Search Results for author:
Found 158 papers, 31 papers with code
GreenSaliency: A Lightweight and Efficient Image Saliency Detection Method
Image saliency detection is crucial in understanding human gaze patterns from visual stimuli.
PCa-RadHop: A Transparent and Lightweight Feed-forward Method for Clinically Significant Prostate Cancer Segmentation
Deep learning (DL) models achieve a high segmentation performance, although require a large model size and complexity.
PSHop: A Lightweight Feed-Forward Method for 3D Prostate Gland Segmentation
Automatic prostate segmentation is an important step in computer-aided diagnosis of prostate cancer and treatment planning.
Treatment-wise Glioblastoma Survival Inference with Multi-parametric Preoperative MRI
In this work, we aim to predict the survival time (ST) of glioblastoma (GBM) patients undergoing different treatments based on preoperative magnetic resonance (MR) scans.
GWPT: A Green Word-Embedding-based POS Tagger
As a fundamental tool for natural language processing (NLP), the part-of-speech (POS) tagger assigns the POS label to each word in a sentence.
Enhancing Edge Intelligence with Highly Discriminant LNT Features
Along this line, we present a novel supervised learning method to generate highly discriminant complementary features based on the least-squares normal transform (LNT).
SemST: Semantically Consistent Multi-Scale Image Translation via Structure-Texture Alignment
Unsupervised image-to-image (I2I) translation learns cross-domain image mapping that transfers input from the source domain to output in the target domain while preserving its semantics.
Knowledge Graph Embedding: An Overview
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.
Unsupervised Green Object Tracker (GOT) without Offline Pre-training
The labeling cost and the huge computational complexity hinder their applications on edge devices.
Bias and Fairness in Chatbots: An Overview
Thus, a comprehensive overview on bias and fairness in chatbot systems is given in this paper.
AsyncET: Asynchronous Learning for Knowledge Graph Entity Typing with Auxiliary Relations
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.
A Comprehensive Overview of Computational Nuclei Segmentation Methods in Digital Pathology
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.
Blind Video Quality Assessment at the Edge
The usage of deep-learning-based methods is restricted to be applied at the edge due to their large model sizes and high computational complexity.
Green Steganalyzer: A Green Learning Approach to Image Steganalysis
A novel learning solution to image steganalysis based on the green learning paradigm, called Green Steganalyzer (GS), is proposed in this work.
An Overview on Generative AI at Scale with Edge-Cloud Computing
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.
Unsupervised Synthetic Image Refinement via Contrastive Learning and Consistent Semantic-Structural Constraints
Ensuring the realism of computer-generated synthetic images is crucial to deep neural network (DNN) training.
Knowledge Graph Embedding with 3D Compound Geometric Transformations
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.
Ranked #7 on
Link Property Prediction
on ogbl-wikikg2
Lightweight High-Performance Blind Image Quality Assessment
Blind image quality assessment (BIQA) is a task that predicts the perceptual quality of an image without its reference.
A Tiny Machine Learning Model for Point Cloud Object Classification
On the other hand, the model size and inference complexity of DGCNN are 42X and 1203X of those of Green-PointHop, respectively.
An Overview on Language Models: Recent Developments and Outlook
Language modeling studies the probability distributions over strings of texts.
LSR: A Light-Weight Super-Resolution Method
A light-weight super-resolution (LSR) method from a single image targeting mobile applications is proposed in this work.
PointFlowHop: Green and Interpretable Scene Flow Estimation from Consecutive Point Clouds
An efficient 3D scene flow estimation method called PointFlowHop is proposed in this work.
S3I-PointHop: SO(3)-Invariant PointHop for 3D Point Cloud Classification
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.
gpcgc: a green point cloud geometry coding method
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
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
A self-supervised adaptive low-light video enhancement method, called SALVE, is proposed in this work.
LGSQE: Lightweight Generated Sample Quality Evaluatoin
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
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 communication.
GENHOP: An Image Generation Method Based on Successive Subspace Learning
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.
