CVPR 2019

1,639 papers

Top Research Directions

Research directions most represented by CVPR 2019 papers.

Generalizing from Synthetic Data to the Real World 28
Preserving Tiny Features Against Spatial Resolution Degradation 24
Adversarial Training for Domain Invariant Representations 21
Deep Learning on Unstructured 3D Point Clouds 19
Resolving Depth Ambiguity in Monocular 3D Reconstruction 18
Compressing Deep Networks for Edge Hardware Constraints 18
Test Time Adaptation for Distribution Shift 17
Learning Depth Estimation without Dense Ground Truth 16
Bypassing the Computational Bottleneck of Adversarial Training 16
Disentangling Attribute Control in Generative Models 15
Cascaded Error Propagation in 2D to 3D Lifting 15
Why Theoretical FLOPs Fail to Predict Real Latency 15
Accelerating Neural Architecture Search Without Full Model Training 15
The Sensitivity of Multi-Objective Loss Balancing 13
Probabilistic Trajectory Forecasting for Autonomous Systems 12

Top Authors

AuthorPapers
Wei Liu33
Alan Yuille15
Dacheng Tao14
Ling Shao14
Ming-Hsuan Yang14
Xiaogang Wang14
Chunhua Shen13
Jiaya Jia13
Luc Van Gool12
Marc Pollefeys12
Baoyuan Wu11
Jie Zhou11
Ming-Ming Cheng11
Wangmeng Zuo11
Andreas Geiger10
Anton van den Hengel10
Chen Change Loy10
Jiebo Luo10
Qi Tian10
Rongrong Ji10

Impactful Papers

Papers from CVPR 2019 that shaped research clusters.

Foundational

Influential

Papers

Title
Panoptic Segmentation.
Parallel Optimal Transport GAN
Parallel Optimal Transport GAN.
Parametric Noise Injection: Trainable Randomness to Improve Deep Neural Network Robustness Against Adversarial Attack
Parametric Noise Injection: Trainable Randomness to Improve Deep Neural Network Robustness Against Adversarial Attack.
Parametric Skeleton Generation via Gaussian Mixture Models
Parsing R-CNN for Instance-Level Human Analysis.
Partial Order Pruning: For Best Speed/Accuracy Trade-Off in Neural Architecture Search
PartNet: A Large-Scale Benchmark for Fine-Grained and Hierarchical Part-Level 3D Object Understanding
PartNet: A Recursive Part Decomposition Network for Fine-Grained and Hierarchical Shape Segmentation
Part-Regularized Near-Duplicate Vehicle Re-Identification
Patch-Based Discriminative Feature Learning for Unsupervised Person Re-Identification.
Patch-Based Progressive 3D Point Set Upsampling
Path-Invariant Map Networks.
Pattern-Affinitive Propagation Across Depth, Surface Normal and Semantic Segmentation
Pay Attention! - Robustifying a Deep Visuomotor Policy Through Task-Focused Visual Attention.
PCAN: 3D Attention Map Learning Using Contextual Information for Point Cloud Based Retrieval.
PDE Acceleration for Active Contours.
Pedestrian Detection With Autoregressive Network Phases
Peeking Into the Future: Predicting Future Person Activities and Locations in Videos
PEPSI : Fast Image Inpainting With Parallel Decoding Network
Perceive Where to Focus: Learning Visibility-Aware Part-Level Features for Partial Person Re-Identification.
Personalized Estimation of Engagement From Videos Using Active Learning With Deep Reinforcement Learning
Perturbation Analysis of the 8-Point Algorithm: A Case Study for Wide FoV Cameras
Phase-Only Image Based Kernel Estimation for Single Image Blind Deblurring
Phase-Only Image Based Kernel Estimation for Single Image Blind Deblurring.
PhotoApp: Photorealistic Appearance Editing of Head Portraits
Photometric Mesh Optimization for Video-Aligned 3D Object Reconstruction
Photon-Flooded Single-Photon 3D Cameras
Photo Wake-Up: 3D Character Animation From a Single Photo.
PIEs: Pose Invariant Embeddings
PifPaf: Composite Fields for Human Pose Estimation.
Pixel-Adaptive Convolutional Neural Networks
PlaneRCNN: 3D Plane Detection and Reconstruction From a Single Image
Pluralistic Image Completion
Pluralistic Image Completion.
PMS-Net: Robust Haze Removal Based on Patch Map for Single Images
Point Cloud Oversegmentation With Graph-Structured Deep Metric Learning
PointConv: Deep Convolutional Networks on 3D Point Clouds
PointFlowNet: Learning Representations for Rigid Motion Estimation From Point Clouds
Point in, Box Out: Beyond Counting Persons in Crowds
Pointing Novel Objects in Image Captioning
Pointing Novel Objects in Image Captioning.
PointNetLK: Robust & Efficient Point Cloud Registration Using PointNet
PointPillars: Fast Encoders for Object Detection From Point Clouds.
PointRCNN: 3D Object Proposal Generation and Detection From Point Cloud.
Point-To-Pose Voting Based Hand Pose Estimation Using Residual Permutation Equivariant Layer
PointWeb: Enhancing Local Neighborhood Features for Point Cloud Processing
Polarimetric Camera Calibration Using an LCD Monitor
Polynomial Representation for Persistence Diagram

« prev Page 23/33 next »