Search Results for author: Ming-Ching Chang

Found 33 papers, 9 papers with code

A Comprehensive Review of Machine Learning Advances on Data Change: A Cross-Field Perspective

no code implementations20 Feb 2024 Jeng-Lin Li, Chih-Fan Hsu, Ming-Ching Chang, Wei-Chao Chen

In this review, we regroup domain shift and concept drift into a single research problem, namely the data change problem, with a systematic overview of state-of-the-art methods in the two research fields.

Improving Limited Supervised Foot Ulcer Segmentation Using Cross-Domain Augmentation

no code implementations16 Jan 2024 Shang-Jui Kuo, Po-Han Huang, Chia-Ching Lin, Jeng-Lin Li, Ming-Ching Chang

Existing segmentation models relying on extensive annotations are impractical in real-world scenarios with limited annotated data.

Segmentation

Scale-Aware Crowd Count Network with Annotation Error Correction

no code implementations28 Dec 2023 Yi-Kuan Hsieh, Jun-Wei Hsieh, Yu-Chee Tseng, Ming-Ching Chang, Li Xin

Furthermore, the use of a fixed Gaussian kernel fails to account for the varying pixel distribution with respect to the camera distance.

Crowd Counting

A New Benchmark and Model for Challenging Image Manipulation Detection

no code implementations23 Nov 2023 Zhenfei Zhang, Mingyang Li, Ming-Ching Chang

Existing Image Manipulation Detection (IMD) methods are mainly based on detecting anomalous features arisen from image editing or double compression artifacts.

Image Manipulation Image Manipulation Detection

MixNet: Toward Accurate Detection of Challenging Scene Text in the Wild

1 code implementation23 Aug 2023 Yu-Xiang Zeng, Jun-Wei Hsieh, Xin Li, Ming-Ching Chang

Detecting small scene text instances in the wild is particularly challenging, where the influence of irregular positions and nonideal lighting often leads to detection errors.

Scene Text Detection Text Detection

The 7th AI City Challenge

no code implementations15 Apr 2023 Milind Naphade, Shuo Wang, David C. Anastasiu, Zheng Tang, Ming-Ching Chang, Yue Yao, Liang Zheng, Mohammed Shaiqur Rahman, Meenakshi S. Arya, Anuj Sharma, Qi Feng, Vitaly Ablavsky, Stan Sclaroff, Pranamesh Chakraborty, Sanjita Prajapati, Alice Li, Shangru Li, Krishna Kunadharaju, Shenxin Jiang, Rama Chellappa

The AI City Challenge's seventh edition emphasizes two domains at the intersection of computer vision and artificial intelligence - retail business and Intelligent Traffic Systems (ITS) - that have considerable untapped potential.

Retrieval

SMILEtrack: SiMIlarity LEarning for Occlusion-Aware Multiple Object Tracking

2 code implementations16 Nov 2022 Yu-Hsiang Wang, Jun-Wei Hsieh, Ping-Yang Chen, Ming-Ching Chang, Hung Hin So, Xin Li

Second, we develop a Similarity Matching Cascade (SMC) module with a novel GATE function for robust object matching across consecutive video frames, further enhancing MOT performance.

 Ranked #1 on Multi-Object Tracking on MOT20 (using extra training data)

Multi-Object Tracking Multiple Object Tracking +3

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

no code implementations13 Nov 2022 Yi-Kuan Hsieh, Jun-Wei Hsieh, Yu-Chee Tseng, Ming-Ching Chang, Bor-Shiun Wang

We then approximate the joint distribution of crowd density maps with the full covariance of multiple scales and derive a low-rank approximation for tractability and efficient implementation.

Crowd Counting

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

no code implementations3 Oct 2022 Yi-Chun Wang, Jun-Wei Hsieh, Ming-Ching Chang

The first architecture search determines the inner cell structure, and the second architecture search considers exponentially growing paths to finalize the outer structure of the network.

Segmentation Semantic Segmentation

FedDig: Robust Federated Learning Using Data Digest to Represent Absent Clients

no code implementations3 Oct 2022 Chih-Fan Hsu, Ming-Ching Chang, Wei-Chao Chen

We address this issue by generating secure data digests from the raw data and using them to guide model training at the FL moderator.

Federated Learning

Class-Specific Channel Attention for Few-Shot Learning

no code implementations3 Sep 2022 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.

Few-Shot Classification and Segmentation Few-Shot Image Classification +3

Open-Eye: An Open Platform to Study Human Performance on Identifying AI-Synthesized Faces

no code implementations13 May 2022 Hui Guo, Shu Hu, Xin Wang, Ming-Ching Chang, Siwei Lyu

In this work, we develop an online platform called Open-eye to study the human performance of AI-synthesized face detection.

