[人工智能]CVPR 2022 57 篇论文分方向整理 + 打包下载｜涵盖目标检测、语义分割、人群计数、异常检测等方向

CVPR2022论文速递系列：
CVPR 2022 3月3日论文速递（22 篇打包下载）涵盖网络架构设计、姿态估计、三维视觉、动作检测、语义分割等方向
CVPR 2022 3月4日论文速递（29 篇打包下载）涵盖目标检测、全景分割、异常检测、度量学习、对比学习、目标跟踪等方向
CVPR 2022 3月7日论文速递（17 篇打包下载）涵盖 3D 目标检测、医学影像、图像去模糊、车道线检测等方向
推荐阅读：CVPR 2022 最全整理：论文分方向汇总 / 代码 / 解读 / 直播 / 项目（更新中）【计算机视觉】

以下为3月9日更新的57篇CVPR2022论文分方向整理，打包下载： 下载地址

2D 目标检测(2D Object Detection)

【1】Unknown-Aware Object Detection: Learning What You Don’t Know from Videos in the Wild(未知感知对象检测：从野外视频中学习你不知道的东西)

paper | code

伪装目标检测(Camouflaged Object Detection)

【1】Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detection(放大和缩小：用于伪装目标检测的混合尺度三元组网络)

paper | code

超分辨率(Super Resolution)

【1】Reflash Dropout in Image Super-Resolution(图像超分辨率中的闪退dropout)

paper

【2】Towards Bidirectional Arbitrary Image Rescaling: Joint Optimization and Cycle Idempotence(迈向双向任意图像缩放：联合优化和循环幂等)

paper

【3】【HyperTransformer: A Textural and Spectral Feature Fusion Transformer for Pansharpening(用于全色锐化的纹理和光谱特征融合Transformer)

paper ｜ code

小样本学习/零样本学习(Few-shot Learning/Zero-shot Learning)

【1】Learning to Affiliate: Mutual Centralized Learning for Few-shot Classification(小样本分类的相互集中学习)

paper

【2】MSDN: Mutually Semantic Distillation Network for Zero-Shot Learning(用于零样本学习的相互语义蒸馏网络)

keywords: Zero-Shot Learning, Knowledge Distillation

paper | code

神经网络可解释性(Neural Network Interpretability)

【1】Interpretable part-whole hierarchies and conceptual-semantic relationships in neural networks(神经网络中可解释的部分-整体层次结构和概念语义关系)

paper

姿态估计(Human Pose Estimation)

【1】Forecasting Characteristic 3D Poses of Human Actions()

paper | project | video

医学影像(Medical Imaging)

【1】Adaptive Early-Learning Correction for Segmentation from Noisy Annotations(从噪声标签中分割的自适应早期学习校正)

keywords: medical-imaging segmentation, Noisy Annotations

paper | code

光流/位姿/运动估计(Optical Flow/Pose/Motion Estimation)

【1】CPPF: Towards Robust Category-Level 9D Pose Estimation in the Wild(CPPF：在野外实现稳健的类别级 9D 位姿估计)

paper | code

【2】OVE6D: Object Viewpoint Encoding for Depth-based 6D Object Pose Estimation(用于基于深度的 6D 对象姿态估计的对象视点编码)

paper | code

【3】CamLiFlow: Bidirectional Camera-LiDAR Fusion for Joint Optical Flow and Scene Flow Estimation(用于联合光流和场景流估计的双向相机-LiDAR 融合)

paper

视觉语言表征学习（Vision-language Representation Learning）

【1】L-Verse: Bidirectional Generation Between Image and Text(图像和文本之间的双向生成) (Oral Presentation)

paper

点云(Point Cloud)

【1】Shape-invariant 3D Adversarial Point Clouds(形状不变的 3D 对抗点云)

paper | code

【2】ART-Point: Improving Rotation Robustness of Point Cloud Classifiers via Adversarial Rotation(通过对抗旋转提高点云分类器的旋转鲁棒性)

paper

【3】Lepard: Learning partial point cloud matching in rigid and deformable scenes(Lepard：在刚性和可变形场景中学习部分点云匹配)

paper | code

深度估计(Depth Estimation)

【1】Rethinking Depth Estimation for Multi-View Stereo: A Unified Representation and Focal Loss(重新思考多视图立体的深度估计：统一表示和焦点损失)

paper | code

场景重建/新视角合成(Novel View Synthesis)

【1】Point-NeRF: Point-based Neural Radiance Fields(基于点的神经辐射场)

paper ｜ code |project

图像生成/图像合成/视频合成(Image Generation/Image Synthesis/Video Generation)

【1】Exploring Dual-task Correlation for Pose Guided Person Image Generation(探索姿势引导人物图像生成的双任务相关性)

paper | code

【2】Show Me What and Tell Me How: Video Synthesis via Multimodal Conditioning(告诉我什么并告诉我如何：通过多模式调节进行视频合成)

paper | code

风格迁移(Style Transfer)

【1】How Well Do Sparse Imagenet Models Transfer?(稀疏 Imagenet 模型的迁移效果如何？)

paper

【2】Style-ERD: Responsive and Coherent Online Motion Style Transfer(响应式和连贯的在线运动风格迁移)

paper

人群计数(Crowd Counting)

【1】Boosting Crowd Counting via Multifaceted Attention(通过多方面注意提高人群计数)

paper | code

数据集(Dataset)

【1】Kubric: A scalable dataset generator(Kubric：可扩展的数据集生成器)

paper | code

【2】A Large-scale Comprehensive Dataset and Copy-overlap Aware Evaluation Protocol for Segment-level Video Copy Detection(用于分段级视频复制检测的大规模综合数据集和复制重叠感知评估协议)

VCSL (Video Copy Segment Localization) dataset

paper | dataset, metric and benchmark codes

语义分割(Semantic Segmentation)

