CVPR2022论文速递（2022.3.30）！共48篇

CVPR2022论文速递（2022.3.30）！共48篇

整理：AI算法与图像处理

CVPR2022论文和代码整理：Toward Compositional and High-Fidelity Text-to-Image Synthesis

论文/Paper: CHannel EXploration for CNN Model Compression

论文/Paper: None

FisherMatch: Semi-Supervised Rotation Regression via Entropy-based Filtering

论文/Paper: None

Integrative Few-Shot Learning for Classification and Segmentation

论文/Paper: None

OakInk: A Large-scale Knowledge Repository for Understanding Hand-Object Interaction

论文/Paper: None

EnvEdit: Environment Editing for Vision-and-Language Navigation

论文/Paper: None

Exploring Frequency Adversarial Attacks for Face Forgery Detection

论文/Paper: None

PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervision

论文/Paper: None

Learning a Structured Latent Space for Unsupervised Point Cloud Completion

论文/Paper: None

BARC: Learning to Regress 3D Dog Shape from Images by Exploiting Breed Information

论文/Paper: None

OSOP: A Multi-Stage One Shot Object Pose Estimation Framework

论文/Paper: None

Learning Structured Gaussians to Approximate Deep Ensembles

论文/Paper: None

Long-term Video Frame Interpolation via Feature Propagation

论文/Paper: None

Quantifying Societal Bias Amplification in Image Captioning

论文/Paper: None

Alignment-Uniformity aware Representation Learning for Zero-shot Video Classification

论文/Paper: Style-aware Discriminator for Controllable Image Translation

论文/Paper: None

Self-Supervised Image Representation Learning with Geometric Set Consistency

论文/Paper: None

Nested Collaborative Learning for Long-Tailed Visual Recognition

论文/Paper: None

Online Continual Learning on a Contaminated Data Stream with Blurry Task Boundaries

论文/Paper: None

SIOD: Single Instance Annotated Per Category Per Image for Object Detection

论文/Paper: None

Task-specific Inconsistency Alignment for Domain Adaptive Object Detection

论文/Paper: None

Balanced Multimodal Learning via On-the-fly Gradient Modulation

论文/Paper: None

CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters

论文/Paper: None

Dressing in the Wild by Watching Dance Videos

论文/Paper: None

Eigenlanes: Data-Driven Lane Descriptors for Structurally Diverse Lanes

论文/Paper: None

Uncertainty-Aware Adaptation for Self-Supervised 3D Human Pose Estimation

论文/Paper: None

MAT: Mask-Aware Transformer for Large Hole Image Inpainting

论文/Paper: None

Eigencontours: Novel Contour Descriptors Based on Low-Rank Approximation

论文/Paper: None

Pop-Out Motion: 3D-Aware Image Deformation via Learning the Shape Laplacian

论文/Paper: None

Zero-Query Transfer Attacks on Context-Aware Object Detectors

论文/Paper: None

Temporal Feature Alignment and Mutual Information Maximization for Video-Based Human Pose Estimation

论文/Paper: None

Affine Medical Image Registration with Coarse-to-Fine Vision Transformer

论文/Paper: Stable Feature Generation for Isolated Camera Supervised Person Re-IDentification

论文/Paper: None

SPAct: Self-supervised Privacy Preservation for Action Recognition

论文/Paper: None

SimT: Handling Open-set Noise for Domain Adaptive Semantic Segmentation

论文/Paper: None

3D Shape Reconstruction from 2D Images with Disentangled Attribute Flow

论文/Paper: None

ASM-Loc: Action-aware Segment Modeling for Weakly-Supervised Temporal Action Localization

论文/Paper: None

Long-term Visual Map Sparsification with Heterogeneous GNN

论文/Paper: None

Unified Transformer Tracker for Object Tracking

论文/Paper: None

Towards End-to-End Unified Scene Text Detection and Layout Analysis

论文/Paper: None

Text2Pos: Text-to-Point-Cloud Cross-Modal Localization

论文/Paper: None

LiDAR Snowfall Simulation for Robust 3D Object Detection

论文/Paper: None

Rethinking Semantic Segmentation: A Prototype View

论文/Paper: None

X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval

论文/Paper: Object Detection with Fully Cross-Transformer

论文/Paper: None

Registering Explicit to Implicit: Towards High-Fidelity Garment mesh Reconstruction from Single Images

论文/Paper: None

Clean Implicit 3D Structure from Noisy 2D STEM Images

论文/Paper: None

Equivariance Allows Handling Multiple Nuisance Variables When Analyzing Pooled Neuroimaging Datasets

论文/Paper: None

版权声明：本文内容由网络用户投稿，版权归原作者所有，本站不拥有其著作权，亦不承担相应法律责任。如果您发现本站中有涉嫌抄袭或描述失实的内容，请联系我们jiasou666@gmail.com 处理，核实后本网站将在24小时内删除侵权内容。