Search Results for author: Ke Chen

Found 106 papers, 44 papers with code

SkipBERT: Efficient Inference with Shallow Layer Skipping

1 code implementation ACL 2022 Jue Wang, Ke Chen, Gang Chen, Lidan Shou, Julian McAuley

In this paper, we propose SkipBERT to accelerate BERT inference by skipping the computation of shallow layers.

AudioSR: Versatile Audio Super-resolution at Scale

no code implementations13 Sep 2023 Haohe Liu, Ke Chen, Qiao Tian, Wenwu Wang, Mark D. Plumbley

Audio super-resolution is a fundamental task that predicts high-frequency components for low-resolution audio, enhancing audio quality in digital applications.

Audio Super-Resolution Super-Resolution

Adopting Dynamic VAR Compensators to Mitigate PV Impacts on Unbalanced Distribution Systems

no code implementations12 Sep 2023 Han Pyo Lee, Keith DSouza, Ke Chen, Ning Lu, Mesut Baran

However, the effectiveness of this scheme is not well documented, and there is limited literature on alternative control and placement schemes that can maximize the effective use of a DVC.

Super-Resolution Surface Reconstruction from Few Low-Resolution Slices

1 code implementation10 Sep 2023 Yiyao Zhang, Ke Chen, Shang-Hua Yang

In many imaging applications where segmented features (e. g. blood vessels) are further used for other numerical simulations (e. g. finite element analysis), the obtained surfaces do not have fine resolutions suitable for the task.

Super-Resolution Surface Reconstruction

Nest-DGIL: Nesterov-optimized Deep Geometric Incremental Learning for CS Image Reconstruction

1 code implementation6 Aug 2023 Xiaohong Fan, Yin Yang, Ke Chen, Yujie Feng, Jianping Zhang

In the image restoration step, a cascade geometric incremental learning module is designed to compensate for the missing texture information from different geometric spectral decomposition domains.

Image Reconstruction Image Restoration +1

Towards Improving Harmonic Sensitivity and Prediction Stability for Singing Melody Extraction

1 code implementation4 Aug 2023 Keren Shao, Ke Chen, Taylor Berg-Kirkpatrick, Shlomo Dubnov

In deep learning research, many melody extraction models rely on redesigning neural network architectures to improve performance.

Melody Extraction

A Bi-variant Variational Model for Diffeomorphic Image Registration with Relaxed Jacobian Determinant Constraints

no code implementations4 Aug 2023 Yanyan Li, Ke Chen, Chong Chen, Jianping Zhang

To prevent deformation folding and enhance the smoothness of deformation, we not only impose a positivity constraint in optimizing the relaxation function, but also employ a regularizer to ensure the smoothness of the relaxation function. Furthermore, the positivity constraint ensures that is as close to one as possible, which helps to obtain a volume-preserving transformation on average. We further analyze the existence of the minimizer for the variational model and propose a penalty splitting method with a multilevel strategy to solve this model.

Image Registration

ShuffleMix: Improving Representations via Channel-Wise Shuffle of Interpolated Hidden States

1 code implementation30 May 2023 KangJun Liu, Ke Chen, Lihua Guo, YaoWei Wang, Kui Jia

Inspired by good robustness of alternative dropout strategies against over-fitting on limited patterns of training samples, this paper introduces a novel concept of ShuffleMix -- Shuffle of Mixed hidden features, which can be interpreted as a kind of dropout operation in feature space.

Benchmarking Data Augmentation +1

Improving Deep Representation Learning via Auxiliary Learnable Target Coding

1 code implementation30 May 2023 KangJun Liu, Ke Chen, YaoWei Wang, Kui Jia

Deep representation learning is a subfield of machine learning that focuses on learning meaningful and useful representations of data through deep neural networks.

Representation Learning Retrieval

Manifold-Aware Self-Training for Unsupervised Domain Adaptation on Regressing 6D Object Pose

1 code implementation18 May 2023 Yichen Zhang, Jiehong Lin, Ke Chen, Zelin Xu, YaoWei Wang, Kui Jia

Domain gap between synthetic and real data in visual regression (\eg 6D pose estimation) is bridged in this paper via global feature alignment and local refinement on the coarse classification of discretized anchor classes in target space, which imposes a piece-wise target manifold regularization into domain-invariant representation learning.

