Search Results for author: C. -C. Jay Kuo

Found 151 papers, 27 papers with code

Knowledge Graph Embedding: An Overview

no code implementations21 Sep 2023 Xiou Ge, Yun-Cheng Wang, Bin Wang, C. -C. Jay Kuo

We will also discuss an emerging approach for KG completion which leverages pre-trained language models (PLMs) and textual descriptions of entities and relations and offer insights into the integration of KGE embedding methods with PLMs for KG completion.

Knowledge Graph Embedding Link Prediction

Bias and Fairness in Chatbots: An Overview

no code implementations16 Sep 2023 Jintang Xue, Yun-Cheng Wang, Chengwei Wei, Xiaofeng Liu, Jonghye Woo, C. -C. Jay Kuo

Thus, a comprehensive overview on bias and fairness in chatbot systems is given in this paper.

Chatbot Fairness

Unsupervised Green Object Tracker (GOT) without Offline Pre-training

no code implementations16 Sep 2023 Zhiruo Zhou, Suya You, C. -C. Jay Kuo

The labeling cost and the huge computational complexity hinder their applications on edge devices.

Object Tracking

AsyncET: Asynchronous Learning for Knowledge Graph Entity Typing with Auxiliary Relations

no code implementations30 Aug 2023 Yun-Cheng Wang, Xiou Ge, Bin Wang, C. -C. Jay Kuo

Previously, KG embedding (KGE) methods tried to solve the KGET task by introducing an auxiliary relation, 'hasType', to model the relationship between entities and their types.

Entity Typing Knowledge Graphs +1

A Comprehensive Overview of Computational Nuclei Segmentation Methods in Digital Pathology

no code implementations16 Aug 2023 Vasileios Magoulianitis, Catherine A. Alexander, C. -C. Jay Kuo

Nuclei segmentation is an important task, as it detects the nuclei cells over background tissue and gives rise to the topology, size, and count of nuclei which are determinant factors for cancer detection.

Explainable Models

Blind Video Quality Assessment at the Edge

no code implementations17 Jun 2023 Zhanxuan Mei, Yun-Cheng Wang, C. -C. Jay Kuo

The usage of deep-learning-based methods is restricted by their large model sizes and high computational complexity.

feature selection Video Quality Assessment

Green Steganalyzer: A Green Learning Approach to Image Steganalysis

no code implementations6 Jun 2023 Yao Zhu, Xinyu Wang, Hong-Shuo Chen, Ronald Salloum, C. -C. Jay Kuo

A novel learning solution to image steganalysis based on the green learning paradigm, called Green Steganalyzer (GS), is proposed in this work.

Self-Supervised Learning Steganalysis

An Overview on Generative AI at Scale with Edge-Cloud Computing

no code implementations2 Jun 2023 Yun-Cheng Wang, Jintang Xue, Chengwei Wei, C. -C. Jay Kuo

The rapid development of GenAI systems has created a huge amount of new data on the Internet, posing new challenges to current computing and communication frameworks.

Cloud Computing

Knowledge Graph Embedding with 3D Compound Geometric Transformations

no code implementations1 Apr 2023 Xiou Ge, Yun-Cheng Wang, Bin Wang, C. -C. Jay Kuo

The cascade of 2D geometric transformations were exploited to model relations between entities in a knowledge graph (KG), leading to an effective KG embedding (KGE) model, CompoundE.

Knowledge Graph Embedding Link Prediction +1

Lightweight High-Performance Blind Image Quality Assessment

no code implementations23 Mar 2023 Zhanxuan Mei, Yun-Cheng Wang, Xingze He, Yong Yan, C. -C. Jay Kuo

Blind image quality assessment (BIQA) is a task that predicts the perceptual quality of an image without its reference.

Blind Image Quality Assessment feature selection +2

A Tiny Machine Learning Model for Point Cloud Object Classification

no code implementations20 Mar 2023 Min Zhang, Jintang Xue, Pranav Kadam, Hardik Prajapati, Shan Liu, C. -C. Jay Kuo

On the other hand, the model size and inference complexity of DGCNN are 42X and 1203X of those of Green-PointHop, respectively.

LSR: A Light-Weight Super-Resolution Method

no code implementations27 Feb 2023 Wei Wang, Xuejing Lei, Yueru Chen, Ming-Sui Lee, C. -C. Jay Kuo

A light-weight super-resolution (LSR) method from a single image targeting mobile applications is proposed in this work.

SSIM Super-Resolution

S3I-PointHop: SO(3)-Invariant PointHop for 3D Point Cloud Classification

no code implementations22 Feb 2023 Pranav Kadam, Hardik Prajapati, Min Zhang, Jintang Xue, Shan Liu, C. -C. Jay Kuo

Many point cloud classification methods are developed under the assumption that all point clouds in the dataset are well aligned with the canonical axes so that the 3D Cartesian point coordinates can be employed to learn features.

3D Point Cloud Classification Classification +1

gpcgc: a green point cloud geometry coding method

no code implementations13 Feb 2023 Qingyang Zhou, Shan Liu, C. -C. Jay Kuo

A low-complexity point cloud compression method called the Green Point Cloud Geometry Codec (GPCGC), is proposed to encode the 3D spatial coordinates of static point clouds efficiently.


Successive Subspace Learning for Cardiac Disease Classification with Two-phase Deformation Fields from Cine MRI

no code implementations21 Jan 2023 Xiaofeng Liu, Fangxu Xing, Hanna K. Gaggin, C. -C. Jay Kuo, Georges El Fakhri, Jonghye Woo

Cardiac cine magnetic resonance imaging (MRI) has been used to characterize cardiovascular diseases (CVD), often providing a noninvasive phenotyping tool.~While recently flourished deep learning based approaches using cine MRI yield accurate characterization results, the performance is often degraded by small training samples.

SALVE: Self-supervised Adaptive Low-light Video Enhancement

no code implementations22 Dec 2022 Zohreh Azizi, C. -C. Jay Kuo

A self-supervised adaptive low-light video enhancement method, called SALVE, is proposed in this work.

Low-Light Image Enhancement regression +1

LGSQE: Lightweight Generated Sample Quality Evaluatoin

no code implementations8 Nov 2022 Ganning Zhao, Vasileios Magoulianitis, Suya You, C. -C. Jay Kuo

Despite prolific work on evaluating generative models, little research has been done on the quality evaluation of an individual generated sample.

