cs.CV（2023-10-18）

📊 共 14 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) 支柱三：空间感知与语义 (Perception & Semantics) (5) 支柱一：机器人控制 (Robot Control) (2 🔗1) 支柱四：生成式动作 (Generative Motion) (1)

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

#	题目	一句话要点	标签	🔗	⭐
1	A New Multimodal Medical Image Fusion based on Laplacian Autoencoder with Channel Attention	提出基于拉普拉斯自编码器的多模态医学图像融合方法以解决特征损失问题	multimodal
2	Evaluating the Fairness of Discriminative Foundation Models in Computer Vision	提出新分类法评估计算机视觉中的偏见问题	foundation model
3	Understanding Video Transformers for Segmentation: A Survey of Application and Interpretability	综述视频变换器在分割中的应用与可解释性问题	multimodal
4	BanglaAbuseMeme: A Dataset for Bengali Abusive Meme Classification	构建BanglaAbuseMeme数据集以解决孟加拉语滥用表情包分类问题	multimodal
5	ChatGPT-guided Semantics for Zero-shot Learning	提出ChatGPT增强语义以解决零样本学习问题	large language model
6	VKIE: The Application of Key Information Extraction on Video Text	提出VKIE以解决视频文本中的关键信息提取问题	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	Towards Abdominal 3-D Scene Rendering from Laparoscopy Surgical Videos using NeRFs	提出基于NeRF的腹部三维场景渲染方法以解决腹腔镜视频的视觉限制问题	depth estimation NeRF neural radiance field
8	IRAD: Implicit Representation-driven Image Resampling against Adversarial Attacks	提出隐式表示驱动的图像重采样以应对对抗攻击	implicit representation
9	VQ-NeRF: Neural Reflectance Decomposition and Editing with Vector Quantization	提出VQ-NeRF以解决3D场景中材料分解与编辑问题	NeRF
10	RGM: A Robust Generalizable Matching Model	提出RGM以解决图像匹配的通用性与鲁棒性问题	optical flow feature matching
11	Panoptic Out-of-Distribution Segmentation	提出Panoptic Out-of-Distribution Segmentation以解决OOD物体分割问题	scene understanding

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
12	ShapeGraFormer: GraFormer-Based Network for Hand-Object Reconstruction from a Single Depth Map	提出ShapeGraFormer以解决单幅深度图下手-物体重建问题	manipulation 3D reconstruction hand reconstruction
13	Tailoring Adversarial Attacks on Deep Neural Networks for Targeted Class Manipulation Using DeepFool Algorithm	提出增强型目标DeepFool算法以解决深度神经网络的针对性攻击问题	manipulation	✅

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
14	On the Benefit of Generative Foundation Models for Human Activity Recognition	提出生成基础模型以解决人类活动识别中的数据稀缺问题	motion synthesis large language model foundation model

⬅️ 返回 cs.CV 首页 · 🏠 返回主页