In this paper, we propose a lightweight Feature Pyramid Branch (FPB) to extract features from different layers of networks and aggregate them in a bidirectional pyramid structure.
Ranked #6 on Person Re-Identification on CUHK03 labeled
In particular, we show that the feature diversity can be well achieved with the use of multiple dropping branches by setting individual dropping ratio for each branch.
Learning diverse features is key to the success of person re-identification.
Ranked #3 on Person Re-Identification on Market-1501-C
Capsules as well as dynamic routing between them are most recently proposed structures for deep neural networks.
Ranked #5 on Image Classification on smallNORB
In this study, we explore capsule networks with dynamic routing for text classification.
Ranked #6 on Sentiment Analysis on MR
Despite the success of many advanced tracking methods in this area, tracking targets with drastic variation of appearance such as deformation, view change and partial occlusion in video sequences is still a challenge in practical applications.