Recovering Sign Bits of DCT Coefficients in Digital Images as an Optimization Problem

no code implementations2 Nov 2022 Ruiyuan Lin, Sheng Liu, Jun Jiang, Shujun Li, Chengqing Li, C. -C. Jay Kuo

Recovering unknown, missing, damaged, distorted or lost information in DCT coefficients is a common task in multiple applications of digital image processing, including image compression, selective image encryption, and image communications.

Image Compression SSIM

GENHOP: An Image Generation Method Based on Successive Subspace Learning

no code implementations7 Oct 2022 Xuejing Lei, Wei Wang, C. -C. Jay Kuo

In the first module, it builds a sequence of high-to-low dimensional subspaces through a sequence of whitening processes, each of which contains samples of joint-spatial-spectral representation.

Dimensionality Reduction Image Generation

Green Learning: Introduction, Examples and Outlook

no code implementations3 Oct 2022 C. -C. Jay Kuo, Azad M. Madni

Rapid advances in artificial intelligence (AI) in the last decade have largely been built upon the wide applications of deep learning (DL).

Decision Making feature selection +1

Lightweight Image Codec via Multi-Grid Multi-Block-Size Vector Quantization (MGBVQ)

no code implementations25 Sep 2022 Yifan Wang, Zhanxuan Mei, Ioannis Katsavounidis, C. -C. Jay Kuo

The fundamental idea of image coding is to remove correlations among pixels before quantization and entropy coding, e. g., the discrete cosine transform (DCT) and intra predictions, adopted by modern image coding standards.


MAGIC: Mask-Guided Image Synthesis by Inverting a Quasi-Robust Classifier

1 code implementation23 Sep 2022 Mozhdeh Rouhsedaghat, Masoud Monajatipoor, C. -C. Jay Kuo, Iacopo Masi

We offer a method for one-shot mask-guided image synthesis that allows controlling manipulations of a single image by inverting a quasi-robust classifier equipped with strong regularizers.

Image Generation

GreenKGC: A Lightweight Knowledge Graph Completion Method

1 code implementation19 Aug 2022 Yun-Cheng Wang, Xiou Ge, Bin Wang, C. -C. Jay Kuo

Knowledge graph completion (KGC) aims to discover missing relationships between entities in knowledge graphs (KGs).

Edge-computing Link Prediction +2

Subtype-Aware Dynamic Unsupervised Domain Adaptation

no code implementations16 Aug 2022 Xiaofeng Liu, Fangxu Xing, Jia You, Jun Lu, C. -C. Jay Kuo, Georges El Fakhri, Jonghye Woo

In TPN, while the closeness of class centers between source and target domains is explicitly enforced in a latent space, the underlying fine-grained subtype structure and the cross-domain within-class compactness have not been fully investigated.

Unsupervised Domain Adaptation

Unsupervised Domain Adaptation for Segmentation with Black-box Source Model

no code implementations16 Aug 2022 Xiaofeng Liu, Chaehwa Yoo, Fangxu Xing, C. -C. Jay Kuo, Georges El Fakhri, Jonghye Woo

Unsupervised domain adaptation (UDA) has been widely used to transfer knowledge from a labeled source domain to an unlabeled target domain to counter the difficulty of labeling in a new domain.

Knowledge Distillation Unsupervised Domain Adaptation

Acceleration of Subspace Learning Machine via Particle Swarm Optimization and Parallel Processing

no code implementations15 Aug 2022 Hongyu Fu, Yijing Yang, Yuhuai Liu, Joseph Lin, Ethan Harrison, Vinod K. Mishra, C. -C. Jay Kuo

First, we adopt the particle swarm optimization (PSO) algorithm to speed up the search of a discriminant dimension that is expressed as a linear combination of current dimensions.

Classification General Classification +1

Human Decision Makings on Curriculum Reinforcement Learning with Difficulty Adjustment

no code implementations4 Aug 2022 Yilei Zeng, Jiali Duan, Yang Li, Emilio Ferrara, Lerrel Pinto, C. -C. Jay Kuo, Stefanos Nikolaidis

In this work, we guide the curriculum reinforcement learning results towards a preferred performance level that is neither too hard nor too easy via learning from the human decision process.

reinforcement-learning Reinforcement Learning (RL)

Statistical Attention Localization (SAL): Methodology and Application to Object Classification

no code implementations3 Aug 2022 Yijing Yang, Vasileios Magoulianitis, Xinyu Wang, C. -C. Jay Kuo

SAL consists of three steps: 1) preliminary attention window selection via decision statistics, 2) attention map refinement, and 3) rectangular attention region finalization.


Augmenting Vision Language Pretraining by Learning Codebook with Visual Semantics

no code implementations31 Jul 2022 Xiaoyuan Guo, Jiali Duan, C. -C. Jay Kuo, Judy Wawira Gichoya, Imon Banerjee

Language modality within the vision language pretraining framework is innately discretized, endowing each word in the language vocabulary a semantic meaning.

Language Modelling Masked Language Modeling

Enhancing Image Rescaling using Dual Latent Variables in Invertible Neural Network

no code implementations24 Jul 2022 Min Zhang, Zhihong Pan, Xin Zhou, C. -C. Jay Kuo

Normalizing flow models have been used successfully for generative image super-resolution (SR) by approximating complex distribution of natural images to simple tractable distribution in latent space through Invertible Neural Networks (INN).

Image Restoration Image Super-Resolution

GUSOT: Green and Unsupervised Single Object Tracking for Long Video Sequences

no code implementations15 Jul 2022 Zhiruo Zhou, Hongyu Fu, Suya You, C. -C. Jay Kuo

Supervised and unsupervised deep trackers that rely on deep learning technologies are popular in recent years.

Edge-computing Object Tracking

CompoundE: Knowledge Graph Embedding with Translation, Rotation and Scaling Compound Operations

no code implementations12 Jul 2022 Xiou Ge, Yun-Cheng Wang, Bin Wang, C. -C. Jay Kuo

Since translation, rotation, and scaling operations are cascaded to form a compound one, the new model is named CompoundE.

