cs.CV（2023-10-04）

📊 共 17 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (6 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (5) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱一：机器人控制 (Robot Control) (3)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (6 篇)

#题目一句话要点标签🔗⭐
1 Comprehensive Multimodal Segmentation in Medical Imaging: Combining YOLOv8 with SAM and HQ-SAM Models 提出YOLOv8与SAM结合的多模态医学影像分割方法 multimodal
2 Improving Automatic VQA Evaluation Using Large Language Models 利用大型语言模型改进自动视觉问答评估 large language model
3 ECoFLaP: Efficient Coarse-to-Fine Layer-Wise Pruning for Vision-Language Models 提出ECoFLaP以解决大规模视觉语言模型的高能耗问题 multimodal
4 Improving Vision Anomaly Detection with the Guidance of Language Modality 提出跨模态引导方法以解决视觉异常检测中的信息冗余问题 multimodal
5 GET: Group Event Transformer for Event-Based Vision 提出Group Event Transformer以解决事件摄像头信息提取不足问题 TAMP ✅
6 ShaSTA-Fuse: Camera-LiDAR Sensor Fusion to Model Shape and Spatio-Temporal Affinities for 3D Multi-Object Tracking 提出ShaSTA-Fuse以解决3D多目标跟踪中的传感器融合问题 multimodal

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

#题目一句话要点标签🔗⭐
7 USB-NeRF: Unrolling Shutter Bundle Adjusted Neural Radiance Fields 提出USB-NeRF以解决滚动快门图像合成问题 NeRF neural radiance field motion estimation
8 CoDA: Collaborative Novel Box Discovery and Cross-modal Alignment for Open-vocabulary 3D Object Detection 提出CoDA以解决开放词汇3D物体检测中的新物体定位与分类问题 open-vocabulary open vocabulary
9 Shielding the Unseen: Privacy Protection through Poisoning NeRF with Spatial Deformation 提出隐私保护方法以应对NeRF模型的生成能力 NeRF neural radiance field scene reconstruction
10 Efficient-3DiM: Learning a Generalizable Single-image Novel-view Synthesizer in One Day 提出Efficient-3DiM以解决单图像新视角合成问题 neural radiance field
11 T$^3$Bench: Benchmarking Current Progress in Text-to-3D Generation 提出T$^3$Bench以解决文本到3D生成评估问题 NeRF

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

#题目一句话要点标签🔗⭐
12 Kosmos-G: Generating Images in Context with Multimodal Large Language Models 提出Kosmos-G以解决多模态图像生成中的输入限制问题 distillation large language model multimodal
13 Reinforcement Learning-based Mixture of Vision Transformers for Video Violence Recognition 提出基于强化学习的混合视觉变换器以解决视频暴力识别问题 reinforcement learning
14 SweetDreamer: Aligning Geometric Priors in 2D Diffusion for Consistent Text-to-3D 提出SweetDreamer以解决2D到3D生成中的几何不一致问题 dreamer

🔬 支柱一：机器人控制 (Robot Control) (3 篇)

#题目一句话要点标签🔗⭐
15 Continuous 3D Myocardial Motion Tracking via Echocardiography 提出神经心脏运动场以解决心肌运动追踪不准确问题 motion tracking ReMoS motion estimation
16 ED-NeRF: Efficient Text-Guided Editing of 3D Scene with Latent Space NeRF 提出ED-NeRF以解决3D场景编辑速度慢的问题 manipulation distillation NeRF
17 A Grammatical Compositional Model for Video Action Detection 提出语法组合模型以解决视频动作检测中的复杂动态问题 manipulation

⬅️ 返回 cs.CV 首页 · 🏠 返回主页