CVPR2022论文速递（2022.6.7）！共14篇！-技术圈

整理：AI算法与图像处理

CVPR2022论文和代码整理：https://github.com/DWCTOD/CVPR2022-Papers-with-Code-Demo

欢迎关注公众号 AI算法与图像处理，获取更多干货：

大家好, 最近正在优化每周分享的CVPR论文, 目前考虑按照不同类别去分类,方便不同方向的小伙伴挑选自己感兴趣的论文哈

欢迎大家留言其他想法, 合适的话会采纳哈! 求个三连支持一波哈

Updated on : 7 Jun 2022

total number : 14

语义分割/Segmentation - 2 篇

Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation

标题：激光雷达语义分割的点到素知识蒸馏

论文/Paper: http://arxiv.org/pdf/2206.02099
代码/Code: https://github.com/cardwing/Codes-for-PVKD

Occlusion-Resistant Instance Segmentation of Piglets in Farrowing Pens Using Center Clustering Network

标题：使用中心聚类网络对猪的遮挡实例分割

论文/Paper: http://arxiv.org/pdf/2206.01942
代码/Code: None

Transformers - - 2 篇

Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning

标题：通过等级自监督学习将视觉Transformers缩放到吉吉像素图像

论文/Paper: http://arxiv.org/pdf/2206.02647
代码/Code: None

Cross-modal Clinical Graph Transformer for Ophthalmic Report Generation

标题：眼科报告生成的跨模式临床图Transformers

论文/Paper: http://arxiv.org/pdf/2206.01988
代码/Code: None

姿态估计/Pose Estimation - 1 篇

Nerfels: Renderable Neural Codes for Improved Camera Pose Estimation

标题：Nerfels：可渲染的神经代码，用于改进相机姿势估计

论文/Paper: http://arxiv.org/pdf/2206.01916
代码/Code: None

人脸相关 / Face - 2 篇

CORE: Consistent Representation Learning for Face Forgery Detection

标题：CORE：面部伪造检测的一致表示学习

论文/Paper: http://arxiv.org/pdf/2206.02749
代码/Code: None

Evaluation-oriented Knowledge Distillation for Deep Face Recognition

标题：以评估为导向的知识蒸馏以进行深度识别

论文/Paper: http://arxiv.org/pdf/2206.02325
代码/Code: None

其他/Other - 7 篇

Universal Photometric Stereo Network using Global Lighting Contexts

标题：使用全局照明环境的通用光度立体网络

论文/Paper: http://arxiv.org/pdf/2206.02452
代码/Code: None

Invariant Grounding for Video Question Answering

标题：视频问答不变的基础

论文/Paper: http://arxiv.org/pdf/2206.02349
代码/Code: None

M2FNet: Multi-modal Fusion Network for Emotion Recognition in Conversation

标题：M2FNet：在对话中识别情绪识别的多模式融合网络

论文/Paper: http://arxiv.org/pdf/2206.02187
代码/Code: None

MotionCNN: A Strong Baseline for Motion Prediction in Autonomous Driving

标题：MotionCNN：自动驾驶中运动预测的强大基线

论文/Paper: http://arxiv.org/pdf/2206.02163
代码/Code: None

Cannot See the Forest for the Trees: Aggregating Multiple Viewpoints to Better Classify Objects in Videos

标题：看不到树木的森林：汇总多个观点以更好地对视频中的对象进行分类

论文/Paper: http://arxiv.org/pdf/2206.02116
代码/Code: None

Learning sRGB-to-Raw-RGB De-rendering with Content-Aware Metadata

标题：学习srgb-to-raw-rgb用内容感知元数据

论文/Paper: http://arxiv.org/pdf/2206.01813
代码/Code: https://github.com/SamsungLabs/content-aware-metadata)

RIDDLE: Lidar Data Compression with Range Image Deep Delta Encoding

标题：RIDDLE：带有范围图像的LIDAR数据压缩深层增量编码

论文/Paper: http://arxiv.org/pdf/2206.01738
代码/Code: None