Knowledge Graph Embedding Translation

GreenBIQA: A Lightweight Blind Image Quality Assessment Method

no code implementations29 Jun 2022 Zhanxuan Mei, Yun-Cheng Wang, Xingze He, C. -C. Jay Kuo

Deep neural networks (DNNs) achieve great success in blind image quality assessment (BIQA) with large pre-trained models in recent years.

Blind Image Quality Assessment feature selection

Design of Supervision-Scalable Learning Systems: Methodology and Performance Benchmarking

no code implementations18 Jun 2022 Yijing Yang, Hongyu Fu, C. -C. Jay Kuo

The design of robust learning systems that offer stable performance under a wide range of supervision degrees is investigated in this work.

Benchmarking Image Classification +1

Subspace Learning Machine (SLM): Methodology and Performance

no code implementations11 May 2022 Hongyu Fu, Yijing Yang, Vinod K. Mishra, C. -C. Jay Kuo

The partitioning process is recursively applied at each child node to build an SLM tree.


DefakeHop++: An Enhanced Lightweight Deepfake Detector

no code implementations30 Apr 2022 Hong-Shuo Chen, Shuowen Hu, Suya You, C. -C. Jay Kuo

Second, for discriminant features selection, DefakeHop uses an unsupervised approach while DefakeHop++ adopts a more effective approach with supervision, called the Discriminant Feature Test (DFT).

Face Swapping

Label Efficient Regularization and Propagation for Graph Node Classification

no code implementations19 Apr 2022 Tian Xie, Rajgopal Kannan, C. -C. Jay Kuo

In this paper, we propose a label efficient regularization and propagation (LERP) framework for graph node classification, and present an alternate optimization procedure for its solution.

Benchmarking Classification +2

HUNIS: High-Performance Unsupervised Nuclei Instance Segmentation

no code implementations28 Mar 2022 Vasileios Magoulianitis, Yijing Yang, C. -C. Jay Kuo

The second stage exploits the segmentation masks obtained in the first stage and leverages color and shape distributions for a more accurate segmentation.

Instance Segmentation Semantic Segmentation +1

PCRP: Unsupervised Point Cloud Object Retrieval and Pose Estimation

no code implementations16 Feb 2022 Pranav Kadam, Qingyang Zhou, Shan Liu, C. -C. Jay Kuo

An unsupervised point cloud object retrieval and pose estimation method, called PCRP, is proposed in this work.

Point Cloud Registration Pose Estimation +1

CORE: A Knowledge Graph Entity Type Prediction Method via Complex Space Regression and Embedding

no code implementations19 Dec 2021 Xiou Ge, Yun-Cheng Wang, Bin Wang, C. -C. Jay Kuo

A new KG entity type prediction method, named CORE (COmplex space Regression and Embedding), is proposed in this work.

Benchmarking regression +2

KGBoost: A Classification-based Knowledge Base Completion Method with Negative Sampling

no code implementations17 Dec 2021 Yun-Cheng Wang, Xiou Ge, Bin Wang, C. -C. Jay Kuo

Knowledge base completion is formulated as a binary classification problem in this work, where an XGBoost binary classifier is trained for each relation using relevant links in knowledge graphs (KGs).

Binary Classification Knowledge Base Completion +2

GreenPCO: An Unsupervised Lightweight Point Cloud Odometry Method

no code implementations8 Dec 2021 Pranav Kadam, Min Zhang, Jiahao Gu, Shan Liu, C. -C. Jay Kuo

GreenPCO is an unsupervised learning method that predicts object motion by matching features of consecutive point cloud scans.

Benchmarking Visual Odometry

Unsupervised Lightweight Single Object Tracking with UHP-SOT++

no code implementations15 Nov 2021 Zhiruo Zhou, Hongyu Fu, Suya You, C. -C. Jay Kuo

Based on the experimental results, we compare pros and cons of supervised and unsupervised trackers and provide a new perspective to understand the performance gap between supervised and unsupervised methods, which is the third contribution of this work.

Object Tracking Trajectory Modeling

A-PixelHop: A Green, Robust and Explainable Fake-Image Detector

no code implementations7 Nov 2021 Yao Zhu, Xinyu Wang, Hong-Shuo Chen, Ronald Salloum, C. -C. Jay Kuo

A novel method for detecting CNN-generated images, called Attentive PixelHop (or A-PixelHop), is proposed in this work.

PEDENet: Image Anomaly Localization via Patch Embedding and Density Estimation

no code implementations29 Oct 2021 Kaitai Zhang, Bin Wang, C. -C. Jay Kuo

PEDENet contains a patch embedding (PE) network, a density estimation (DE) network, and an auxiliary network called the location prediction (LP) network.

Anomaly Detection Density Estimation +1

Task-Specific Dependency-based Word Embedding Methods

no code implementations26 Oct 2021 Chengwei Wei, Bin Wang, C. -C. Jay Kuo

Two task-specific dependency-based word embedding methods are proposed for text classification in this work.

text-classification Text Classification

Unsupervised Data-Driven Nuclei Segmentation For Histology Images

no code implementations14 Oct 2021 Vasileios Magoulianitis, Peida Han, Yijing Yang, C. -C. Jay Kuo

An unsupervised data-driven nuclei segmentation method for histology images, called CBM, is proposed in this work.

Binarization Dimensionality Reduction

UHP-SOT: An Unsupervised High-Performance Single Object Tracker

no code implementations5 Oct 2021 Zhiruo Zhou, Hongyu Fu, Suya You, Christoph C. Borel-Donohue, C. -C. Jay Kuo

An unsupervised online object tracking method that exploits both foreground and background correlations is proposed and named UHP-SOT (Unsupervised High-Performance Single Object Tracker) in this work.

Object Tracking Vocal Bursts Intensity Prediction

GSIP: Green Semantic Segmentation of Large-Scale Indoor Point Clouds

no code implementations24 Sep 2021 Min Zhang, Pranav Kadam, Shan Liu, C. -C. Jay Kuo

It is named GSIP (Green Segmentation of Indoor Point clouds) and its performance is evaluated on a representative large-scale benchmark -- the Stanford 3D Indoor Segmentation (S3DIS) dataset.

Semantic Segmentation

Bridging Gap between Image Pixels and Semantics via Supervision: A Survey

no code implementations29 Jul 2021 Jiali Duan, C. -C. Jay Kuo

The fact that there exists a gap between low-level features and semantic meanings of images, called the semantic gap, is known for decades.

