【CVPR2022】论文列表与下载——PartTwo

CVPR2022将于6月22日召开🎉🎉🎉，本次会议共收录了2067篇论文。由于数量较多，本文将分四个子文章呈现，可直接点击论文标题获取文档。
📃第一部分, 📃第三部分, 📃 第四部分。

2. Part Two

Cannot See the Forest for the Trees: Aggregating Multiple Viewpoints To Better Classify Objects in Videos [supp]

Learning Canonical F-Correlation Projection for Compact Multiview Representation [supp]

DIFNet: Boosting Visual Information Flow for Image Captioning

Weakly Supervised Object Localization As Domain Adaption [supp]

Tencent-MVSE: A Large-Scale Benchmark Dataset for Multi-Modal Video Similarity Evaluation

Dynamic Prototype Convolution Network for Few-Shot Semantic Segmentation [supp]

Deep Orientation-Aware Functional Maps: Tackling Symmetry Issues in Shape Matching [supp]

Tree Energy Loss: Towards Sparsely Annotated Semantic Segmentation [supp]

Mr.BiQ: Post-Training Non-Uniform Quantization Based on Minimizing the Reconstruction Error [supp]

MatteFormer: Transformer-Based Image Matting via Prior-Tokens [supp]

Video Shadow Detection via Spatio-Temporal Interpolation Consistency Training [supp]

Ranking Distance Calibration for Cross-Domain Few-Shot Learning [supp]

Robust and Accurate Superquadric Recovery: A Probabilistic Approach [supp]

Zero-Shot Text-Guided Object Generation With Dream Fields [supp]

Learning Pixel Trajectories With Multiscale Contrastive Random Walks

Self-Supervised Correlation Mining Network for Person Image Generation

Grounding Answers for Visual Questions Asked by Visually Impaired People [supp]

Task Adaptive Parameter Sharing for Multi-Task Learning [supp]

Sparse Instance Activation for Real-Time Instance Segmentation

Automatic Color Image Stitching Using Quaternion Rank-1 Alignment [supp]

VisualGPT: Data-Efficient Adaptation of Pretrained Language Models for Image Captioning [supp]

ESCNet: Gaze Target Detection With the Understanding of 3D Scenes [supp]

Can You Spot the Chameleon? Adversarially Camouflaging Images From Co-Salient Object Detection

Finding Badly Drawn Bunnies [supp]

Point2Cyl: Reverse Engineering 3D Objects From Point Clouds to Extrusion Cylinders [supp]

All-Photon Polarimetric Time-of-Flight Imaging [supp]

MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation [supp]

Surface-Aligned Neural Radiance Fields for Controllable 3D Human Synthesis [supp]

Learning From Temporal Gradient for Semi-Supervised Action Recognition [supp]

Towards Implicit Text-Guided 3D Shape Generation [supp]

Audio-Driven Neural Gesture Reenactment With Video Motion Graphs [supp]

SoftCollage: A Differentiable Probabilistic Tree Generator for Image Collage [supp]

Transforming Model Prediction for Tracking [supp]

A Unified Framework for Implicit Sinkhorn Differentiation [supp]

DGECN: A Depth-Guided Edge Convolutional Network for End-to-End 6D Pose Estimation [supp]

Unsupervised Vision-Language Parsing: Seamlessly Bridging Visual Scene Graphs With Language Structures via Dependency Relationships

Open-Vocabulary Instance Segmentation via Robust Cross-Modal Pseudo-Labeling [supp]

Locality-Aware Inter- and Intra-Video Reconstruction for Self-Supervised Correspondence Learning [supp]

A Versatile Multi-View Framework for LiDAR-Based 3D Object Detection With Guidance From Panoptic Segmentation [supp]

Query and Attention Augmentation for Knowledge-Based Explainable Reasoning [supp]

Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality [supp]

RFNet: Unsupervised Network for Mutually Reinforcing Multi-Modal Image Registration and Fusion [supp]

Progressive Attention on Multi-Level Dense Difference Maps for Generic Event Boundary Detection [supp]

Interactron: Embodied Adaptive Object Detection [supp]

3D Scene Painting via Semantic Image Synthesis [supp]