6D Pose Estimation regression +2

Deep Partial Multi-Label Learning with Graph Disambiguation

no code implementations10 May 2023 Haobo Wang, Shisong Yang, Gengyu Lyu, Weiwei Liu, Tianlei Hu, Ke Chen, Songhe Feng, Gang Chen

In partial multi-label learning (PML), each data example is equipped with a candidate label set, which consists of multiple ground-truth labels and other false-positive labels.

Multi-Label Learning

SwinFSR: Stereo Image Super-Resolution using SwinIR and Frequency Domain Knowledge

no code implementations25 Apr 2023 Ke Chen, Liangyan Li, Huan Liu, Yunzhe Li, Congling Tang, Jun Chen

Stereo Image Super-Resolution (stereoSR) has attracted significant attention in recent years due to the extensive deployment of dual cameras in mobile phones, autonomous vehicles and robots.

Autonomous Vehicles Image Restoration +1

TC-GAT: Graph Attention Network for Temporal Causality Discovery

no code implementations21 Apr 2023 Xiaosong Yuan, Ke Chen, Wanli Zuo, Yijia Zhang

The present study explores the intricacies of causal relationship extraction, a vital component in the pursuit of causality knowledge.

Graph Attention

Pac-HuBERT: Self-Supervised Music Source Separation via Primitive Auditory Clustering and Hidden-Unit BERT

no code implementations4 Apr 2023 Ke Chen, Gordon Wichern, François G. Germain, Jonathan Le Roux

In this paper, we propose a self-supervised learning framework for music source separation inspired by the HuBERT speech representation model.

Clustering Music Source Separation +1

Closed-Loop Transcription via Convolutional Sparse Coding

no code implementations18 Feb 2023 Xili Dai, Ke Chen, Shengbang Tong, Jingyuan Zhang, Xingjian Gao, Mingyang Li, Druv Pai, Yuexiang Zhai, Xiaojun Yuan, Heung-Yeung Shum, Lionel M. Ni, Yi Ma

Our method is arguably the first to demonstrate that a concatenation of multiple convolution sparse coding/decoding layers leads to an interpretable and effective autoencoder for modeling the distribution of large-scale natural image datasets.

Rolling Shutter Correction

Deep Operator Learning Lessens the Curse of Dimensionality for PDEs

no code implementations28 Jan 2023 Ke Chen, Chunmei Wang, Haizhao Yang

Deep neural networks (DNNs) have achieved remarkable success in numerous domains, and their application to PDE-related problems has been rapidly advancing.

Operator learning

An Efficient Semi-Automated Scheme for Infrastructure LiDAR Annotation

no code implementations25 Jan 2023 Aotian Wu, Pan He, Xiao Li, Ke Chen, Sanjay Ranka, Anand Rangarajan

Specifically, we introduce a human-in-the-loop schema in which annotators recursively fix and refine annotations imperfectly predicted by our tool and incrementally add them to the training dataset to obtain better SOT and MOT models.

Autonomous Driving Multi-Object Tracking +3

Graph Contrastive Learning with Implicit Augmentations

no code implementations7 Nov 2022 Huidong Liang, Xingjian Du, Bilei Zhu, Zejun Ma, Ke Chen, Junbin Gao

Existing graph contrastive learning methods rely on augmentation techniques based on random perturbations (e. g., randomly adding or dropping edges and nodes).

Contrastive Learning

NVRadarNet: Real-Time Radar Obstacle and Free Space Detection for Autonomous Driving

no code implementations29 Sep 2022 Alexander Popov, Patrik Gebhardt, Ke Chen, Ryan Oldja, Heeseok Lee, Shane Murray, Ruchi Bhargava, Nikolai Smolyanskiy

To this end, we present NVRadarNet, a deep neural network (DNN) that detects dynamic obstacles and drivable free space using automotive RADAR sensors.

