221 citations
- Beijing Normal UniversityCN15 papers
- Dezhou UniversityCN9 papers
- Nanjing University of Aeronautics and AstronauticsCN9 papers
- Chinese Academy of SciencesCN8 papers
- Beijing Computational Science Research CenterCN6 papers
- Southeast UniversityCN6 papers
- Toronto Metropolitan UniversityCA6 papers
- Soochow UniversityCN5 papers
- Zhejiang UniversityCN5 papers
- Nanjing University of Posts and TelecommunicationsCN4 papers
- National University of SingaporeSG4 papers
- Peking UniversityCN4 papers
5 papers · 1 filter
Motion Estimation for Multi-Object Tracking using KalmanNet with Semantic-Independent Encoding
Jian Song, Wei Mei, Yunfeng Xu +4
Motion estimation is a crucial component in multi-object tracking (MOT). It predicts the trajectory of objects by analyzing the changes in their positions in consecutive frames of…
Improving the Transferability of Adversarial Examples with Resized-Diverse-Inputs, Diversity-Ensemble and Region Fitting
Junhua Zou, Zhisong Pan, Junyang Qiu +3
We introduce a three stage pipeline: resized-diverse-inputs (RDIM), diversity-ensemble (DEM) and region fitting, that work together to generate transferable adversarial examples. W…
Grafted network for person re-identification
Jiabao Wang, Yang Li, Shanshan Jiao +2
Convolutional neural networks have shown outstanding effectiveness in person re-identification (re-ID). However, the models always have large number of parameters and much computat…
A heterogeneous branch and multi-level classification network for person re-identification
Jiabao Wang, Yang Li, Yangshuo Zhang +2
Convolutional neural networks with multiple branches have recently been proved highly effective in person re-identification (re-ID). Researchers design multi-branch networks using…
A Biologically Inspired Feature Enhancement Framework for Zero-Shot Learning
Zhongwu Xie, Weipeng Cao, Xizhao Wang +3
Most of the Zero-Shot Learning (ZSL) algorithms currently use pre-trained models as their feature extractors, which are usually trained on the ImageNet data set by using deep neura…