27 citations · 67 across the 14 of their papers we have counts for
5 papers · 1 filter
Video Person Re-identification using Attribute-enhanced Features
Tianrui Chai, Zhiyuan Chen, Annan Li +3
Video-based person re-identification (Re-ID) which aims to associate people across non-overlapping cameras using surveillance video is a challenging task. Pedestrian attribute, suc…
Frequency Domain Convolutional Neural Network: Accelerated CNN for Large Diabetic Retinopathy Image Classification
Ee Fey Goh, ZhiYuan Chen, Wei Xiang Lim
The conventional spatial convolution layers in the Convolutional Neural Networks (CNNs) are computationally expensive at the point where the training time could take days unless th…
IDEAL: Independent Domain Embedding Augmentation Learning
Zhiyuan Chen, Guang Yao, Wennan Ma +1
Many efforts have been devoted to designing sampling, mining, and weighting strategies in high-level deep metric learning (DML) loss objectives. However, little attention has been…
Attribute-aware Identity-hard Triplet Loss for Video-based Person Re-identification
Zhiyuan Chen, Annan Li, Shilu Jiang +1
Video-based person re-identification (Re-ID) is an important computer vision task. The batch-hard triplet loss frequently used in video-based person Re-ID suffers from the Distance…
A Temporal Attentive Approach for Video-Based Pedestrian Attribute Recognition
Zhiyuan Chen, Annan Li, Yunhong Wang
In this paper, we first tackle the problem of pedestrian attribute recognition by video-based approach. The challenge mainly lies in spatial and temporal modeling and how to integr…