Green Learning: Introduction, Examples and Outlook
Rapid advances in artificial intelligence (AI) in the last decade have largely been built upon the wide applications of deep learning (DL).
Lightweight Image Codec via Multi-Grid Multi-Block-Size Vector Quantization (MGBVQ)
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
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.
GreenKGC: A Lightweight Knowledge Graph Completion Method
Knowledge graph completion (KGC) aims to discover missing relationships between entities in knowledge graphs (KGs).
Ranked #21 on
Link Prediction
on FB15k-237
Unsupervised Domain Adaptation for Segmentation with Black-box Source Model
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.
Subtype-Aware Dynamic Unsupervised Domain Adaptation
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.
Acceleration of Subspace Learning Machine via Particle Swarm Optimization and Parallel Processing
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.
Human Decision Makings on Curriculum Reinforcement Learning with Difficulty Adjustment
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.
Statistical Attention Localization (SAL): Methodology and Application to Object Classification
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
Language modality within the vision language pretraining framework is innately discretized, endowing each word in the language vocabulary a semantic meaning.
Enhancing Image Rescaling using Dual Latent Variables in Invertible Neural Network
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).
GUSOT: Green and Unsupervised Single Object Tracking for Long Video Sequences
Supervised and unsupervised deep trackers that rely on deep learning technologies are popular in recent years.
CompoundE: Knowledge Graph Embedding with Translation, Rotation and Scaling Compound Operations
Since translation, rotation, and scaling operations are cascaded to form a compound one, the new model is named CompoundE.
GreenBIQA: A Lightweight Blind Image Quality Assessment Method
Deep neural networks (DNNs) achieve great success in blind image quality assessment (BIQA) with large pre-trained models in recent years.
SynWMD: Syntax-aware Word Mover's Distance for Sentence Similarity Evaluation
It also outperforms other WMD-based methods on sentence classification tasks.
Design of Supervision-Scalable Learning Systems: Methodology and Performance Benchmarking
The design of robust learning systems that offer stable performance under a wide range of supervision degrees is investigated in this work.
PAGER: Progressive Attribute-Guided Extendable Robust Image Generation
PAGER consists of three modules: core generator, resolution enhancer, and quality booster.
Subspace Learning Machine (SLM): Methodology and Performance
The partitioning process is recursively applied at each child node to build an SLM tree.
DefakeHop++: An Enhanced Lightweight Deepfake Detector
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).
Label Efficient Regularization and Propagation for Graph Node Classification
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.
HUNIS: High-Performance Unsupervised Nuclei Instance Segmentation
The second stage exploits the segmentation masks obtained in the first stage and leverages color and shape distributions for a more accurate segmentation.
On Supervised Feature Selection from High Dimensional Feature Spaces
The application of machine learning to image and video data often yields a high dimensional feature space.
Just Rank: Rethinking Evaluation with Word and Sentence Similarities
Word and sentence similarity tasks have become the de facto evaluation method.
PCRP: Unsupervised Point Cloud Object Retrieval and Pose Estimation
An unsupervised point cloud object retrieval and pose estimation method, called PCRP, is proposed in this work.
CORE: A Knowledge Graph Entity Type Prediction Method via Complex Space Regression and Embedding
A new KG entity type prediction method, named CORE (COmplex space Regression and Embedding), is proposed in this work.
KGBoost: A Classification-based Knowledge Base Completion Method with Negative Sampling
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).
GreenPCO: An Unsupervised Lightweight Point Cloud Odometry Method
GreenPCO is an unsupervised learning method that predicts object motion by matching features of consecutive point cloud scans.
Unsupervised Lightweight Single Object Tracking with UHP-SOT++
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.
A-PixelHop: A Green, Robust and Explainable Fake-Image Detector
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
PEDENet contains a patch embedding (PE) network, a density estimation (DE) network, and an auxiliary network called the location prediction (LP) network.
Ranked #71 on
Anomaly Detection
on MVTec AD
Task-Specific Dependency-based Word Embedding Methods
Two task-specific dependency-based word embedding methods are proposed for text classification in this work.