Autonomous Driving

Fisher Matrix Based Fault Detection for PMUs Data in Power Grids

no code implementations9 Aug 2022 Ke Chen, Dandan Jiang, Bo wang, Hongxia Wang

Firstly, the fault detection matrix is constructed and the event detection problem is reformatted as a two-sample covariance matrices test problem.

Event Detection Fault Detection

Convolutional Fine-Grained Classification with Self-Supervised Target Relation Regularization

1 code implementation3 Aug 2022 KangJun Liu, Ke Chen, Kui Jia

Such target coding schemes are less flexible to model inter-class correlation and are sensitive to sparse and imbalanced data distribution as well.

Classification Data Augmentation +2

Multitrack Music Transformer

2 code implementations14 Jul 2022 Hao-Wen Dong, Ke Chen, Shlomo Dubnov, Julian McAuley, Taylor Berg-Kirkpatrick

Existing approaches for generating multitrack music with transformer models have been limited in terms of the number of instruments, the length of the music segments and slow inference.

Music Generation

An Interpretable MRI Reconstruction Network with Two-grid-cycle Correction and Geometric Prior Distillation

1 code implementation14 May 2022 Xiaohong Fan, Yin Yang, Ke Chen, Jianping Zhang, Ke Dong

Although existing deep learning compressed-sensing-based Magnetic Resonance Imaging (CS-MRI) methods have achieved considerably impressive performance, explainability and generalizability continue to be challenging for such methods since the transition from mathematical analysis to network design not always natural enough, often most of them are not flexible enough to handle multi-sampling-ratio reconstruction assignments.

MRI Reconstruction

BiCo-Net: Regress Globally, Match Locally for Robust 6D Pose Estimation

1 code implementation7 May 2022 Zelin Xu, Yichen Zhang, Ke Chen, Kui Jia

Inspired by the success of point-pair features, the goal of this paper is to recover the 6D pose of an object instance segmented from RGB-D images by locally matching pairs of oriented points between the model and camera space.

6D Pose Estimation Benchmarking +1

Fast Multi-grid Methods for Minimizing Curvature Energy

1 code implementation17 Apr 2022 Zhenwei Zhang, Ke Chen, Ke Tang, Yuping Duan

In this paper, we propose fast multi-grid algorithms for minimizing both mean curvature and Gaussian curvature energy functionals without sacrificing accuracy for efficiency.

Image Denoising MRI Reconstruction

Fine-Grained Object Classification via Self-Supervised Pose Alignment

2 code implementations CVPR 2022 Xuhui Yang, YaoWei Wang, Ke Chen, Yong Xu, Yonghong Tian

Semantic patterns of fine-grained objects are determined by subtle appearance difference of local parts, which thus inspires a number of part-based methods.

Classification Representation Learning

Quasi-Balanced Self-Training on Noise-Aware Synthesis of Object Point Clouds for Closing Domain Gap

1 code implementation8 Mar 2022 Yongwei Chen, ZiHao Wang, Longkun Zou, Ke Chen, Kui Jia

Such a challenge of Simulation-to-Reality (Sim2Real) domain gap could be mitigated via learning algorithms of domain adaptation; however, we argue that generation of synthetic point clouds via more physically realistic rendering is a powerful alternative, as systematic non-uniform noise patterns can be captured.

Benchmarking Point Cloud Classification +1

TONet: Tone-Octave Network for Singing Melody Extraction from Polyphonic Music

1 code implementation2 Feb 2022 Ke Chen, Shuai Yu, Cheng-i Wang, Wei Li, Taylor Berg-Kirkpatrick, Shlomo Dubnov

In this paper, we propose TONet, a plug-and-play model that improves both tone and octave perceptions by leveraging a novel input representation and a novel network architecture.

Information Retrieval Melody Extraction +2

HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection

1 code implementation2 Feb 2022 Ke Chen, Xingjian Du, Bilei Zhu, Zejun Ma, Taylor Berg-Kirkpatrick, Shlomo Dubnov

To combat these problems, we introduce HTS-AT: an audio transformer with a hierarchical structure to reduce the model size and training time.

