CVPR2022论文速递（2022.6.2）！共9篇！

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

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!

Updated on : 2 Jun 2022

total number : 9

CLIP4IDC: CLIP for Image Difference Captioning

• 论文/Paper: http://arxiv.org/pdf/2206.00629
• 代码/Code: https://github.com/sushizixin/clip4idc

On the Choice of Data for Efficient Training and Validation of End-to-End Driving Models

• 论文/Paper: http://arxiv.org/pdf/2206.00608
• 代码/Code: None

Where are my Neighbors? Exploiting Patches Relations in Self-Supervised Vision Transformer

• 论文/Paper: http://arxiv.org/pdf/2206.00481
• 代码/Code: None

PanopticDepth: A Unified Framework for Depth-aware Panoptic Segmentation

• 论文/Paper: http://arxiv.org/pdf/2206.00468
• 代码/Code: https://github.com/naiyugao/panopticdepth

Efficient Multi-Purpose Cross-Attention Based Image Alignment Block for Edge Devices

• 论文/Paper: http://arxiv.org/pdf/2206.00291
• 代码/Code: None

Interpretable Deep Learning Classifier by Detection of Prototypical Parts on Kidney Stones Images

• 论文/Paper: http://arxiv.org/pdf/2206.00252
• 代码/Code: None

VALHALLA: Visual Hallucination for Machine Translation

• 论文/Paper: http://arxiv.org/pdf/2206.00100
• 代码/Code: None

Towards Generalisable Audio Representations for Audio-Visual Navigation

• 论文/Paper: http://arxiv.org/pdf/2206.00393
• 代码/Code: None

A comparative study between vision transformers and CNNs in digital pathology

• 论文/Paper: http://arxiv.org/pdf/2206.00389
• 代码/Code: None