cs.CV（2024-02-29）

📊 共 24 篇论文 | 🔗 9 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (7 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (7 🔗1) 支柱一：机器人控制 (Robot Control) (4 🔗2) 支柱三：空间感知与语义 (Perception & Semantics) (4 🔗3) 支柱七：动作重定向 (Motion Retargeting) (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) (7 篇)

#题目一句话要点标签🔗⭐
1 Percept, Chat, and then Adapt: Multimodal Knowledge Transfer of Foundation Models for Open-World Video Recognition 提出多模态知识转移方法以提升开放世界视频识别性能 foundation model multimodal
2 EAMA : Entity-Aware Multimodal Alignment Based Approach for News Image Captioning 提出EAMA以解决新闻图像字幕生成中的实体信息处理问题 multimodal
3 Aligning Knowledge Graph with Visual Perception for Object-goal Navigation 提出AKGVP方法以解决物体目标导航中的知识图谱与视觉感知对齐问题 multimodal ✅
4 Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers 提出Panda-70M以解决高质量视频文本标注问题 multimodal
5 The All-Seeing Project V2: Towards General Relation Comprehension of the Open World 提出All-Seeing Model V2以解决开放世界中的关系理解问题 large language model ✅
6 Navigating Hallucinations for Reasoning of Unintentional Activities 提出Dream of Thoughts以解决视频中无意活动理解问题 multimodal
7 Unveiling Typographic Deceptions: Insights of the Typographic Vulnerability in Large Vision-Language Model 提出针对大型视觉语言模型的排版攻击防御方法 large language model ✅

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

#题目一句话要点标签🔗⭐
8 PCDepth: Pattern-based Complementary Learning for Monocular Depth Estimation by Best of Both Worlds 提出PCDepth以解决单目深度估计中的模态融合问题 representation learning depth estimation monocular depth
9 MaskFi: Unsupervised Learning of WiFi and Vision Representations for Multimodal Human Activity Recognition 提出MaskFi以解决多模态人类活动识别中的数据标注问题 representation learning multimodal
10 Modality-Agnostic Structural Image Representation Learning for Deformable Multi-Modality Medical Image Registration 提出模态无关的结构图像表示学习以解决多模态医学图像配准问题 representation learning contrastive learning multimodal
11 CricaVPR: Cross-image Correlation-aware Representation Learning for Visual Place Recognition 提出CricaVPR以解决视觉位置识别中的跨图像变异问题 representation learning foundation model ✅
12 VideoMAC: Video Masked Autoencoders Meet ConvNets 提出VideoMAC以解决视频自监督学习中资源消耗问题 representation learning masked autoencoder MAE
13 Enhancing Visual Document Understanding with Contrastive Learning in Large Visual-Language Models 提出DoCo框架以解决视觉文档理解中的细粒度特征崩溃问题 contrastive learning multimodal
14 Continuous Sign Language Recognition Based on Motor attention mechanism and frame-level Self-distillation 提出基于运动注意机制和帧级自蒸馏的连续手语识别方法 distillation

🔬 支柱一：机器人控制 (Robot Control) (4 篇)

#题目一句话要点标签🔗⭐
15 DOZE: A Dataset for Open-Vocabulary Zero-Shot Object Navigation in Dynamic Environments 提出DOZE数据集以解决动态环境下的零样本物体导航问题 humanoid open-vocabulary open vocabulary ✅
16 VIXEN: Visual Text Comparison Network for Image Difference Captioning 提出VIXEN以解决图像差异描述中的内容操控问题 manipulation large language model ✅
17 PrivatEyes: Appearance-based Gaze Estimation Using Federated Secure Multi-Party Computation 提出PrivatEyes以解决隐私风险下的注视估计问题 MPC
18 OHTA: One-shot Hand Avatar via Data-driven Implicit Priors 提出OHTA以解决单图像生成高保真手头像问题 manipulation

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

#题目一句话要点标签🔗⭐
19 Deep learning for 3D human pose estimation and mesh recovery: A survey 综述深度学习在3D人体姿态估计与网格恢复中的应用 implicit representation human mesh recovery HMR ✅
20 WHU-Synthetic: A Synthetic Perception Dataset for 3-D Multitask Model Research 提出WHU-Synthetic数据集以推动3D多任务学习研究 3D reconstruction scene understanding ✅
21 FusionVision: A comprehensive approach of 3D object reconstruction and segmentation from RGB-D cameras using YOLO and fast segment anything 提出FusionVision以解决RGB-D图像中的3D物体重建与分割问题 scene understanding ✅
22 SeMoLi: What Moves Together Belongs Together 提出SeMoLi以解决基于运动线索的半监督目标检测问题 scene flow

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

#题目一句话要点标签🔗⭐
23 Feature boosting with efficient attention for scene parsing 提出高效注意力机制的特征增强网络以解决场景解析问题 spatial relationship

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

#题目一句话要点标签🔗⭐
24 SIFT-Aided Rectified 2D-DIC for Displacement and Strain Measurements in Asphalt Concrete Testing 提出基于SIFT的二维数字图像相关技术以解决非垂直相机对齐问题 feature matching

⬅️ 返回 cs.CV 首页 · 🏠 返回主页