cs.CV（2023-11-24）

📊 共 17 篇论文 | 🔗 6 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (7 🔗3) 支柱三：空间感知与语义 (Perception & Semantics) (6 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱八：物理动画 (Physics-based Animation) (1 🔗1)

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

#题目一句话要点标签🔗⭐
1 Charting New Territories: Exploring the Geographic and Geospatial Capabilities of Multimodal LLMs 探索多模态大语言模型在地理与地理空间领域的能力 large language model multimodal
2 Large Language Models as Automated Aligners for benchmarking Vision-Language Models 提出Auto-Bench以解决VLM评估中的数据不足问题 large language model
3 Griffon: Spelling out All Object Locations at Any Granularity with Large Language Models 提出Griffon以解决LVLMs在物体定位中的局限性 large language model ✅
4 GeoChat: Grounded Large Vision-Language Model for Remote Sensing 提出GeoChat以解决遥感领域对话模型的局限性 multimodal instruction following ✅
5 Inferring Latent Class Statistics from Text for Robust Visual Few-Shot Learning 提出利用文本推断潜在类别统计以增强视觉少样本学习的鲁棒性 foundation model
6 Segment (Almost) Nothing: Prompt-Agnostic Adversarial Attacks on Segmentation Models 提出无提示对抗攻击以增强分割模型的鲁棒性 foundation model
7 ZeroPS: High-quality Cross-modal Knowledge Transfer for Zero-Shot 3D Part Segmentation 提出ZeroPS以解决零样本3D部件分割问题 foundation model ✅

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

#题目一句话要点标签🔗⭐
8 GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting 提出GaussianEditor以解决传统3D编辑速度慢与控制力不足的问题 gaussian splatting splatting NeRF ✅
9 Text and Click inputs for unambiguous open vocabulary instance segmentation 提出文本与点击输入的实例分割方法以解决模糊分类问题 open-vocabulary open vocabulary
10 SEGIC: Unleashing the Emergent Correspondence for In-Context Segmentation 提出SEGIC以解决上下文分割任务中的样本依赖问题 open-vocabulary open vocabulary foundation model ✅
11 Animate124: Animating One Image to 4D Dynamic Scene 提出Animate124以解决单图像生成4D动态场景的问题 NeRF neural radiance field
12 Highly Detailed and Temporal Consistent Video Stylization via Synchronized Multi-Frame Diffusion 提出同步多帧扩散框架以解决视频风格化中的细节与一致性问题 optical flow
13 RSB-Pose: Robust Short-Baseline Binocular 3D Human Pose Estimation with Occlusion Handling 提出RSB-Pose以解决短基线双目3D人体姿态估计中的遮挡问题 3D reconstruction

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

#题目一句话要点标签🔗⭐
14 UniHPE: Towards Unified Human Pose Estimation via Contrastive Learning 提出UniHPE以实现统一的人体姿态估计 contrastive learning
15 Maximizing Discrimination Capability of Knowledge Distillation with Energy Function 提出基于能量函数的知识蒸馏方法以提升模型性能 distillation
16 Cosine Similarity Knowledge Distillation for Individual Class Information Transfer 提出余弦相似度知识蒸馏以提升模型性能 distillation

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
17 VSViG: Real-time Video-based Seizure Detection via Skeleton-based Spatiotemporal ViG 提出VSViG以解决视频监测癫痫发作检测延迟问题 spatiotemporal ✅

⬅️ 返回 cs.CV 首页 · 🏠 返回主页