cs.CV（2024-03-06）

📊 共 19 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (7 🔗2) 支柱三：空间感知与语义 (Perception & Semantics) (5) 支柱一：机器人控制 (Robot Control) (3 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (3) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)

#题目一句话要点标签🔗⭐
1 Multi-Grained Cross-modal Alignment for Learning Open-vocabulary Semantic Segmentation from Text Supervision 提出多粒度跨模态对齐框架以解决开放词汇语义分割问题 contrastive learning open-vocabulary open vocabulary
2 MedMamba: Vision Mamba for Medical Image Classification 提出MedMamba以解决医疗图像分类中的长程依赖问题 Mamba SSM state space model ✅
3 Causality-based Cross-Modal Representation Learning for Vision-and-Language Navigation 提出CausalVLN以解决视觉与语言导航中的偏差关联问题 representation learning VLN
4 Contrastive Learning of Person-independent Representations for Facial Action Unit Detection 提出对比学习方法以解决面部动作单元检测的数据稀缺问题 representation learning contrastive learning
5 Unlocking Dataset Distillation with Diffusion Models 提出LD3M方法以解决数据集蒸馏中的梯度消失问题 distillation ✅
6 Dcl-Net: Dual Contrastive Learning Network for Semi-Supervised Multi-Organ Segmentation 提出Dcl-Net以解决半监督多脏器分割问题 contrastive learning
7 LoDisc: Learning Global-Local Discriminative Features for Self-Supervised Fine-Grained Visual Recognition 提出LoDisc框架以解决细粒度视觉识别中的特征学习问题 representation learning contrastive learning

🔬 支柱三：空间感知与语义 (Perception & Semantics) (5 篇)

#题目一句话要点标签🔗⭐
8 GSNeRF: Generalizable Semantic Neural Radiance Fields with Enhanced 3D Scene Understanding 提出GSNeRF以解决3D场景理解与图像合成问题 NeRF neural radiance field scene understanding
9 Popeye: A Unified Visual-Language Model for Multi-Source Ship Detection from Remote Sensing Imagery 提出Popeye以解决多源遥感图像船舶检测问题 open-vocabulary open vocabulary large language model
10 Scene Depth Estimation from Traditional Oriental Landscape Paintings 提出双阶段图像转换框架以解决东方山水画深度估计问题 depth estimation
11 DART: Implicit Doppler Tomography for Radar Novel View Synthesis 提出DART以解决雷达扫描模拟的挑战 neural radiance field
12 HDRFlow: Real-Time HDR Video Reconstruction with Large Motions 提出HDRFlow以解决大运动下的实时HDR视频重建问题 optical flow

🔬 支柱一：机器人控制 (Robot Control) (3 篇)

#题目一句话要点标签🔗⭐
13 HMD-Poser: On-Device Real-time Human Motion Tracking from Scalable Sparse Observations 提出HMD-Poser以解决独立VR头显的人体运动实时跟踪问题 motion tracking human motion ✅
14 Self-supervised Photographic Image Layout Representation Learning 提出自监督学习方法以优化摄影图像布局表示 manipulation representation learning
15 Investigation of the Impact of Synthetic Training Data in the Industrial Application of Terminal Strip Object Detection 提出合成训练数据生成方法以解决工业终端条形物体检测问题 sim-to-real

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

#题目一句话要点标签🔗⭐
16 Are Language Models Puzzle Prodigies? Algorithmic Puzzles Unveil Serious Challenges in Multimodal Reasoning 提出多模态拼图求解任务以评估语言模型的推理能力 large language model multimodal
17 Multimodal Transformer for Comics Text-Cloze 提出多模态Transformer以解决漫画文本填空问题 large language model multimodal
18 Enhancing chest X-ray datasets with privacy-preserving large language models and multi-type annotations: a data-driven approach for improved classification 提出MAPLEZ以解决胸部X光报告标签质量不足问题 large language model

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
19 Temporal Enhanced Floating Car Observers 提出时序增强浮动车观察者以提升交通数据收集精度 penetration spatiotemporal

⬅️ 返回 cs.CV 首页 · 🏠 返回主页