cs.CV（2023-10-01）

📊 共 14 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) (6 🔗3) 支柱三：空间感知与语义 (Perception & Semantics) (3) 支柱一：机器人控制 (Robot Control) (2) 支柱二：RL算法与架构 (RL & Architecture) (1 🔗1) 支柱五：交互与反应 (Interaction & Reaction) (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) (6 篇)

#题目一句话要点标签🔗⭐
1 Reformulating Vision-Language Foundation Models and Datasets Towards Universal Multimodal Assistants 提出Muffin框架和UniMM-Chat数据集以提升多模态助手性能 large language model foundation model multimodal ✅
2 HOH: Markerless Multimodal Human-Object-Human Handover Dataset with Large Object Count 提出HOH数据集以解决无标记人机交互中的物体交接问题 multimodal
3 RegBN: Batch Normalization of Multimodal Data with Regularization 提出RegBN以解决多模态数据归一化问题 multimodal ✅
4 LiveChat: Video Comment Generation from Audio-Visual Multimodal Contexts 提出LiveChat以解决视频直播评论生成问题 multimodal
5 Propagating Semantic Labels in Video Data 提出视频数据语义标签传播方法以减少手动标注工作量 foundation model
6 Pink: Unveiling the Power of Referential Comprehension for Multi-modal LLMs 提出新框架以提升多模态大语言模型的细粒度图像理解能力 large language model ✅

🔬 支柱三：空间感知与语义 (Perception & Semantics) (3 篇)

#题目一句话要点标签🔗⭐
7 Multi-tiling Neural Radiance Field (NeRF) -- Geometric Assessment on Large-scale Aerial Datasets 提出多切片神经辐射场以解决大规模航空数据集的几何评估问题 3D reconstruction NeRF neural radiance field
8 Logical Bias Learning for Object Relation Prediction 提出基于因果推理的逻辑偏见学习以改善对象关系预测 scene understanding foundation model
9 Win-Win: Training High-Resolution Vision Transformers from Two Windows 提出Win-Win方法以高效训练高分辨率视觉变换器 monocular depth optical flow

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
10 A Hierarchical Graph-based Approach for Recognition and Description Generation of Bimanual Actions in Videos 提出层次图模型以提升双手动作视频的识别与描述生成 manipulation bi-manual
11 GhostEncoder: Stealthy Backdoor Attacks with Dynamic Triggers to Pre-trained Encoders in Self-supervised Learning 提出GhostEncoder以解决自监督学习中的隐形后门攻击问题 manipulation

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

#题目一句话要点标签🔗⭐
12 Beyond Task Performance: Evaluating and Reducing the Flaws of Large Multimodal Models with In-Context Learning 提出多模态ICL变体以解决大型多模态模型的局限性 RLHF generalist agent large language model ✅

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#题目一句话要点标签🔗⭐
13 Scene-aware Human Motion Forecasting via Mutual Distance Prediction 提出基于互距预测的场景感知人类动作预测方法 human-scene interaction human motion

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

#题目一句话要点标签🔗⭐
14 Comics for Everyone: Generating Accessible Text Descriptions for Comic Strips 提出可访问的漫画文本描述生成方法以解决视觉障碍者的阅读问题 HuMoR large language model multimodal

⬅️ 返回 cs.CV 首页 · 🏠 返回主页