J
Jianming Zhang
Researcher at Changsha University of Science and Technology
Publications - 25
Citations - 1562
Jianming Zhang is an academic researcher from Changsha University of Science and Technology. The author has contributed to research in topics: Convolutional neural network & Video tracking. The author has an hindex of 16, co-authored 25 publications receiving 999 citations.
Papers
More filters
Journal ArticleDOI
A Cascaded R-CNN With Multiscale Attention and Imbalanced Samples for Traffic Sign Detection
TL;DR: A cascaded R-CNN to obtain the multiscale features in pyramids to solve the undetection and false detection of traffic sign detection and the data augment method expands the German traffic sign training dataset by simulation of complex environment changes.
Journal ArticleDOI
A Real-Time Chinese Traffic Sign Detection Algorithm Based on Modified YOLOv2
TL;DR: This paper proposes an end-to-end convolutional network inspired by YOLOv2 to achieve real-time Chinese traffic sign detection and demonstrates that the proposed method is the faster and more robust.
Journal ArticleDOI
Lightweight deep network for traffic sign classification
TL;DR: Two novel lightweight networks are proposed that can obtain higher recognition precision while preserving less trainable parameters in the models and can be useful when deploying deep convolutional neural networks (CNNs) on mobile embedded devices.
Journal ArticleDOI
Spatial and semantic convolutional features for robust visual object tracking
TL;DR: A novel model updating strategy is presented, and peak sidelobe ratio (PSR) and skewness are exploited to measure the comprehensive fluctuation of response map for efficient tracking performance.
Journal ArticleDOI
Visual object tracking based on residual network and cascaded correlation filters
TL;DR: A tracking algorithm based on features extracted by residual network called Resnet features and cascaded correlation filters to improve precision and accuracy is proposed and performs favorably against other state-of-the-art trackers.