Spatial-Temporal Person Re-identification

Most of current person re-identification (ReID) methods neglect a spatial-temporal constraint. Given a query image, conventional methods compute the feature distances between the query image and all the gallery images and return a similarity ranked table... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Person Re-Identification DukeMTMC-reID st-ReID(RE, RK,Cam) Rank-1 94.5 # 1
MAP 92.7 # 1
Person Re-Identification Market-1501 st-ReID(RE, RK) Rank-1 98.0 # 1
MAP 95.5 # 2
Rank-5 98.9 # 1
Rank-10 99.1 # 1

Methods used in the Paper


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