cs.CV（2024-01-25）

📊 共 19 篇论文 | 🔗 7 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) (5 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗2) 支柱六：视频提取与匹配 (Video Extraction) (1 🔗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 Revisiting Active Learning in the Era of Vision Foundation Models 提出新策略以提升基础视觉模型在主动学习中的效率 foundation model ✅
2 Multimodal Pathway: Improve Transformers with Irrelevant Data from Other Modalities 提出多模态通路以利用其他模态的无关数据提升变换器性能 multimodal ✅
3 JUMP: A joint multimodal registration pipeline for neuroimaging with minimal preprocessing 提出JUMP以解决神经影像多模态配准问题 multimodal
4 CreativeSynth: Cross-Art-Attention for Artistic Image Synthesis with Multimodal Diffusion 提出CreativeSynth以解决艺术图像合成中的多模态信息整合问题 multimodal ✅
5 On generalisability of segment anything model for nuclear instance segmentation in histology images 利用SAM模型实现组织学图像中核实例分割 foundation model
6 LanDA: Language-Guided Multi-Source Domain Adaptation 提出LanDA以解决无目标图像的多源领域适应问题 multimodal
7 Knowledge Guided Entity-aware Video Captioning and A Basketball Benchmark 提出知识引导的实体感知视频字幕生成方法以解决篮球赛事描述问题 multimodal

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

#题目一句话要点标签🔗⭐
8 GauU-Scene: A Scene Reconstruction Benchmark on Large Scale 3D Reconstruction Dataset Using Gaussian Splatting 提出GauU-Scene基准以解决大规模3D重建问题 3D reconstruction gaussian splatting splatting
9 Range-Agnostic Multi-View Depth Estimation With Keyframe Selection 提出RAMDepth以解决无先验范围的多视图深度估计问题 depth estimation 3D reconstruction ✅
10 Learning Robust Generalizable Radiance Field with Visibility and Feature Augmented Point Representation 提出基于点表示的通用神经辐射场以解决现有方法的局限性 NeRF neural radiance field feature matching
11 TIFu: Tri-directional Implicit Function for High-Fidelity 3D Character Reconstruction 提出TIFu以解决高保真3D角色重建问题 3D reconstruction
12 pix2gestalt: Amodal Segmentation by Synthesizing Wholes 提出pix2gestalt以解决零-shot模态分割问题 3D reconstruction

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

#题目一句话要点标签🔗⭐
13 Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks 提出Grounded SAM以解决开放世界视觉任务的检测与分割问题 world model world models open-vocabulary
14 Vivim: a Video Vision Mamba for Medical Video Segmentation 提出Vivim框架以解决医学视频分割中的长序列建模问题 Mamba SSM state space model ✅
15 Rethinking Patch Dependence for Masked Autoencoders 提出CrossMAE以优化掩码自编码器的重建效率 representation learning masked autoencoder MAE
16 Deep Clustering with Diffused Sampling and Hardness-aware Self-distillation 提出HaDis以解决深度聚类中的样本不均衡问题 contrastive learning distillation ✅
17 Self-supervised Video Object Segmentation with Distillation Learning of Deformable Attention 提出自监督视频目标分割方法以解决长视频处理中的注意力对齐问题 representation learning distillation

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

#题目一句话要点标签🔗⭐
18 Incorporating Test-Time Optimization into Training with Dual Networks for Human Mesh Recovery 提出双网络架构以优化人类网格恢复的测试时间性能 human mesh recovery HMR ✅

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

#题目一句话要点标签🔗⭐
19 Neighbor-Aware Calibration of Segmentation Networks with Penalty-Based Constraints 提出邻域感知校准方法以提升分割网络的置信度 spatial relationship

⬅️ 返回 cs.CV 首页 · 🏠 返回主页