Search Results for author: Ping-Yang Chen

Found 8 papers, 5 papers with code

SMILEtrack: SiMIlarity LEarning for Multiple Object Tracking

1 code implementation16 Nov 2022 Yu-Hsiang Wang, Jun-Wei Hsieh, Ping-Yang Chen, Ming-Ching Chang

This design strengthens the modeling of object motion and appearance features for data association.

 Ranked #1 on Multi-Object Tracking on MOT17 (using extra training data)

Association Multi-Object Tracking +3

Learnable Discrete Wavelet Pooling (LDW-Pooling) For Convolutional Networks

no code implementations13 Sep 2021 Bor-Shiun Wang, Jun-Wei Hsieh, Ming-Ching Chang, Ping-Yang Chen, Lipeng Ke, Siwei Lyu

We introduce the Learning Discrete Wavelet Pooling (LDW-Pooling) that can be applied universally to replace standard pooling operations to better extract features with improved accuracy and efficiency.

MS-DARTS: Mean-Shift Based Differentiable Architecture Search

1 code implementation23 Aug 2021 Jun-Wei Hsieh, Ming-Ching Chang, Ping-Yang Chen, Santanu Santra, Cheng-Han Chou, Chih-Sheng Huang

Our approach can improve bot the stability and accuracy of DARTS, by smoothing the loss landscape and sampling architecture parameters within a suitable bandwidth.

Parallel Residual Bi-Fusion Feature Pyramid Network for Accurate Single-Shot Object Detection

1 code implementation3 Dec 2020 Ping-Yang Chen, Ming-Ching Chang, Jun-Wei Hsieh, Yong-Sheng Chen

Feature Pyramid (FP) is widely used in recent visual detection, however the top-down pathway of FP cannot preserve accurate localization due to pooling shifting.

Multi-Object Tracking object-detection +1

CSPNet: A New Backbone that can Enhance Learning Capability of CNN

126 code implementations27 Nov 2019 Chien-Yao Wang, Hong-Yuan Mark Liao, I-Hau Yeh, Yueh-Hua Wu, Ping-Yang Chen, Jun-Wei Hsieh

Neural networks have enabled state-of-the-art approaches to achieve incredible results on computer vision tasks such as object detection.

Image Classification Real-Time Object Detection

Multiple-Instance Logistic Regression with LASSO Penalty

no code implementations13 Jul 2016 Ray-Bing Chen, Kuang-Hung Cheng, Sheng-Mao Chang, Shuen-Lin Jeng, Ping-Yang Chen, Chun-Hao Yang, Chi-Chun Hsia

In this work, we consider a manufactory process which can be described by a multiple-instance logistic regression model.


Cannot find the paper you are looking for? You can Submit a new open access paper.