cs.CV（2024-02-14）

📊 共 13 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱三：空间感知与语义 (Perception & Semantics) (6 🔗3) 支柱八：物理动画 (Physics-based Animation) (2 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (1) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱九：具身大模型 (Embodied Foundation Models) (1) 支柱六：视频提取与匹配 (Video Extraction) (1 🔗1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱三：空间感知与语义 (Perception & Semantics) (6 篇)

#题目一句话要点标签🔗⭐
1 DUDF: Differentiable Unsigned Distance Fields with Hyperbolic Scaling 提出超曲率缩放的无符号距离场以解决3D重建问题 3D reconstruction
2 PC-NeRF: Parent-Child Neural Radiance Fields Using Sparse LiDAR Frames in Autonomous Driving Environments 提出PC-NeRF以解决稀疏LiDAR帧下的3D场景重建问题 3D reconstruction NeRF neural radiance field ✅
3 Open-Vocabulary Segmentation with Unpaired Mask-Text Supervision 提出Unpair-Seg以解决开放词汇分割中的标注成本问题 open-vocabulary open vocabulary
4 HaLo-NeRF: Learning Geometry-Guided Semantics for Exploring Unconstrained Photo Collections 提出HaLo-NeRF以解决无约束照片集合的语义理解问题 NeRF large language model ✅
5 Moving Object Proposals with Deep Learned Optical Flow for Video Object Segmentation 提出深度学习光流的移动物体提议以解决视频物体分割问题 scene understanding optical flow
6 Depth-aware Volume Attention for Texture-less Stereo Matching 提出深度感知体积注意力以解决无纹理立体匹配问题 depth estimation ✅

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

#题目一句话要点标签🔗⭐
7 Fast Window-Based Event Denoising with Spatiotemporal Correlation Enhancement 提出基于窗口的事件去噪方法以解决实时处理难题 spatiotemporal
8 TDViT: Temporal Dilated Video Transformer for Dense Video Tasks 提出TDViT以解决稠密视频任务中的长程时间依赖问题 spatiotemporal ✅

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

#题目一句话要点标签🔗⭐
9 Advancing Human Action Recognition with Foundation Models trained on Unlabeled Public Videos 利用无标签公共视频推动人类动作识别的进展 masked autoencoder MAE foundation model

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
10 Weatherproofing Retrieval for Localization with Generative AI and Geometric Consistency 提出生成AI与几何一致性结合的检索方法以提升定位精度 geometric consistency

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

#题目一句话要点标签🔗⭐
11 Headset: Human emotion awareness under partial occlusions multimodal dataset 提出HEADSET多模态数据集以解决情感识别中的遮挡问题 multimodal

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

#题目一句话要点标签🔗⭐
12 Comment-aided Video-Language Alignment via Contrastive Pre-training for Short-form Video Humor Detection 提出Comment-aided Video-Language Alignment以解决短视频幽默检测问题 HuMoR ✅

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
13 DivaTrack: Diverse Bodies and Motions from Acceleration-Enhanced Three-Point Trackers 提出DivaTrack以解决全身姿态推断问题 locomotion

⬅️ 返回 cs.CV 首页 · 🏠 返回主页