Sparse Events Completion 提出事件导向的扩散精炼方法以解决稀疏事件补全问题 spatiotemporal TAMP

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

#题目一句话要点标签🔗⭐
11 Exploiting Data Hierarchy as a New Modality for Contrastive Learning 提出层次对比学习方法以提升自监督学习效果 contrastive learning

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
12 Dress-Me-Up: A Dataset & Method for Self-Supervised 3D Garment Retargeting 提出自监督框架以解决非参数化3D服装重定向问题 SMPL

⬅️ 返回 cs.CV 首页 · 🏠 返回主页