Content-Based Image Retrieval Metric Learning +3

Adversarial Unsupervised Domain Adaptation with Conditional and Label Shift: Infer, Align and Iterate

no code implementations ICCV 2021 Xiaofeng Liu, Zhenhua Guo, Site Li, Fangxu Xing, Jane You, C. -C. Jay Kuo, Georges El Fakhri, Jonghye Woo

In this work, we propose an adversarial unsupervised domain adaptation (UDA) approach with the inherent conditional and label shifts, in which we aim to align the distributions w. r. t.

Unsupervised Domain Adaptation

Segmentation of Cardiac Structures via Successive Subspace Learning with Saab Transform from Cine MRI

no code implementations22 Jul 2021 Xiaofeng Liu, Fangxu Xing, Hanna K. Gaggin, Weichung Wang, C. -C. Jay Kuo, Georges El Fakhri, Jonghye Woo

Assessment of cardiovascular disease (CVD) with cine magnetic resonance imaging (MRI) has been used to non-invasively evaluate detailed cardiac structure and function.

Dimensionality Reduction feature selection +1

E-PixelHop: An Enhanced PixelHop Method for Object Classification

no code implementations7 Jul 2021 Yijing Yang, Vasileios Magoulianitis, C. -C. Jay Kuo

Forth, pixel-level decisions from each hop and from each color subspace are fused together for image-level decision.

Binary Classification Classification +1

AnomalyHop: An SSL-based Image Anomaly Localization Method

1 code implementation8 May 2021 Kaitai Zhang, Bin Wang, Wei Wang, Fahad Sohrab, Moncef Gabbouj, C. -C. Jay Kuo

An image anomaly localization method based on the successive subspace learning (SSL) framework, called AnomalyHop, is proposed in this work.


Dynamic Texture Synthesis by Incorporating Long-range Spatial and Temporal Correlations

no code implementations13 Apr 2021 Kaitai Zhang, Bin Wang, Hong-Shuo Chen, Ye Wang, Shiyu Mou, C. -C. Jay Kuo

The main challenge of dynamic texture synthesis lies in how to maintain spatial and temporal consistency in synthesized videos.

Texture Synthesis

CalibDNN: Multimodal Sensor Calibration for Perception Using Deep Neural Networks

no code implementations27 Mar 2021 Ganning Zhao, Jiesi Hu, Suya You, C. -C. Jay Kuo

Current perception systems often carry multimodal imagers and sensors such as 2D cameras and 3D LiDAR sensors.

R-PointHop: A Green, Accurate, and Unsupervised Point Cloud Registration Method

1 code implementation15 Mar 2021 Pranav Kadam, Min Zhang, Shan Liu, C. -C. Jay Kuo

Inspired by the recent PointHop classification method, an unsupervised 3D point cloud registration method, called R-PointHop, is proposed in this work.

Dimensionality Reduction Point Cloud Registration +1

Successive Subspace Learning: An Overview

no code implementations27 Feb 2021 Mozhdeh Rouhsedaghat, Masoud Monajatipoor, Zohreh Azizi, C. -C. Jay Kuo

Successive Subspace Learning (SSL) offers a light-weight unsupervised feature learning method based on inherent statistical properties of data units (e. g. image pixels and points in point cloud sets).

Symmetric-Constrained Irregular Structure Inpainting for Brain MRI Registration with Tumor Pathology

no code implementations17 Jan 2021 Xiaofeng Liu, Fangxu Xing, Chao Yang, C. -C. Jay Kuo, Georges ElFakhri, Jonghye Woo

Deformable registration of magnetic resonance images between patients with brain tumors and healthy subjects has been an important tool to specify tumor geometry through location alignment and facilitate pathological analysis.

Brain Tumor Segmentation Image Inpainting +3

VoxelHop: Successive Subspace Learning for ALS Disease Classification Using Structural MRI

no code implementations13 Jan 2021 Xiaofeng Liu, Fangxu Xing, Chao Yang, C. -C. Jay Kuo, Suma Babu, Georges El Fakhri, Thomas Jenkins, Jonghye Woo

Deep learning has great potential for accurate detection and classification of diseases with medical imaging data, but the performance is often limited by the number of training datasets and memory requirements.

Classification Dimensionality Reduction +1

GraphHop: An Enhanced Label Propagation Method for Node Classification

1 code implementation7 Jan 2021 Tian Xie, Bin Wang, C. -C. Jay Kuo

In Step 2, a new label vector is predicted for each node based on the label of the node itself and the aggregated label information obtained in Step 1.

Classification General Classification +3

Protecting Big Data Privacy Using Randomized Tensor Network Decomposition and Dispersed Tensor Computation

no code implementations4 Jan 2021 Jenn-Bing Ong, Wee-Keong Ng, Ivan Tjuawinata, Chao Li, Jielin Yang, Sai None Myne, Huaxiong Wang, Kwok-Yan Lam, C. -C. Jay Kuo

The distributed tensor representations are dispersed on multiple clouds / fogs or servers / devices with metadata privacy, this provides both distributed trust and management to seamlessly secure big data storage, communication, sharing, and computation.

Dimensionality Reduction Management +1

Subtype-aware Unsupervised Domain Adaptation for Medical Diagnosis

no code implementations1 Jan 2021 Xiaofeng Liu, Xiongchang Liu, Bo Hu, Wenxuan Ji, Fangxu Xing, Jun Lu, Jane You, C. -C. Jay Kuo, Georges El Fakhri, Jonghye Woo

Recent advances in unsupervised domain adaptation (UDA) show that transferable prototypical learning presents a powerful means for class conditional alignment, which encourages the closeness of cross-domain class centroids.

Medical Diagnosis Unsupervised Domain Adaptation

Low-Resolution Face Recognition In Resource-Constrained Environments

no code implementations23 Nov 2020 Mozhdeh Rouhsedaghat, Yifan Wang, Shuowen Hu, Suya You, C. -C. Jay Kuo

A non-parametric low-resolution face recognition model for resource-constrained environments with limited networking and computing is proposed in this work.