Face Detection

GAN-generated Faces Detection: A Survey and New Perspectives

no code implementations15 Feb 2022 Xin Wang, Hui Guo, Shu Hu, Ming-Ching Chang, Siwei Lyu

Generative Adversarial Networks (GAN) have led to the generation of very realistic face images, which have been used in fake social media accounts and other disinformation matters that can generate profound impacts.

Face Detection

VocBench: A Neural Vocoder Benchmark for Speech Synthesis

1 code implementation6 Dec 2021 Ehab A. AlBadawy, Andrew Gibiansky, Qing He, JiLong Wu, Ming-Ching Chang, Siwei Lyu

We perform a subjective and objective evaluation to compare the performance of each vocoder along a different axis.

Speech Synthesis

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.

Robust Attentive Deep Neural Network for Exposing GAN-generated Faces

no code implementations5 Sep 2021 Hui Guo, Shu Hu, Xin Wang, Ming-Ching Chang, Siwei Lyu

However, images from existing public datasets do not represent real-world scenarios well enough in terms of view variations and data distributions (where real faces largely outnumber synthetic faces).

Face Detection

Eyes Tell All: Irregular Pupil Shapes Reveal GAN-generated Faces

no code implementations1 Sep 2021 Hui Guo, Shu Hu, Xin Wang, Ming-Ching Chang, Siwei Lyu

Generative adversary network (GAN) generated high-realistic human faces have been used as profile images for fake social media accounts and are visually challenging to discern from real ones.

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

MagGAN: High-Resolution Face Attribute Editing with Mask-Guided Generative Adversarial Network

no code implementations3 Oct 2020 Yi Wei, Zhe Gan, Wenbo Li, Siwei Lyu, Ming-Ching Chang, Lei Zhang, Jianfeng Gao, Pengchuan Zhang

We present Mask-guided Generative Adversarial Network (MagGAN) for high-resolution face attribute editing, in which semantic facial masks from a pre-trained face parser are used to guide the fine-grained image editing process.

Attribute Generative Adversarial Network +1

Robust Adversarial Perturbation on Deep Proposal-based Models

no code implementations16 Sep 2018 Yuezun Li, Daniel Tian, Ming-Ching Chang, Xiao Bian, Siwei Lyu

Adversarial noises are useful tools to probe the weakness of deep learning based computer vision algorithms.

Instance Segmentation Region Proposal +2

Exploring the Vulnerability of Single Shot Module in Object Detectors via Imperceptible Background Patches

no code implementations16 Sep 2018 Yuezun Li, Xiao Bian, Ming-Ching Chang, Siwei Lyu

In this paper, we focus on exploring the vulnerability of the Single Shot Module (SSM) commonly used in recent object detectors, by adding small perturbations to patches in the background outside the object.

Object Region Proposal

Multi-Scale Supervised Network for Human Pose Estimation

no code implementations5 Aug 2018 Lipeng Ke, Ming-Ching Chang, Honggang Qi, Siwei Lyu

Human pose estimation is an important topic in computer vision with many applications including gesture and activity recognition.

Activity Recognition Keypoint Detection +1

Who did What at Where and When: Simultaneous Multi-Person Tracking and Activity Recognition

no code implementations3 Jul 2018 Wenbo Li, Ming-Ching Chang, Siwei Lyu

We present a bootstrapping framework to simultaneously improve multi-person tracking and activity recognition at individual, interaction and social group activity levels.

Activity Recognition Visual Tracking

In Ictu Oculi: Exposing AI Generated Fake Face Videos by Detecting Eye Blinking

3 code implementations7 Jun 2018 Yuezun Li, Ming-Ching Chang, Siwei Lyu

The new developments in deep generative networks have significantly improve the quality and efficiency in generating realistically-looking fake face videos.

Face Swapping

UA-DETRAC: A New Benchmark and Protocol for Multi-Object Detection and Tracking

no code implementations13 Nov 2015 Longyin Wen, Dawei Du, Zhaowei Cai, Zhen Lei, Ming-Ching Chang, Honggang Qi, Jongwoo Lim, Ming-Hsuan Yang, Siwei Lyu

In this work, we perform a comprehensive quantitative study on the effects of object detection accuracy to the overall MOT performance, using the new large-scale University at Albany DETection and tRACking (UA-DETRAC) benchmark dataset.

Multi-Object Tracking Object +2

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