Search Results for author: Chang-Tsun Li

Found 18 papers, 2 papers with code

Cross-Age Contrastive Learning for Age-Invariant Face Recognition

1 code implementation18 Dec 2023 Haoyi Wang, Victor Sanchez, Chang-Tsun Li

Cross-age facial images are typically challenging and expensive to collect, making noise-free age-oriented datasets relatively small compared to widely-used large-scale facial datasets.

Age-Invariant Face Recognition Contrastive Learning +1

Deep Learning Techniques for Video Instance Segmentation: A Survey

no code implementations19 Oct 2023 Chenhao Xu, Chang-Tsun Li, Yongjian Hu, Chee Peng Lim, Douglas Creighton

Video instance segmentation, also known as multi-object tracking and segmentation, is an emerging computer vision research area introduced in 2019, aiming at detecting, segmenting, and tracking instances in videos simultaneously.

Action Recognition Instance Segmentation +6

Deepfake Detection via Joint Unsupervised Reconstruction and Supervised Classification

no code implementations24 Nov 2022 Bosheng Yan, Chang-Tsun Li, Xuequan Lu

Most of the previous methods use the backbone network to extract global features for making predictions and only employ binary supervision (i. e., indicating whether the training instances are fake or authentic) to train the network.

Classification DeepFake Detection +1

Improving Face-Based Age Estimation with Attention-Based Dynamic Patch Fusion

no code implementations19 Dec 2021 Haoyi Wang, Victor Sanchez, Chang-Tsun Li

Since the proposed RMHHA mechanism ranks the discovered patches based on their importance, the length of the learning path of each patch in the FusionNet is proportional to the amount of information it carries (the longer, the more important).

Age Estimation

Beyond PRNU: Learning Robust Device-Specific Fingerprint for Source Camera Identification

no code implementations3 Nov 2021 Manisha, Chang-Tsun Li, Xufeng Lin, Karunakar A. Kotegar

Source camera identification tools assist image forensic investigators to associate an image in question with a suspect camera.

On the detection-to-track association for online multi-object tracking

no code implementations1 Jul 2021 Xufeng Lin, Chang-Tsun Li, Victor Sanchez, Carsten Maple

Driven by recent advances in object detection with deep neural networks, the tracking-by-detection paradigm has gained increasing prevalence in the research community of multi-object tracking (MOT).

Multi-Object Tracking object-detection +2

Deep Learning for Predictive Analytics in Reversible Steganography

no code implementations13 Jun 2021 Ching-Chun Chang, Xu Wang, Sisheng Chen, Isao Echizen, Victor Sanchez, Chang-Tsun Li

Given that reversibility is governed independently by the coding module, we narrow our focus to the incorporation of neural networks into the analytics module, which serves the purpose of predicting pixel intensities and a pivotal role in determining capacity and imperceptibility.

DeepfakeUCL: Deepfake Detection via Unsupervised Contrastive Learning

no code implementations23 Apr 2021 Sheldon Fung, Xuequan Lu, Chao Zhang, Chang-Tsun Li

Extensive experiments show that our unsupervised learning method enables comparable detection performance to state-of-the-art supervised techniques, in both the intra- and inter-dataset settings.

Contrastive Learning DeepFake Detection +1

Multi-Domain Adversarial Feature Generalization for Person Re-Identification

no code implementations25 Nov 2020 Shan Lin, Chang-Tsun Li, Alex C. Kot

To make Person Re-ID systems more practical and scalable, several cross-dataset domain adaptation methods have been proposed, which achieve high performance without the labeled data from the target domain.

Domain Generalization Person Re-Identification +1

Age-Oriented Face Synthesis with Conditional Discriminator Pool and Adversarial Triplet Loss

no code implementations1 Jul 2020 Haoyi Wang, Victor Sanchez, Chang-Tsun Li

In this paper, we propose a method for the age-oriented face synthesis task that achieves a high synthesis accuracy with strong identity permanence capabilities.

Face Generation

On Addressing the Impact of ISO Speed upon PRNU and Forgery Detection

no code implementations20 Jun 2020 Yijun Quan, Chang-Tsun Li

Due to such dependency, we postulate that a correlation predictor is ISO speed-specific, i. e. \textit{reliable correlation predictions can only be made when a correlation predictor is trained with images of similar ISO speeds to the image in question}.

Attribute Image Forgery Detection

Warwick Image Forensics Dataset for Device Fingerprinting In Multimedia Forensics

no code implementations22 Apr 2020 Yijun Quan, Chang-Tsun Li, Yujue Zhou, Li Li

Device fingerprints like sensor pattern noise (SPN) are widely used for provenance analysis and image authentication.

Image Forensics

Atypical Facial Landmark Localisation with Stacked Hourglass Networks: A Study on 3D Facial Modelling for Medical Diagnosis

no code implementations5 Sep 2019 Gary Storey, Ahmed Bouridane, Richard Jiang, Chang-Tsun Li

While facial biometrics has been widely used for identification purpose, it has recently been researched as medical biometrics for a range of diseases.

Face Alignment Facial Landmark Detection +1

Homogeneous Feature Transfer and Heterogeneous Location Fine-tuning for Cross-City Property Appraisal Framework

no code implementations11 Dec 2018 Yihan Guo, Shan Lin, Xiao Ma, Jay Bal, Chang-Tsun Li

Most existing real estate appraisal methods focus on building accuracy and reliable models from a given dataset but pay little attention to the extensibility of their trained model.

Fusion Network for Face-based Age Estimation

no code implementations27 Jul 2018 Haoyi Wang, Xingjie Wei, Victor Sanchez, Chang-Tsun Li

Convolutional Neural Networks (CNN) have been applied to age-related research as the core framework.

Age Estimation MORPH

Multi-task Mid-level Feature Alignment Network for Unsupervised Cross-Dataset Person Re-Identification

no code implementations4 Jul 2018 Shan Lin, Haoliang Li, Chang-Tsun Li, Alex ChiChung Kot

Most existing person re-identification (Re-ID) approaches follow a supervised learning framework, in which a large number of labelled matching pairs are required for training.

Attribute Person Re-Identification

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