ICCV 2019

HumanPose2D

TRB: A Novel Triplet Representation for Understanding 2D Human Body

Single-Stage Multi-Person Pose Machines

Single-Network Whole-Body Pose Estimation

Imitation Learning for Human Pose Prediction

Imitation Learning for Human Pose Prediction

Dynamic Kernel Distillation for Efficient Pose Estimation in Videos

 

HumanPose3D

Learning to Reconstruct 3D Human Pose and Shape via Model-Fitting in the Loop(SPIN)

On Boosting Single-Frame 3D Human Pose Estimation via Monocular Videos

Occlusion-Aware Networks for 3D Human Pose Estimation in Video

TexturePose: Supervising Human Mesh Estimation With Texture Consistency

GP2C: Geometric Projection Parameter Consensus for Joint 3D Pose and Focal Length Estimation in the Wild

Moulding Humans: Non-Parametric 3D Human Shape Estimation From Single Images

3DPeople: Modeling the Geometry of Dressed Humans

Optimizing Network Structure for 3D Human Pose Estimation

Camera Distance-Aware Top-Down Approach for 3D Multi-Person Pose Estimation From a Single RGB Image

Exploiting Spatial-Temporal Relationships for 3D Pose Estimation via Graph Convolutional Networks

Resolving 3D Human Pose Ambiguities With 3D Scene Constraints

Tex2Shape: Detailed Full Human Body Geometry From a Single Image

Monocular 3D Human Pose Estimation by Generation and Ordinal Ranking

HEMlets Pose: Learning Part-Centric Heatmap Triplets for Accurate 3D Human Pose Estimation

xR-EgoPose: Egocentric 3D Human Pose From an HMD Camera

DeepHuman: 3D Human Reconstruction From a Single Image

Holistic++ Scene Understanding: Single-View 3D Holistic Scene Parsing and Human Pose Estimation With Human-Object Interaction and Physical Commonsense

Delving Deep Into Hybrid Annotations for 3D Human Recovery in the Wild

Human Mesh Recovery From Monocular Images via a Skeleton-Disentangled Representation

Multi-Garment Net: Learning to Dress 3D People From Images

Learning Compositional Neural Information Fusion for Human Parsing

Everybody Dance Now

Three-D Safari: Learning to Estimate Zebra Pose, Shape, and Texture From Images “In the Wild”

 

HumanPose3D MultiView

Cross View Fusion for 3D Human Pose Estimation

Shape-Aware Human Pose and Shape Reconstruction Using Multi-View Images

Learnable Triangulation of Human Pose

 

Teacher Students

Teacher Supervises Students How to Learn From Partially Labeled Images for Facial Landmark Detection

UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation

Distilling Knowledge From a Deep Pose Regressor Network

Distill Knowledge From NRSfM for Weakly Supervised 3D Pose Learning

Similarity-Preserving Knowledge Distillation

Distillation-Based Training for Multi-Exit Architectures

Knowledge Distillation via Route Constrained Optimization

A Comprehensive Overhaul of Feature Distillation(CLOVA)

Customizing Student Networks From Heterogeneous Teachers via Adaptive Knowledge Amalgamation

Data-Free Learning of Student Networks

Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation

DSConv: Efficient Convolution Operator

On the Efficacy of Knowledge Distillation

Correlation Congruence for Knowledge Distillation

Dual Student: Breaking the Limits of the Teacher in Semi-Supervised Learning

 

Light-weight Network

Searching for MobileNetV3

ThunderNet: Towards Real-Time Generic Object Detection on Mobile Devices

Accelerate CNN via Recursive Bayesian Pruning

Data-Free Quantization Through Weight Equalization and Bias Correction

MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning

A Camera That CNNs: Towards Embedded Neural Networks on Pixel Processor Arrays

AdaTransform: Adaptive Data Transformation

Teacher Guided Architecture Search

Improved Techniques for Training Adaptive Deep Networks

HarDNet: A Low Memory Traffic Network

Fast and Practical Neural Architecture Search

 

Segmentation

YOLACT: Real-Time Instance Segmentation

 

ETC

EvalNorm: Estimating Batch Normalization Statistics for Evaluation

Transformable Bottleneck Networks

Adaptive Wing Loss for Robust Face Alignment via Heatmap Regression

Differentiable Learning-to-Group Channels via Groupable Convolutional Neural Networks

LIP: Local Importance-Based Pooling

Global Feature Guided Local Pooling

Information Entropy Based Feature Pooling for Convolutional Neural Networks