MeMOT: Multi-Object Tracking With Memory

Revisiting Weakly Supervised Pre-Training of Visual Perception Models [supp]

Semi-Supervised Semantic Segmentation With Error Localization Network

Meta Convolutional Neural Networks for Single Domain Generalization [supp]

Generalizing Gaze Estimation With Rotation Consistency

Anomaly Detection via Reverse Distillation From One-Class Embedding [supp]

Fine-Grained Object Classification via Self-Supervised Pose Alignment [supp]

Spatio-Temporal Gating-Adjacency GCN for Human Motion Prediction [supp]

CellTypeGraph: A New Geometric Computer Vision Benchmark [supp]

Clustering Plotted Data by Image Segmentation

Accelerating Neural Network Optimization Through an Automated Control Theory Lens [supp]

Animal Kingdom: A Large and Diverse Dataset for Animal Behavior Understanding [supp]

Learning To Learn Across Diverse Data Biases in Deep Face Recognition [supp]

Back to Reality: Weakly-Supervised 3D Object Detection With Shape-Guided Label Enhancement [supp]

Long-Tail Recognition via Compositional Knowledge Transfer [supp]

EI-CLIP: Entity-Aware Interventional Contrastive Learning for E-Commerce Cross-Modal Retrieval [supp]

Multi-Dimensional, Nuanced and Subjective - Measuring the Perception of Facial Expressions [supp]

PyMiceTracking: An Open-Source Toolbox for Real-Time Behavioral Neuroscience Experiments

Self-Taught Metric Learning Without Labels [supp]

MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition [supp]

Fine-Grained Temporal Contrastive Learning for Weakly-Supervised Temporal Action Localization

Embracing Single Stride 3D Object Detector With Sparse Transformer [supp]

Multidimensional Belief Quantification for Label-Efficient Meta-Learning [supp]

UTC: A Unified Transformer With Inter-Task Contrastive Learning for Visual Dialog

Relieving Long-Tailed Instance Segmentation via Pairwise Class Balance [supp]

Online Convolutional Re-Parameterization [supp]

Mimicking the Oracle: An Initial Phase Decorrelation Approach for Class Incremental Learning [supp]

RIDDLE: Lidar Data Compression With Range Image Deep Delta Encoding [supp]

RelTransformer: A Transformer-Based Long-Tail Visual Relationship Recognition [supp]

HODEC: Towards Efficient High-Order DEcomposed Convolutional Neural Networks

RigidFlow: Self-Supervised Scene Flow Learning on Point Clouds by Local Rigidity Prior [supp]

Smooth Maximum Unit: Smooth Activation Function for Deep Networks Using Smoothing Maximum Technique [supp]

Learning Invisible Markers for Hidden Codes in Offline-to-Online Photography [supp]

Personalized Image Aesthetics Assessment With Rich Attributes

Task2Sim: Towards Effective Pre-Training and Transfer From Synthetic Data [supp]

Part-Based Pseudo Label Refinement for Unsupervised Person Re-Identification [supp]

Bridging the Gap Between Learning in Discrete and Continuous Environments for Vision-and-Language Navigation [supp]

HDNet: High-Resolution Dual-Domain Learning for Spectral Compressive Imaging

OW-DETR: Open-World Detection Transformer [supp]

Learning Deep Implicit Functions for 3D Shapes With Dynamic Code Clouds [supp]

Reversible Vision Transformers [supp]

Amodal Panoptic Segmentation [supp]

Gravitationally Lensed Black Hole Emission Tomography [supp]

3D-Aware Image Synthesis via Learning Structural and Textural Representations [supp]

Text-to-Image Synthesis Based on Object-Guided Joint-Decoding Transformer [supp]

Correlation Verification for Image Retrieval [supp]

Unsupervised Vision-and-Language Pre-Training via Retrieval-Based Multi-Granular Alignment [supp]

Protecting Facial Privacy: Generating Adversarial Identity Masks via Style-Robust Makeup Transfer [supp]

PONI: Potential Functions for ObjectGoal Navigation With Interaction-Free Learning [supp]

Noise Is Also Useful: Negative Correlation-Steered Latent Contrastive Learning

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

Spatially-Adaptive Multilayer Selection for GAN Inversion and Editing

Self-Supe