activity
20192023
most citedCSPNet: A New Backbone that can Enhance Learning Capability of CNN

361 citations · 416 across the 14 of their papers we have counts for

collaborators
Showing 2022 · cs.CVShow all

7 papers · 2 filters

cs.CV2022★ 3 cited

SARAS-Net: Scale and Relation Aware Siamese Network for Change Detection

Chao-Peng Chen, Jun-Wei Hsieh, Ping-Yang Chen +2

Change detection (CD) aims to find the difference between two images at different times and outputs a change map to represent whether the region has changed or not. To achieve a be…

cs.CV2022★ 10 cited

SMILEtrack: SiMIlarity LEarning for Occlusion-Aware Multiple Object Tracking

Yu-Hsiang Wang, Jun-Wei Hsieh, Ping-Yang Chen +3

Despite recent progress in Multiple Object Tracking (MOT), several obstacles such as occlusions, similar objects, and complex scenes remain an open challenge. Meanwhile, a systemat…

cs.CV2022

Scale-Aware Crowd Counting Using a Joint Likelihood Density Map and Synthetic Fusion Pyramid Network

Yi-Kuan Hsieh, Jun-Wei Hsieh, Yu-Chee Tseng +2

We develop a Synthetic Fusion Pyramid Network (SPF-Net) with a scale-aware loss function design for accurate crowd counting. Existing crowd-counting methods assume that the trainin…

cs.CV2022

NAS-based Recursive Stage Partial Network (RSPNet) for Light-Weight Semantic Segmentation

Yi-Chun Wang, Jun-Wei Hsieh, Ming-Ching Chang

Current NAS-based semantic segmentation methods focus on accuracy improvements rather than light-weight design. In this paper, we proposed a two-stage framework to design our NAS-b…

cs.CV2022

Siamese-NAS: Using Trained Samples Efficiently to Find Lightweight Neural Architecture by Prior Knowledge

Yu-Ming Zhang, Jun-Wei Hsieh, Chun-Chieh Lee +1

In the past decade, many architectures of convolution neural networks were designed by handcraft, such as Vgg16, ResNet, DenseNet, etc. They all achieve state-of-the-art level on d…

cs.CV2022

Class-Specific Channel Attention for Few-Shot Learning

Ying-Yu Chen, Jun-Wei Hsieh, Ming-Ching Chang

Few-Shot Learning (FSL) has attracted growing attention in computer vision due to its capability in model training without the need for excessive data. FSL is challenging because t…