Geo-DefakeHop: High-Performance Geographic Fake Image Detection
A robust fake satellite image detection method, called Geo-DefakeHop, is proposed in this work.
Unsupervised Data-Driven Nuclei Segmentation For Histology Images
An unsupervised data-driven nuclei segmentation method for histology images, called CBM, is proposed in this work.
UHP-SOT: An Unsupervised High-Performance Single Object Tracker
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.
GSIP: Green Semantic Segmentation of Large-Scale Indoor Point Clouds
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.
BERTHop: An Effective Vision-and-Language Model for Chest X-ray Disease Diagnosis
Vision-and-language(V&L) models take image and text as input and learn to capture the associations between them.
Bridging Gap between Image Pixels and Semantics via Supervision: A Survey
The fact that there exists a gap between low-level features and semantic meanings of images, called the semantic gap, is known for decades.
Adversarial Unsupervised Domain Adaptation with Conditional and Label Shift: Infer, Align and Iterate
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.
Segmentation of Cardiac Structures via Successive Subspace Learning with Saab Transform from Cine MRI
Assessment of cardiovascular disease (CVD) with cine magnetic resonance imaging (MRI) has been used to non-invasively evaluate detailed cardiac structure and function.
TGHop: An Explainable, Efficient and Lightweight Method for Texture Generation
Finally, texture patches are stitched to form texture images of a large size.
E-PixelHop: An Enhanced PixelHop Method for Object Classification
Forth, pixel-level decisions from each hop and from each color subspace are fused together for image-level decision.
AnomalyHop: An SSL-based Image Anomaly Localization Method
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
The main challenge of dynamic texture synthesis lies in how to maintain spatial and temporal consistency in synthesized videos.
CalibDNN: Multimodal Sensor Calibration for Perception Using Deep Neural Networks
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
Inspired by the recent PointHop classification method, an unsupervised 3D point cloud registration method, called R-PointHop, is proposed in this work.
DefakeHop: A Light-Weight High-Performance Deepfake Detector
A light-weight high-performance Deepfake detection method, called DefakeHop, is proposed in this work.
Successive Subspace Learning: An Overview
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
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.
VoxelHop: Successive Subspace Learning for ALS Disease Classification Using Structural MRI
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.
GraphHop: An Enhanced Label Propagation Method for Node Classification
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.
Protecting Big Data Privacy Using Randomized Tensor Network Decomposition and Dispersed Tensor Computation
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.
Subtype-aware Unsupervised Domain Adaptation for Medical Diagnosis
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.
Low-Resolution Face Recognition In Resource-Constrained Environments
A non-parametric low-resolution face recognition model for resource-constrained environments with limited networking and computing is proposed in this work.
SLADE: A Self-Training Framework For Distance Metric Learning
We first train a teacher model on the labeled data and use it to generate pseudo labels for the unlabeled data.
Point Cloud Attribute Compression via Successive Subspace Graph Transform
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
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
Here, we propose to study the inductive learning setting for CKG completion where unseen entities may present at test time.
From Two-Class Linear Discriminant Analysis to Interpretable Multilayer Perceptron Design
Besides input layer $l_{in}$ and output layer $l_{out}$, the MLP of interest consists of two intermediate layers, $l_1$ and $l_2$.
Unsupervised Point Cloud Registration via Salient Points Analysis (SPA)
An unsupervised point cloud registration method, called salient points analysis (SPA), is proposed in this work.
NITES: A Non-Parametric Interpretable Texture Synthesis Method
A non-parametric interpretable texture synthesis method, called the NITES method, is proposed in this work.
Noise-Aware Texture-Preserving Low-Light Enhancement
A simple and effective low-light image enhancement method based on a noise-aware texture-preserving retinex model is proposed in this work.
Unsupervised Feedforward Feature (UFF) Learning for Point Cloud Classification and Segmentation
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.