【1】Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels(使用不可靠伪标签的半监督语义分割)

paper | code | project

【2】Weakly Supervised Semantic Segmentation using Out-of-Distribution Data(使用分布外数据的弱监督语义分割)

paper | code

【3】Self-supervised Image-specific Prototype Exploration for Weakly Supervised Semantic Segmentation(弱监督语义分割的自监督图像特定原型探索)

paper | code

【4】Multi-class Token Transformer for Weakly Supervised Semantic Segmentation(用于弱监督语义分割的多类token Transformer)

paper | code

【5】Cross Language Image Matching for Weakly Supervised Semantic Segmentation(用于弱监督语义分割的跨语言图像匹配)

paper

【6】Learning Affinity from Attention: End-to-End Weakly-Supervised Semantic Segmentation with Transformers(从注意力中学习亲和力：使用 Transformers 的端到端弱监督语义分割)

paper | code

实例分割(Instance Segmentation)

【1】 E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance Segmentation(一种基于端到端轮廓的高质量高速实例分割方法)

paper | code

模型训练/泛化(Model Training/Generalization)

【1】Towards Efficient and Scalable Sharpness-Aware Minimization(迈向高效和可扩展的锐度感知最小化)

keywords: Sharp Local Minima, Large-Batch Training

paper

行为识别/动作识别/检测/分割/定位(Action/Activity Recognition)

【1】End-to-End Semi-Supervised Learning for Video Action Detection(视频动作检测的端到端半监督学习)

paper

【2】Learnable Irrelevant Modality Dropout for Multimodal Action Recognition on Modality-Specific Annotated Videos(模态特定注释视频上多模态动作识别的可学习不相关模态丢失)

paper

【3】Weakly Supervised Temporal Action Localization via Representative Snippet Knowledge Propagation(通过代表性片段知识传播的弱监督时间动作定位)

paper | code

图像分类(Image Classification)

【1】 GlideNet: Global, Local and Intrinsic based Dense Embedding NETwork for Multi-category Attributes Prediction(用于多类别属性预测的基于全局、局部和内在的密集嵌入网络)

keywords: multi-label classification

paper | code | project

联邦学习(Federated Learning)

【1】 Differentially Private Federated Learning with Local Regularization and Sparsification(局部正则化和稀疏化的差分私有联邦学习)

paper

GAN/生成式/对抗式(GAN/Generative/Adversarial)

【1】Shadows can be Dangerous: Stealthy and Effective Physical-world Adversarial Attack by Natural Phenomenon(阴影可能很危险：自然现象的隐秘而有效的物理世界对抗性攻击)

paper

【2】Protecting Facial Privacy: Generating Adversarial Identity Masks via Style-robust Makeup Transfer(保护面部隐私：通过风格稳健的化妆转移生成对抗性身份面具)

paper

【3】Adversarial Texture for Fooling Person Detectors in the Physical World(物理世界中愚弄人探测器的对抗性纹理)

paper

三维重建(3D Reconstruction)

【1】Neural Face Identification in a 2D Wireframe Projection of a Manifold Object(流形对象的二维线框投影中的神经人脸识别)

paper | [code](https://manycore- research.github.io/faceformer) | project

【2】Generating 3D Bio-Printable Patches Using Wound Segmentation and Reconstruction to Treat Diabetic Foot Ulcers()

keywords: semantic segmentation, 3D reconstruction, 3D bio-printers

paper

异常检测(Anomaly Detection)

【1】Generative Cooperative Learning for Unsupervised Video Anomaly Detection(用于无监督视频异常检测的生成式协作学习)

paper

持续学习(Continual Learning/Life-long Learning)

【1】On Generalizing Beyond Domains in Cross-Domain Continual Learning(关于跨域持续学习中的域外泛化)

paper

视觉预测(Vision-based Prediction)

【1】Motron: Multimodal Probabilistic Human Motion Forecasting(多模式概率人体运动预测)

paper

对比学习(Contrastive Learning)

【1】Selective-Supervised Contrastive Learning with Noisy Labels(带有噪声标签的选择性监督对比学习)

paper | code

迁移学习(Transfer Learning)

【1】A Simple Multi-Modality Transfer Learning Baseline for Sign Language Translation(用于手语翻译的简单多模态迁移学习基线)

paper

图像特征提取与匹配(Image feature extraction and matching)

【1】 Probabilistic Warp Consistency for Weakly-Supervised Semantic Correspondences(弱监督语义对应的概率扭曲一致性)

paper | code

量化(Quantization)

【1】IntraQ: Learning Synthetic Images with Intra-Class Heterogeneity for Zero-Shot Network Quantization(学习具有类内异质性的合成图像以进行零样本网络量化)

paper | code

数据增广(Data Augmentation)

【1】TeachAugment: Data Augmentation Optimization Using Teacher Knowledge(使用教师知识进行数据增强优化)

paper ｜ code

Transformer

【1】Delving Deep into the Generalization of Vision Transformers under Distribution Shifts(深入研究分布变化下的视觉Transformer的泛化)

keywords: out-of-distribution (OOD) generalization, Vision Transformers

paper | code

CNN

【1】DeltaCNN: End-to-End CNN Inference of Sparse Frame Differences in Videos(视频中稀疏帧差异的端到端 CNN 推断)

keywords: sparse convolutional neural network, video inference accelerating

paper

暂无分类

[5] Contrastive Conditional Neural Processes(对比条件神经过程)

paper

[4] Deep Rectangling for Image Stitching: A Learning Baseline(图像拼接的深度矩形：学习基线)(Image Stitching)

paper | code

[3] Online Learning of Reusable Abstract Models for Object Goal Navigation(对象目标导航可重用抽象模型的在线学习)

paper