Active Learning Face Recognition

Point Cloud Attribute Compression via Successive Subspace Graph Transform

no code implementations29 Oct 2020 Yueru Chen, Yiting shao, Jing Wang, Ge Li, C. -C. Jay Kuo

Inspired by the recently proposed successive subspace learning (SSL) principles, we develop a successive subspace graph transform (SSGT) to address point cloud attribute compression in this work.

Constructing Multilayer Perceptrons as Piecewise Low-Order Polynomial Approximators: A Signal Processing Approach

no code implementations15 Oct 2020 Ruiyuan Lin, Suya You, Raghuveer Rao, C. -C. Jay Kuo

Through the construction, a one-to-one correspondence between the approximation of an MLP and that of a piecewise low-order polynomial is established.

Inductive Learning on Commonsense Knowledge Graph Completion

1 code implementation19 Sep 2020 Bin Wang, Guangtao Wang, Jing Huang, Jiaxuan You, Jure Leskovec, C. -C. Jay Kuo

Here, we propose to study the inductive learning setting for CKG completion where unseen entities may present at test time.

Entity Embeddings Knowledge Graph Completion +2

From Two-Class Linear Discriminant Analysis to Interpretable Multilayer Perceptron Design

no code implementations9 Sep 2020 Ruiyuan Lin, Zhiruo Zhou, Suya You, Raghuveer Rao, C. -C. Jay Kuo

Besides input layer $l_{in}$ and output layer $l_{out}$, the MLP of interest consists of two intermediate layers, $l_1$ and $l_2$.

Vocal Bursts Valence Prediction

NITES: A Non-Parametric Interpretable Texture Synthesis Method

no code implementations2 Sep 2020 Xuejing Lei, Ganning Zhao, C. -C. Jay Kuo

A non-parametric interpretable texture synthesis method, called the NITES method, is proposed in this work.

Texture Synthesis

Noise-Aware Texture-Preserving Low-Light Enhancement

no code implementations2 Sep 2020 Zohreh Azizi, Xuejing Lei, C. -C. Jay Kuo

A simple and effective low-light image enhancement method based on a noise-aware texture-preserving retinex model is proposed in this work.

Low-Light Image Enhancement

Unsupervised Point Cloud Registration via Salient Points Analysis (SPA)

no code implementations2 Sep 2020 Pranav Kadam, Min Zhang, Shan Liu, C. -C. Jay Kuo

An unsupervised point cloud registration method, called salient points analysis (SPA), is proposed in this work.

Point Cloud Registration

Unsupervised Feedforward Feature (UFF) Learning for Point Cloud Classification and Segmentation

no code implementations2 Sep 2020 Min Zhang, Pranav Kadam, Shan Liu, C. -C. Jay Kuo

The UFF method exploits statistical correlations of points in a point cloud set to learn shape and point features in a one-pass feedforward manner through a cascaded encoder-decoder architecture.

Classification General Classification +1

FaceHop: A Light-Weight Low-Resolution Face Gender Classification Method

no code implementations18 Jul 2020 Mozhdeh Rouhsedaghat, Yifan Wang, Xiou Ge, Shuowen Hu, Suya You, C. -C. Jay Kuo

For gray-scale face images of resolution $32 \times 32$ in the LFW and the CMU Multi-PIE datasets, FaceHop achieves correct gender classification rates of 94. 63% and 95. 12% with model sizes of 16. 9K and 17. 6K parameters, respectively.

Classification Gender Classification +1

Learning Color Compatibility in Fashion Outfits

no code implementations5 Jul 2020 Heming Zhang, Xuewen Yang, Jianchao Tan, Chi-Hao Wu, Jue Wang, C. -C. Jay Kuo

Color compatibility is important for evaluating the compatibility of a fashion outfit, yet it was neglected in previous studies.

graph construction

Novel Human-Object Interaction Detection via Adversarial Domain Generalization

no code implementations22 May 2020 Yuhang Song, Wenbo Li, Lei Zhang, Jianwei Yang, Emre Kiciman, Hamid Palangi, Jianfeng Gao, C. -C. Jay Kuo, Pengchuan Zhang

We study in this paper the problem of novel human-object interaction (HOI) detection, aiming at improving the generalization ability of the model to unseen scenarios.

Domain Generalization Human-Object Interaction Detection

Multi-View Matching (MVM): Facilitating Multi-Person 3D Pose Estimation Learning with Action-Frozen People Video

no code implementations11 Apr 2020 Yeji Shen, C. -C. Jay Kuo

To tackle the challeging problem of multi-person 3D pose estimation from a single image, we propose a multi-view matching (MVM) method in this work.

Ranked #108 on 3D Human Pose Estimation on 3DPW (PA-MPJPE metric)

3D Human Pose Estimation 3D Pose Estimation

Efficient Sentence Embedding via Semantic Subspace Analysis

1 code implementation22 Feb 2020 Bin Wang, Fenxiao Chen, Yuncheng Wang, C. -C. Jay Kuo

Given the fact that word embeddings can capture semantic relationship while semantically similar words tend to form semantic groups in a high-dimensional embedding space, we develop a sentence representation scheme by analyzing semantic subspaces of its constituent words.

Sentence Embedding Sentence-Embedding +1

SBERT-WK: A Sentence Embedding Method by Dissecting BERT-based Word Models

3 code implementations16 Feb 2020 Bin Wang, C. -C. Jay Kuo

Yet, it is an open problem to generate a high quality sentence representation from BERT-based word models.

Semantic Textual Similarity Sentence Embedding +1

PointHop++: A Lightweight Learning Model on Point Sets for 3D Classification

2 code implementations9 Feb 2020 Min Zhang, Yifan Wang, Pranav Kadam, Shan Liu, C. -C. Jay Kuo

The PointHop method was recently proposed by Zhang et al. for 3D point cloud classification with unsupervised feature extraction.

3D Classification 3D Point Cloud Classification +2

PixelHop++: A Small Successive-Subspace-Learning-Based (SSL-based) Model for Image Classification

no code implementations8 Feb 2020 Yueru Chen, Mozhdeh Rouhsedaghat, Suya You, Raghuveer Rao, C. -C. Jay Kuo

In PixelHop++, one can control the learning model size of fine-granularity, offering a flexible tradeoff between the model size and the classification performance.

Classification General Classification +1

Towards Disentangled Representations for Human Retargeting by Multi-view Learning

no code implementations12 Dec 2019 Chao Yang, Xiaofeng Liu, Qingming Tang, C. -C. Jay Kuo

We study the problem of learning disentangled representations for data across multiple domains and its applications in human retargeting.


PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representation

2 code implementations NeurIPS 2019 Can Qin, Haoxuan You, Lichen Wang, C. -C. Jay Kuo, Yun Fu

Specifically, most general-purpose DA methods that struggle for global feature alignment and ignore local geometric information are not suitable for 3D domain alignment.

Unsupervised Domain Adaptation

PixelHop: A Successive Subspace Learning (SSL) Method for Object Classification

2 code implementations17 Sep 2019 Yueru Chen, C. -C. Jay Kuo

A new machine learning methodology, called successive subspace learning (SSL), is introduced in this work.

Benchmarking Decision Making +2

Graph Representation Learning: A Survey

1 code implementation3 Sep 2019 Fenxiao Chen, Yuncheng Wang, Bin Wang, C. -C. Jay Kuo

Research on graph representation learning has received a lot of attention in recent years since many data in real-world applications come in form of graphs.

Graph Embedding Graph Representation Learning

PointHop: An Explainable Machine Learning Method for Point Cloud Classification

3 code implementations30 Jul 2019 Min Zhang, Haoxuan You, Pranav Kadam, Shan Liu, C. -C. Jay Kuo

In the attribute building stage, we address the problem of unordered point cloud data using a space partitioning procedure and developing a robust descriptor that characterizes the relationship between a point and its one-hop neighbor in a PointHop unit.

BIG-bench Machine Learning Classification +2

An Interpretable Compression and Classification System: Theory and Applications

no code implementations21 Jul 2019 Tzu-Wei Tseng, Kai-Jiun Yang, C. -C. Jay Kuo, Shang-Ho, Tsai

Thanks to the linear property, the extracted and reduced features can be inversed to original data, like a linear transform such as Fourier transform, so that one can quantify and visualize the contribution of individual features towards the original data.

Classification Data Compression +1

Accelerating Proposal Generation Network for \\Fast Face Detection on Mobile Devices

no code implementations27 Apr 2019 Heming Zhang, Xiaolong Wang, Jingwen Zhu, C. -C. Jay Kuo

In this work, we present a proposal generation acceleration framework for real-time face detection.

Face Detection

Class-incremental Learning via Deep Model Consolidation

2 code implementations19 Mar 2019 Junting Zhang, Jie Zhang, Shalini Ghosh, Dawei Li, Serafettin Tasci, Larry Heck, Heming Zhang, C. -C. Jay Kuo

The idea is to first train a separate model only for the new classes, and then combine the two individual models trained on data of two distinct set of classes (old classes and new classes) via a novel double distillation training objective.

class-incremental learning Class Incremental Learning +4

Generative Visual Dialogue System via Adaptive Reasoning and Weighted Likelihood Estimation

no code implementations26 Feb 2019 Heming Zhang, Shalini Ghosh, Larry Heck, Stephen Walsh, Junting Zhang, Jie Zhang, C. -C. Jay Kuo

The key challenge of generative Visual Dialogue (VD) systems is to respond to human queries with informative answers in natural and contiguous conversation flow.

Visual Dialog

Semi-supervised learning via Feedforward-Designed Convolutional Neural Networks

no code implementations6 Feb 2019 Yueru Chen, Yijing Yang, Min Zhang, C. -C. Jay Kuo

A semi-supervised learning framework using the feedforward-designed convolutional neural networks (FF-CNNs) is proposed for image classification in this work.

Benchmarking General Classification +1

Evaluating Word Embedding Models: Methods and Experimental Results

no code implementations28 Jan 2019 Bin Wang, Angela Wang, Fenxiao Chen, Yuncheng Wang, C. -C. Jay Kuo

Extensive evaluation on a large number of word embedding models for language processing applications is conducted in this work.

Word Embeddings

Efficient Image Splicing Localization via Contrastive Feature Extraction

no code implementations22 Jan 2019 Ronald Salloum, C. -C. Jay Kuo

This technique, referred to as cPCA++, utilizes the fact that the interesting features of a "target" dataset may be obscured by high variance components during traditional PCA.

Clustering Data Visualization

Ensembles of feedforward-designed convolutional neural networks

no code implementations8 Jan 2019 Yueru Chen, Yijing Yang, Wei Wang, C. -C. Jay Kuo

An ensemble method that fuses the output decision vectors of multiple feedforward-designed convolutional neural networks (FF-CNNs) to solve the image classification problem is proposed in this work.

General Classification Image Classification

Towards Visible and Thermal Drone Monitoring with Convolutional Neural Networks

no code implementations19 Dec 2018 Ye Wang, Yueru Chen, Jongmoo Choi, C. -C. Jay Kuo

One is a model-based drone augmentation technique that automatically generates visible drone images with a bounding box label on the drone's location.

Data Augmentation

Unsupervised Video Object Segmentation with Distractor-Aware Online Adaptation

no code implementations19 Dec 2018 Ye Wang, Jongmoo Choi, Yueru Chen, Siyang Li, Qin Huang, Kaitai Zhang, Ming-Sui Lee, C. -C. Jay Kuo

Unsupervised video object segmentation is a crucial application in video analysis without knowing any prior information about the objects.

Instance Segmentation Semantic Segmentation +2

Design Pseudo Ground Truth with Motion Cue for Unsupervised Video Object Segmentation

no code implementations13 Dec 2018 Ye Wang, Jongmoo Choi, Yueru Chen, Qin Huang, Siyang Li, Ming-Sui Lee, C. -C. Jay Kuo

Experimental results on DAVIS and FBMS show that the proposed method outperforms state-of-the-art unsupervised segmentation methods on various benchmark datasets.

Instance Segmentation Object Tracking +3

Analysis on Gradient Propagation in Batch Normalized Residual Networks

no code implementations ICLR 2018 Abhishek Panigrahi, Yueru Chen, C. -C. Jay Kuo

We conduct mathematical analysis on the effect of batch normalization (BN) on gradient backpropogation in residual network training, which is believed to play a critical role in addressing the gradient vanishing/explosion problem, in this work.

Unsupervised Multi-modal Neural Machine Translation

no code implementations CVPR 2019 Yuanhang Su, Kai Fan, Nguyen Bach, C. -C. Jay Kuo, Fei Huang

Unsupervised neural machine translation (UNMT) has recently achieved remarkable results with only large monolingual corpora in each language.