FaceHop: A Light-Weight Low-Resolution Face Gender Classification Method
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.
Learning Color Compatibility in Fashion Outfits
Color compatibility is important for evaluating the compatibility of a fashion outfit, yet it was neglected in previous studies.
Novel Human-Object Interaction Detection via Adversarial Domain Generalization
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.
Multi-View Matching (MVM): Facilitating Multi-Person 3D Pose Estimation Learning with Action-Frozen People Video
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 #121 on
3D Human Pose Estimation
on 3DPW
(PA-MPJPE metric)
Efficient Sentence Embedding via Semantic Subspace Analysis
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.
SBERT-WK: A Sentence Embedding Method by Dissecting BERT-based Word Models
Yet, it is an open problem to generate a high quality sentence representation from BERT-based word models.
PointHop++: A Lightweight Learning Model on Point Sets for 3D Classification
The PointHop method was recently proposed by Zhang et al. for 3D point cloud classification with unsupervised feature extraction.
PixelHop++: A Small Successive-Subspace-Learning-Based (SSL-based) Model for Image Classification
In PixelHop++, one can control the learning model size of fine-granularity, offering a flexible tradeoff between the model size and the classification performance.
Towards Disentangled Representations for Human Retargeting by Multi-view Learning
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
Specifically, most general-purpose DA methods that struggle for global feature alignment and ignore local geometric information are not suitable for 3D domain alignment.
Ranked #1 on
Unsupervised Domain Adaptation
on PreSIL to KITTI
PixelHop: A Successive Subspace Learning (SSL) Method for Object Classification
A new machine learning methodology, called successive subspace learning (SSL), is introduced in this work.
Graph Representation Learning: A Survey
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.
PointHop: An Explainable Machine Learning Method for Point Cloud Classification
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.
An Interpretable Compression and Classification System: Theory and Applications
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.
Deep Kinship Verification via Appearance-shape Joint Prediction and Adaptation-based Approach
Kinship verification aims to identify the kin relation between two given face images.
Accelerating Proposal Generation Network for \\Fast Face Detection on Mobile Devices
In this work, we present a proposal generation acceleration framework for real-time face detection.
Class-incremental Learning via Deep Model Consolidation
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.
Generative Visual Dialogue System via Adaptive Reasoning and Weighted Likelihood Estimation
The key challenge of generative Visual Dialogue (VD) systems is to respond to human queries with informative answers in natural and contiguous conversation flow.
Semi-supervised learning via Feedforward-Designed Convolutional Neural Networks
A semi-supervised learning framework using the feedforward-designed convolutional neural networks (FF-CNNs) is proposed for image classification in this work.
Evaluating Word Embedding Models: Methods and Experimental Results
Extensive evaluation on a large number of word embedding models for language processing applications is conducted in this work.
Efficient Image Splicing Localization via Contrastive Feature Extraction
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.
Ensembles of feedforward-designed convolutional neural networks
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.
Towards Visible and Thermal Drone Monitoring with Convolutional Neural Networks
One is a model-based drone augmentation technique that automatically generates visible drone images with a bounding box label on the drone's location.
Unsupervised Video Object Segmentation with Distractor-Aware Online Adaptation
Unsupervised video object segmentation is a crucial application in video analysis without knowing any prior information about the objects.
Design Pseudo Ground Truth with Motion Cue for Unsupervised Video Object Segmentation
Experimental results on DAVIS and FBMS show that the proposed method outperforms state-of-the-art unsupervised segmentation methods on various benchmark datasets.
Analysis on Gradient Propagation in Batch Normalized Residual Networks
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
Unsupervised neural machine translation (UNMT) has recently achieved remarkable results with only large monolingual corpora in each language.
Convolutional Neural Networks with Transformed Input based on Robust Tensor Network Decomposition
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.
An Interpretable Generative Model for Handwritten Digit Image Synthesis
An interpretable generative model for handwritten digits synthesis is proposed in this work.
