cs.CV（2024-03-05）

📊 共 19 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (11 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱六：视频提取与匹配 (Video Extraction) (2) 支柱三：空间感知与语义 (Perception & Semantics) (2) 支柱七：动作重定向 (Motion Retargeting) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (11 篇)

#题目一句话要点标签🔗⭐
1 Feast Your Eyes: Mixture-of-Resolution Adaptation for Multimodal Large Language Models 提出混合分辨率适应方法以提升多模态大语言模型的视觉识别能力 large language model multimodal ✅
2 Finetuned Multimodal Language Models Are High-Quality Image-Text Data Filters 提出基于微调多模态语言模型的高质量图文数据过滤方法 foundation model multimodal
3 MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer 提出MADTP以解决视觉语言Transformer的动态令牌修剪问题 multimodal
4 Multi-modal Instruction Tuned LLMs with Fine-grained Visual Perception 提出AnyRef以解决多模态细粒度视觉感知问题 large language model multimodal
5 ChatGPT and biometrics: an assessment of face recognition, gender detection, and age estimation capabilities 评估ChatGPT在生物识别中的面部识别、性别检测和年龄估计能力 large language model foundation model
6 Interactive Continual Learning: Fast and Slow Thinking 提出交互式持续学习框架以解决持续学习中的遗忘问题 large language model multimodal
7 Modeling Collaborator: Enabling Subjective Vision Classification With Minimal Human Effort via LLM Tool-Use 提出新框架以减少主观视觉分类中的人工标注工作量 large language model foundation model
8 Learning Zero-Shot Material States Segmentation, by Implanting Natural Image Patterns in Synthetic Data 通过将自然图像模式植入合成数据解决零样本材料状态分割问题 foundation model
9 ImgTrojan: Jailbreaking Vision-Language Models with ONE Image 提出ImgTrojan以解决视觉语言模型的安全性问题 large language model
10 Few-shot Learner Parameterization by Diffusion Time-steps 提出基于扩散时间步的少样本学习者以解决属性提取问题 foundation model ✅
11 VEglue: Testing Visual Entailment Systems via Object-Aligned Joint Erasing 提出VEglue以解决视觉蕴含系统测试中的挑战 multimodal

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
12 Enhancing Conceptual Understanding in Multimodal Contrastive Learning through Hard Negative Samples 通过引入困难负样本提升多模态对比学习的概念理解 contrastive learning multimodal
13 PromptKD: Unsupervised Prompt Distillation for Vision-Language Models 提出无监督领域提示蒸馏框架以提升视觉语言模型性能 distillation
14 Dual Mean-Teacher: An Unbiased Semi-Supervised Framework for Audio-Visual Source Localization 提出双均值教师框架以解决音视频源定位问题 contrastive learning teacher-student

🔬 支柱六：视频提取与匹配 (Video Extraction) (2 篇)

#题目一句话要点标签🔗⭐
15 Semantic Human Mesh Reconstruction with Textures 提出SHERT以解决3D人类网格重建中的纹理和细节问题 SMPL SMPL-X
16 A Backpack Full of Skills: Egocentric Video Understanding with Diverse Task Perspectives 提出EgoPack以解决视频理解中的多任务协同问题 egocentric Ego4D

🔬 支柱三：空间感知与语义 (Perception & Semantics) (2 篇)

#题目一句话要点标签🔗⭐
17 Improved LiDAR Odometry and Mapping using Deep Semantic Segmentation and Novel Outliers Detection 提出基于深度语义分割的改进LiDAR里程计与地图构建方法 semantic map motion estimation
18 HUNTER: Unsupervised Human-centric 3D Detection via Transferring Knowledge from Synthetic Instances to Real Scenes 提出无监督3D检测方法以解决人类中心场景理解问题 scene understanding

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

#题目一句话要点标签🔗⭐
19 MiKASA: Multi-Key-Anchor & Scene-Aware Transformer for 3D Visual Grounding 提出MiKASA以解决3D视觉定位中的多锚点和场景感知问题 spatial relationship visual grounding

⬅️ 返回 cs.CV 首页 · 🏠 返回主页