CVPR2022論文速遞！共18篇（2022.3.9）
A Simple Multi-Modality Transfer Learning Baseline for Sign Language Translation
論文/Paper：https://arxiv.org/abs/2203.04287
代碼/Code：
Probabilistic Warp Consistency for Weakly-Supervised Semantic Correspondences
論文/Paper：https://arxiv.org/abs/2203.04279
代碼/Code：https://github.com/PruneTruong/DenseMatching
End-to-End Semi-Supervised Learning for Video Action Detection
論文/Paper：https://arxiv.org/abs/2203.04251
代碼/Code：
Neural Face Identification in a 2D Wireframe Projection of a Manifold Object
論文/Paper：https://arxiv.org/abs/2203.04229
代碼/Code：https://github.com/manycore-research/faceformer
主頁：https://manycore-research.github.io/faceformer/
Selective-Supervised Contrastive Learning with Noisy Labels
論文/Paper：https://arxiv.org/abs/2203.04181
代碼/Code：https://github.com/ShikunLi/Sel-CL
Motron: Multimodal Probabilistic Human Motion Forecasting
論文/Paper：https://arxiv.org/abs/2203.04132
代碼/Code：
E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance Segmentation
論文/Paper：https://arxiv.org/abs/2203.04074
代碼/Code：https://github.com/zhang-tao-whu/e2ec
Shape-invariant 3D Adversarial Point Clouds
論文/Paper：https://arxiv.org/abs/2203.04041
代碼/Code：https://github.com/shikiw/SI-Adv
DeltaCNN: End-to-End CNN Inference of Sparse Frame Differences in Videos
論文/Paper：https://arxiv.org/abs/2203.03996
代碼/Code：
Generative Cooperative Learning for Unsupervised Video Anomaly Detection
論文/Paper：https://arxiv.org/abs/2203.03962
代碼/Code：
ART-Point: Improving Rotation Robustness of Point Cloud Classifiers via Adversarial Rotation
論文/Paper：https://arxiv.org/abs/2203.03888
代碼/Code：
Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels
論文/Paper：https://arxiv.org/abs/2203.03884
代碼/Code：
Weakly Supervised Semantic Segmentation using Out-of-Distribution Data
論文/Paper：https://arxiv.org/abs/2203.03860
代碼/Code：
Deep Rectangling for Image Stitching: A Learning Baseline
論文/Paper：https://arxiv.org/abs/2203.03831
代碼/Code：https://github.com/nie-lang/DeepRectangling
Shadows can be Dangerous: Stealthy and Effective Physical-world Adversarial Attack by Natural Phenomenon
論文/Paper：https://arxiv.org/abs/2203.03818
代碼/Code：
Unknown-Aware Object Detection: Learning What You Don't Know from Videos in the Wild
論文/Paper：https://arxiv.org/abs/2203.03800
代碼/Code：https://github.com/deeplearning-wisc/stud
On Generalizing Beyond Domains in Cross-Domain Continual Learning
論文/Paper：https://arxiv.org/abs/2203.03970
代碼/Code：
Generating 3D Bio-Printable Patches Using Wound Segmentation and Reconstruction to Treat Diabetic Foot Ulcers
論文/Paper：https://arxiv.org/abs/2203.03814
代碼/Code：