cs.CV（2024-01-22）

📊 共 17 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (7 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (3) 支柱六：视频提取与匹配 (Video Extraction) (1) 支柱七：动作重定向 (Motion Retargeting) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (7 篇)

#题目一句话要点标签🔗⭐
1 Less Could Be Better: Parameter-efficient Fine-tuning Advances Medical Vision Foundation Models 提出参数高效微调方法以提升医学影像模型性能 large language model foundation model ✅
2 Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs 提出RPG框架以解决复杂文本提示下的图像生成问题 multimodal chain-of-thought ✅
3 A Vision-Language Foundation Model to Enhance Efficiency of Chest X-ray Interpretation 提出CheXagent以提高胸部X光解读效率 foundation model
4 DeepCERES: A Deep learning method for cerebellar lobule segmentation using ultra-high resolution multimodal MRI 提出DeepCERES以解决小脑叶段分割问题 multimodal
5 Leveraging Chat-Based Large Vision Language Models for Multimodal Out-Of-Context Detection 利用聊天式大型视觉语言模型解决多模态上下文外检测问题 multimodal
6 M2-CLIP: A Multimodal, Multi-task Adapting Framework for Video Action Recognition 提出M2-CLIP框架以解决视频动作识别中的迁移能力不足问题 multimodal
7 Look, Listen and Recognise: Character-Aware Audio-Visual Subtitling 提出角色感知的自动字幕生成方法以提升视频可访问性 TAMP

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
8 Zoom-shot: Fast and Efficient Unsupervised Zero-Shot Transfer of CLIP to Vision Encoders with Multimodal Loss 提出Zoom-shot以解决VLM训练资源消耗问题 distillation multimodal zero-shot transfer
9 Stereo-Matching Knowledge Distilled Monocular Depth Estimation Filtered by Multiple Disparity Consistency 提出无监督单目深度估计的新方法以解决伪深度图错误问题 distillation depth estimation monocular depth
10 SignVTCL: Multi-Modal Continuous Sign Language Recognition Enhanced by Visual-Textual Contrastive Learning 提出SignVTCL以解决手语识别中的数据不足问题 contrastive learning optical flow
11 Rethinking Centered Kernel Alignment in Knowledge Distillation 提出关系中心核对齐框架以简化知识蒸馏过程 teacher-student distillation ✅
12 Contrastive Learning and Cycle Consistency-based Transductive Transfer Learning for Target Annotation 提出H-CUT网络以解决目标域标注性能不足问题 contrastive learning

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

#题目一句话要点标签🔗⭐
13 Exploring Simple Open-Vocabulary Semantic Segmentation 提出S-Seg以解决开放词汇语义分割问题 open-vocabulary open vocabulary
14 HG3-NeRF: Hierarchical Geometric, Semantic, and Photometric Guided Neural Radiance Fields for Sparse View Inputs 提出HG3-NeRF以解决稀疏视图输入下的NeRF性能下降问题 NeRF neural radiance field
15 MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View Stereo 提出MVSFormer++以提升多视角立体视觉的深度估计能力 depth estimation

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

#题目一句话要点标签🔗⭐
16 Full-Body Motion Reconstruction with Sparse Sensing from Graph Perspective 提出基于图的全身运动重建方法以解决稀疏传感器数据问题 sparse sensors human motion motion reconstruction

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

#题目一句话要点标签🔗⭐
17 SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities 提出SpatialVLM以解决视觉语言模型的空间推理能力不足问题 spatial relationship chain-of-thought

⬅️ 返回 cs.CV 首页 · 🏠 返回主页