CVPR2022论文速递（2022.5.10）！共15篇！

Updated on :  10 May 2022

total number : 15

Online Unsupervised Domain Adaptation for Person Re-identification

• 论文/Paper: http://arxiv.org/pdf/2205.04383

• 代码/Code: None

Beyond a Pre-Trained Object Detector: Cross-Modal Textual and Visual Context for Image Captioning

• 论文/Paper: http://arxiv.org/pdf/2205.04363

• 代码/Code: https://github.com/GT-RIPL/Xmodal-Ctx

Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation

• 论文/Paper: http://arxiv.org/pdf/2205.04334

• 代码/Code: None

SwinIQA: Learned Swin Distance for Compressed Image Quality Assessment

• 论文/Paper: http://arxiv.org/pdf/2205.04264

• 代码/Code: None

Beyond Bounding Box: Multimodal Knowledge Learning for Object Detection

• 论文/Paper: http://arxiv.org/pdf/2205.04072

• 代码/Code: None

On Conditioning the Input Noise for Controlled Image Generation with Diffusion Models

• 论文/Paper: http://arxiv.org/pdf/2205.03859

• 代码/Code: None

Unsupervised Homography Estimation with Coplanarity-Aware GAN

• 论文/Paper: http://arxiv.org/pdf/2205.03821

• 代码/Code: https://github.com/megvii-research/HomoGAN.

Transformer Tracking with Cyclic Shifting Window Attention

• 论文/Paper: http://arxiv.org/pdf/2205.03806

• 代码/Code: None

A Closer Look at Few-shot Image Generation

• 论文/Paper: http://arxiv.org/pdf/2205.03805

• 代码/Code: None

Non-parametric Depth Distribution Modelling based Depth Inference for Multi-view Stereo

• 论文/Paper: http://arxiv.org/pdf/2205.03783

• 代码/Code: https://github.com/NVlabs/NP-CVP-MVSNet

Recurrent Dynamic Embedding for Video Object Segmentation

• 论文/Paper: http://arxiv.org/pdf/2205.03761

• 代码/Code: https://github.com/Limingxing00/RDE-VOS-CVPR2022.

End-to-End Rubbing Restoration Using Generative Adversarial Networks

• 论文/Paper: http://arxiv.org/pdf/2205.03743

• 代码/Code: None

GenISP: Neural ISP for Low-Light Machine Cognition

• 论文/Paper: http://arxiv.org/pdf/2205.03688

• 代码/Code: None

NeuralHDHair: Automatic High-fidelity Hair Modeling from a Single Image Using Implicit Neural Representations

• 论文/Paper: http://arxiv.org/pdf/2205.04175

• 代码/Code: None

Bandits for Structure Perturbation-based Black-box Attacks to Graph Neural Networks with Theoretical Guarantees

• 论文/Paper: http://arxiv.org/pdf/2205.03546

• 代码/Code: https://github.com/Metaoblivion/Bandit_GNN_Attack