cs.CV（2023-10-19）

📊 共 16 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (5 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (5) 支柱七：动作重定向 (Motion Retargeting) (2 🔗1) 支柱一：机器人控制 (Robot Control) (2) 支柱四：生成式动作 (Generative Motion) (1) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)

#	题目	一句话要点	标签	🔗	⭐
1	RSAdapter: Adapting Multimodal Models for Remote Sensing Visual Question Answering	提出RSAdapter以解决遥感视觉问答中的资源消耗问题	multimodal	✅
2	CLAIR: Evaluating Image Captions with Large Language Models	提出CLAIR以解决图像描述评估的挑战	large language model	✅
3	Weakly-Supervised Semantic Segmentation with Image-Level Labels: from Traditional Models to Foundation Models	提出弱监督语义分割方法以解决图像级标签的挑战	foundation model
4	2D-3D Interlaced Transformer for Point Cloud Segmentation with Scene-Level Supervision	提出多模态交错变换器以解决弱监督点云分割问题	multimodal	✅
5	Query-aware Long Video Localization and Relation Discrimination for Deep Video Understanding	提出查询感知方法以解决长视频定位与关系辨别问题	multimodal

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

#	题目	一句话要点	标签	🔗	⭐
6	LoMAE: Low-level Vision Masked Autoencoders for Low-dose CT Denoising	提出LoMAE以解决低剂量CT图像去噪问题	masked autoencoder MAE
7	Exploiting Low-confidence Pseudo-labels for Source-free Object Detection	提出低置信度伪标签利用方法以提升源无关目标检测性能	contrastive learning spatial relationship
8	Representation Learning via Consistent Assignment of Views over Random Partitions	提出CARP方法以解决自监督聚类中的一致性问题	representation learning
9	WeedCLR: Weed Contrastive Learning through Visual Representations with Class-Optimized Loss in Long-Tailed Datasets	提出WeedCLR以解决长尾数据集中的杂草分类问题	contrastive learning
10	SAM Meets UAP: Attacking Segment Anything Model With Universal Adversarial Perturbation	提出基于自监督对比学习的UAP生成方法以攻击SAM模型	contrastive learning foundation model

🔬 支柱七：动作重定向 (Motion Retargeting) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
11	Real-Time Motion Prediction via Heterogeneous Polyline Transformer with Relative Pose Encoding	提出KNARPE机制以解决自主驾驶中的运动预测效率问题	motion prediction	✅
12	Multiscale Motion-Aware and Spatial-Temporal-Channel Contextual Coding Network for Learned Video Compression	提出MASTC-VC以解决视频压缩中的运动估计不准确问题	motion estimation motion prediction

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
13	3D-GPT: Procedural 3D Modeling with Large Language Models	提出3D-GPT以解决程序化3D建模的复杂性问题	manipulation large language model
14	CycleNet: Rethinking Cycle Consistency in Text-Guided Diffusion for Image Manipulation	提出CycleNet以解决无配对图像翻译中的一致性问题	manipulation

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
15	HumanTOMATO: Text-aligned Whole-body Motion Generation	提出HumanTOMATO以解决文本驱动的全身动作生成问题	text-driven motion motion generation VQ-VAE

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
16	FSD: Fast Self-Supervised Single RGB-D to Categorical 3D Objects	提出快速自监督方法以解决单RGB-D图像的3D物体识别问题	6D pose estimation

⬅️ 返回 cs.CV 首页 · 🏠 返回主页