Machine Translation Translation

Convolutional Neural Networks with Transformed Input based on Robust Tensor Network Decomposition

no code implementations20 Nov 2018 Jenn-Bing Ong, Wee-Keong Ng, C. -C. Jay Kuo

Tensor network decomposition, originated from quantum physics to model entangled many-particle quantum systems, turns out to be a promising mathematical technique to efficiently represent and process big data in parsimonious manner.

Privacy Preserving Tensor Networks

Interpretable Convolutional Neural Networks via Feedforward Design

2 code implementations5 Oct 2018 C. -C. Jay Kuo, Min Zhang, Siyang Li, Jiali Duan, Yueru Chen

To construct convolutional layers, we develop a new signal transform, called the Saab (Subspace Approximation with Adjusted Bias) transform.

Graph-based Deep-Tree Recursive Neural Network (DTRNN) for Text Classification

no code implementations4 Sep 2018 Fenxiao Chen, Bin Wang, C. -C. Jay Kuo

A novel graph-to-tree conversion mechanism called the deep-tree generation (DTG) algorithm is first proposed to predict text data represented by graphs.

Benchmarking General Classification +2

Post-Processing of Word Representations via Variance Normalization and Dynamic Embedding

1 code implementation20 Aug 2018 Bin Wang, Fenxiao Chen, Angela Wang, C. -C. Jay Kuo

Although embedded vector representations of words offer impressive performance on many natural language processing (NLP) applications, the information of ordered input sequences is lost to some extent if only context-based samples are used in the training.

Defense Against Adversarial Attacks with Saak Transform

no code implementations6 Aug 2018 Sibo Song, Yueru Chen, Ngai-Man Cheung, C. -C. Jay Kuo

Therefore, we propose a Saak transform based preprocessing method with three steps: 1) transforming an input image to a joint spatial-spectral representation via the forward Saak transform, 2) apply filtering to its high-frequency components, and, 3) reconstructing the image via the inverse Saak transform.

Adversarial Defense

Tree-structured multi-stage principal component analysis (TMPCA): theory and applications

no code implementations22 Jul 2018 Yuanhang Su, Ruiyuan Lin, C. -C. Jay Kuo

A PCA based sequence-to-vector (seq2vec) dimension reduction method for the text classification problem, called the tree-structured multi-stage principal component analysis (TMPCA) is presented in this paper.

Dimensionality Reduction General Classification +2

PortraitGAN for Flexible Portrait Manipulation

no code implementations5 Jul 2018 Jiali Duan, Xiaoyuan Guo, Yuhang Song, Chao Yang, C. -C. Jay Kuo

Previous methods have dealt with discrete manipulation of facial attributes such as smile, sad, angry, surprise etc, out of canonical expressions and they are not scalable, operating in single modality.

Depth-Aware Stereo Video Retargeting

no code implementations CVPR 2018 Bing Li, Chia-Wen Lin, Boxin Shi, Tiejun Huang, Wen Gao, C. -C. Jay Kuo

As compared with traditional video retargeting, stereo video retargeting poses new challenges because stereo video contains the depth information of salient objects and its time dynamics.

SPG-Net: Segmentation Prediction and Guidance Network for Image Inpainting

1 code implementation9 May 2018 Yuhang Song, Chao Yang, Yeji Shen, Peng Wang, Qin Huang, C. -C. Jay Kuo

In this paper, we focus on image inpainting task, aiming at recovering the missing area of an incomplete image given the context information.

Image Inpainting Interactive Segmentation +1

Image Inpainting using Block-wise Procedural Training with Annealed Adversarial Counterpart

no code implementations23 Mar 2018 Chao Yang, Yuhang Song, Xiaofeng Liu, Qingming Tang, C. -C. Jay Kuo

We present a new approach to address the difficulty of training a very deep generative model to synthesize high-quality photo-realistic inpainting.

Facial Inpainting Image Harmonization

On Extended Long Short-term Memory and Dependent Bidirectional Recurrent Neural Network

1 code implementation27 Feb 2018 Yuanhang Su, C. -C. Jay Kuo

In this work, we first analyze the memory behavior in three recurrent neural networks (RNN) cells; namely, the simple RNN (SRN), the long short-term memory (LSTM) and the gated recurrent unit (GRU), where the memory is defined as a function that maps previous elements in a sequence to the current output.

Dependency Parsing

Efficient Text Classification Using Tree-structured Multi-linear Principal Component Analysis

no code implementations20 Jan 2018 Yuanhang Su, Yuzhong Huang, C. -C. Jay Kuo

A novel text data dimension reduction technique, called the tree-structured multi-linear principal component anal- ysis (TMPCA), is proposed in this work.

Dimensionality Reduction General Classification +2

Instance Embedding Transfer to Unsupervised Video Object Segmentation

no code implementations CVPR 2018 Siyang Li, Bryan Seybold, Alexey Vorobyov, Alireza Fathi, Qin Huang, C. -C. Jay Kuo

We propose a method for unsupervised video object segmentation by transferring the knowledge encapsulated in image-based instance embedding networks.

Optical Flow Estimation Semantic Segmentation +2

Dependent Bidirectional RNN with Extended-long Short-term Memory

no code implementations ICLR 2018 Yuanhang Su, Yuzhong Huang, C. -C. Jay Kuo

Based on the analysis, we propose a new design, called the extended-long short-term memory (ELSTM), to extend the memory length of a cell.

A Deep Learning Approach to Drone Monitoring

no code implementations4 Dec 2017 Yueru Chen, Pranav Aggarwal, Jongmoo Choi, C. -C. Jay Kuo

A drone monitoring system that integrates deep-learning-based detection and tracking modules is proposed in this work.

Multiple Instance Curriculum Learning for Weakly Supervised Object Detection

no code implementations25 Nov 2017 Siyang Li, Xiangxin Zhu, Qin Huang, Hao Xu, C. -C. Jay Kuo

When supervising an object detector with weakly labeled data, most existing approaches are prone to trapping in the discriminative object parts, e. g., finding the face of a cat instead of the full body, due to lacking the supervision on the extent of full objects.