Interpretable Convolutional Neural Networks via Feedforward Design
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
A novel graph-to-tree conversion mechanism called the deep-tree generation (DTG) algorithm is first proposed to predict text data represented by graphs.
Unsupervised Video Object Segmentation with Motion-based Bilateral Networks
First, we propose a motion-based bilateral network to estimate the background based on the motion pattern of non-object regions.
Ranked #3 on
Video Salient Object Detection
on MCL
(using extra training data)
Post-Processing of Word Representations via Variance Normalization and Dynamic Embedding
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
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.
Tree-structured multi-stage principal component analysis (TMPCA): theory and applications
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.
PortraitGAN for Flexible Portrait Manipulation
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.
Show, Attend and Translate: Unsupervised Image Translation with Self-Regularization and Attention
It has been applied to numerous domains, such as data augmentation, domain adaptation, and unsupervised training.
Depth-Aware Stereo Video Retargeting
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
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 using Block-wise Procedural Training with Annealed Adversarial Counterpart
We present a new approach to address the difficulty of training a very deep generative model to synthesize high-quality photo-realistic inpainting.
On Extended Long Short-term Memory and Dependent Bidirectional Recurrent Neural Network
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.
Efficient Text Classification Using Tree-structured Multi-linear Principal Component Analysis
A novel text data dimension reduction technique, called the tree-structured multi-linear principal component anal- ysis (TMPCA), is proposed in this work.
Instance Embedding Transfer to Unsupervised Video Object Segmentation
We propose a method for unsupervised video object segmentation by transferring the knowledge encapsulated in image-based instance embedding networks.
Dependent Bidirectional RNN with Extended-long Short-term Memory
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
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
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.
Contextual-based Image Inpainting: Infer, Match, and Translate
We study the task of image inpainting, which is to fill in the missing region of an incomplete image with plausible contents.
A Fully Convolutional Tri-branch Network (FCTN) for Domain Adaptation
We evaluate the proposed network on large-scale domain adaptation experiments using both synthetic (GTA) and real (Cityscapes) images.
A Taught-Obesrve-Ask (TOA) Method for Object Detection with Critical Supervision
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.
A Saak Transform Approach to Efficient, Scalable and Robust Handwritten Digits Recognition
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
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)
Experiments show that the SFCN and MFCN outperform existing splicing localization algorithms, and that the MFCN can achieve finer localization than the SFCN.
Semantic Segmentation with Reverse Attention
Recent development in fully convolutional neural network enables efficient end-to-end learning of semantic segmentation.
Ranked #94 on
Semantic Segmentation
on NYU Depth v2
Design, Analysis and Application of A Volumetric Convolutional Neural Network
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 Retrieval via Irrelevance Filtering and Similarity Ranking (IF/SR)
The remaining gallery samples are ranked in the SR module using the local feature.
CNN as Guided Multi-layer RECOS Transform
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
Keywords: Convolutional Neural Network (CNN), Nonlinear Activation, RECOS Model, Rectified Linear Unit (ReLU), MNIST Dataset.
A Coarse-to-Fine Indoor Layout Estimation (CFILE) Method
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
The proposed Global-attributes Assisted Labeling (GAL) system exploits both local features and global attributes.
Robust Uncalibrated Stereo Rectification with Constrained Geometric Distortions (USR-CGD)
A novel algorithm for uncalibrated stereo image-pair rectification under the constraint of geometric distortion, called USR-CGD, is presented in this work.
Object Boundary Guided Semantic Segmentation
Semantic segmentation is critical to image content understanding and object localization.
A ParaBoost Stereoscopic Image Quality Assessment (PBSIQA) System
The problem of stereoscopic image quality assessment, which finds applications in 3D visual content delivery such as 3DTV, is investigated in this work.
A Two-Stage Shape Retrieval (TSR) Method with Global and Local Features
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
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.
Robust Image Segmentation Using Contour-Guided Color Palettes
The contour-guided color palette (CCP) is proposed for robust image segmentation.
A GMM-Based Stair Quality Model for Human Perceived JPEG Images
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
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.
