Parsing R-CNN for Instance-Level Human Analysis

Instance-level human analysis is common in real-life scenarios and has multiple manifestations, such as human part segmentation, dense pose estimation, human-object interactions, etc. Models need to distinguish different human instances in the image panel and learn rich features to represent the details of each instance... (read more)

PDF Abstract CVPR 2019 PDF CVPR 2019 Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Human Part Segmentation CIHP Parsing R-CNN + ResNext101 Mean IoU 61.1 # 1
Pose Estimation DensePose-COCO Parsing R-CNN + ResNext101 AP 61.6 # 1
Human Part Segmentation MHP v2.0 Parsing R-CNN + ResNext101 Mean IoU 41.8 # 1

Methods used in the Paper


METHOD TYPE
Average Pooling
Pooling Operations
ResNeXt Block
Skip Connection Blocks
Grouped Convolution
Convolutions
Global Average Pooling
Pooling Operations
Residual Connection
Skip Connections
ReLU
Activation Functions
Kaiming Initialization
Initialization
1x1 Convolution
Convolutions
Convolution
Convolutions
Batch Normalization
Normalization
ResNeXt
Convolutional Neural Networks