Multiple Instance Learning object-detection +2

Contextual-based Image Inpainting: Infer, Match, and Translate

no code implementations ECCV 2018 Yuhang Song, Chao Yang, Zhe Lin, Xiaofeng Liu, Qin Huang, Hao Li, C. -C. Jay Kuo

We study the task of image inpainting, which is to fill in the missing region of an incomplete image with plausible contents.

Image Inpainting Translation

A Fully Convolutional Tri-branch Network (FCTN) for Domain Adaptation

no code implementations10 Nov 2017 Junting Zhang, Chen Liang, C. -C. Jay Kuo

We evaluate the proposed network on large-scale domain adaptation experiments using both synthetic (GTA) and real (Cityscapes) images.

Domain Adaptation Scene Segmentation

A Taught-Obesrve-Ask (TOA) Method for Object Detection with Critical Supervision

no code implementations3 Nov 2017 Chi-Hao Wu, Qin Huang, Siyang Li, C. -C. Jay Kuo

Being inspired by child's learning experience - taught first and followed by observation and questioning, we investigate a critically supervised learning methodology for object detection in this work.

object-detection Object Detection +1

A Saak Transform Approach to Efficient, Scalable and Robust Handwritten Digits Recognition

no code implementations29 Oct 2017 Yueru Chen, Zhuwei Xu, Shanshan Cai, Yujian Lang, C. -C. Jay Kuo

We conduct a comparative study on the performance of the LeNet-5 and the Saak-transform-based solutions in terms of scalability and robustness as well as the efficiency of lossless and lossy Saak transforms under a comparable accuracy level.

On Data-Driven Saak Transform

2 code implementations11 Oct 2017 C. -C. Jay Kuo, Yueru Chen

The Saak transform consists of three steps: 1) building the optimal linear subspace approximation with orthonormal bases using the second-order statistics of input vectors, 2) augmenting each transform kernel with its negative, 3) applying the rectified linear unit (ReLU) to the transform output.

Image Splicing Localization Using A Multi-Task Fully Convolutional Network (MFCN)

1 code implementation6 Sep 2017 Ronald Salloum, Yuzhuo Ren, C. -C. Jay Kuo

Experiments show that the SFCN and MFCN outperform existing splicing localization algorithms, and that the MFCN can achieve finer localization than the SFCN.

Multi-Task Learning

Semantic Segmentation with Reverse Attention

no code implementations20 Jul 2017 Qin Huang, Chunyang Xia, Chi-Hao Wu, Siyang Li, Ye Wang, Yuhang Song, C. -C. Jay Kuo

Recent development in fully convolutional neural network enables efficient end-to-end learning of semantic segmentation.

Semantic Segmentation

Design, Analysis and Application of A Volumetric Convolutional Neural Network

no code implementations1 Feb 2017 Xiaqing Pan, Yueru Chen, C. -C. Jay Kuo

In the design of the VCNN, we propose a feed-forward K-means clustering algorithm to determine the filter number and size at each convolutional layer systematically.

3D Shape Classification Classification +2

CNN as Guided Multi-layer RECOS Transform

no code implementations30 Jan 2017 C. -C. Jay Kuo

Afterwards, we interpret a CNN as a network that implements the guided multi-layer RECOS transform with three highlights.


Understanding Convolutional Neural Networks with A Mathematical Model

1 code implementation14 Sep 2016 C. -C. Jay Kuo

Keywords: Convolutional Neural Network (CNN), Nonlinear Activation, RECOS Model, Rectified Linear Unit (ReLU), MNIST Dataset.

A Coarse-to-Fine Indoor Layout Estimation (CFILE) Method

1 code implementation3 Jul 2016 Yuzhuo Ren, Chen Chen, Shang-Wen Li, C. -C. Jay Kuo

The task of estimating the spatial layout of cluttered indoor scenes from a single RGB image is addressed in this work.

GAL: A Global-Attributes Assisted Labeling System for Outdoor Scenes

no code implementations3 Apr 2016 Yuzhuo Ren, Chen Chen, Shang-Wen Li, C. -C. Jay Kuo

The proposed Global-attributes Assisted Labeling (GAL) system exploits both local features and global attributes.

A ParaBoost Stereoscopic Image Quality Assessment (PBSIQA) System

no code implementations31 Mar 2016 Hyunsuk Ko, Rui Song, C. -C. Jay Kuo

The problem of stereoscopic image quality assessment, which finds applications in 3D visual content delivery such as 3DTV, is investigated in this work.

Stereoscopic image quality assessment

Robust Uncalibrated Stereo Rectification with Constrained Geometric Distortions (USR-CGD)

no code implementations31 Mar 2016 Hyunsuk Ko, Han Suk Shim, Ouk Choi, C. -C. Jay Kuo

A novel algorithm for uncalibrated stereo image-pair rectification under the constraint of geometric distortion, called USR-CGD, is presented in this work.

A Two-Stage Shape Retrieval (TSR) Method with Global and Local Features

no code implementations7 Mar 2016 Xiaqing Pan, Sachin Chachada, C. -C. Jay Kuo

A robust two-stage shape retrieval (TSR) method is proposed to address the 2D shape retrieval problem.


Measuring and Predicting Tag Importance for Image Retrieval

no code implementations28 Feb 2016 Shang-Wen Li, Sanjay Purushotham, Chen Chen, Yuzhuo Ren, C. -C. Jay Kuo

Textual data such as tags, sentence descriptions are combined with visual cues to reduce the semantic gap for image retrieval applications in today's Multimodal Image Retrieval (MIR) systems.

Image Retrieval Retrieval +1

A GMM-Based Stair Quality Model for Human Perceived JPEG Images

no code implementations11 Nov 2015 Sudeng Hu, Haiqiang Wang, C. -C. Jay Kuo

Based on the notion of just noticeable differences (JND), a stair quality function (SQF) was recently proposed to model human perception on JPEG images.


MCL-3D: a database for stereoscopic image quality assessment using 2D-image-plus-depth source

no code implementations23 Mar 2014 Rui Song, Hyunsuk Ko, C. -C. Jay Kuo

A new stereoscopic image quality assessment database rendered using the 2D-image-plus-depth source, called MCL-3D, is described and the performance benchmarking of several known 2D and 3D image quality metrics using the MCL-3D database is presented in this work.

Benchmarking Stereoscopic image quality assessment

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