Audio Classification Event Detection +3

Using Deep Image Prior to Assist Variational Selective Segmentation Deep Learning Algorithms

no code implementations1 Dec 2021 Liam Burrows, Ke Chen, Francesco Torella

Recently, it was shown in the Deep Image Prior work that the explicit regularisation in a model can be removed and replaced by the implicit regularisation captured by the architecture of a neural network.

Sparse Steerable Convolutions: An Efficient Learning of SE(3)-Equivariant Features for Estimation and Tracking of Object Poses in 3D Space

1 code implementation NeurIPS 2021 Jiehong Lin, Hongyang Li, Ke Chen, Jiangbo Lu, Kui Jia

In this paper, we propose a novel design of Sparse Steerable Convolution (SS-Conv) to address the shortcoming; SS-Conv greatly accelerates steerable convolution with sparse tensors, while strictly preserving the property of SE(3)-equivariance.

6D Pose Estimation Pose Tracking

Geometry-Aware Self-Training for Unsupervised Domain Adaptationon Object Point Clouds

1 code implementation20 Aug 2021 Longkun Zou, Hui Tang, Ke Chen, Kui Jia

The point cloud representation of an object can have a large geometric variation in view of inconsistent data acquisition procedure, which thus leads to domain discrepancy due to diverse and uncontrollable shape representation cross datasets.

Point Cloud Classification Representation Learning +1

Neural-to-Tree Policy Distillation with Policy Improvement Criterion

no code implementations16 Aug 2021 Zhao-Hua Li, Yang Yu, Yingfeng Chen, Ke Chen, Zhipeng Hu, Changjie Fan

The empirical results show that the proposed method can preserve a higher cumulative reward than behavior cloning and learn a more consistent policy to the original one.

Decision Making reinforcement-learning +1

GLIB: Towards Automated Test Oracle for Graphically-Rich Applications

1 code implementation19 Jun 2021 Ke Chen, Yufei Li, Yingfeng Chen, Changjie Fan, Zhipeng Hu, Wei Yang

We perform an evaluation of \texttt{GLIB} on 20 real-world game apps (with bug reports available) and the result shows that \texttt{GLIB} can achieve 100\% precision and 99. 5\% recall in detecting non-crashing bugs such as game GUI glitches.

Data Augmentation

Effective Slot Filling via Weakly-Supervised Dual-Model Learning

1 code implementation AAAI 2021 Jue Wang, Ke Chen, Lidan Shou, Sai Wu, Gang Chen

By using some particular weakly-labeled data, namely the plain phrases included in sentences, we propose a weaklysupervised slot filling approach.

slot-filling Slot Filling +1

MAX Phase Zr2SeC and Its Thermal Conduction Behavior

no code implementations4 Feb 2021 Ke Chen, Xiaojing Bai, Xulin Mu, Pengfei Yan, Nianxiang Qiu, Youbing Li, Jie zhou, Yujie Song, Yiming Zhang, Shiyu Du, Zhifang Chai, Qing Huang

The elemental diversity is crucial to screen out ternary MAX phases with outstanding properties via tuning of bonding types and strength between constitutive atoms.

Materials Science

Label-Efficient Point Cloud Semantic Segmentation: An Active Learning Approach

no code implementations18 Jan 2021 Xian Shi, Xun Xu, Ke Chen, Lile Cai, Chuan Sheng Foo, Kui Jia

Deep learning models are the state-of-the-art methods for semantic point cloud segmentation, the success of which relies on the availability of large-scale annotated datasets.

Active Learning Benchmarking +2

Geometry-Aware Self-Training for Unsupervised Domain Adaptation on Object Point Clouds

1 code implementation ICCV 2021 Longkun Zou, Hui Tang, Ke Chen, Kui Jia

The point cloud representation of an object can have a large geometric variation in view of inconsistent data acquisition procedure, which thus leads to domain discrepancy due to diverse and uncontrollable shape representation cross datasets.

Point Cloud Classification Representation Learning +1

Real-Time Vanishing Point Detector Integrating Under-Parameterized RANSAC and Hough Transform

no code implementations ICCV 2021 Jianping Wu, Liang Zhang, Ye Liu, Ke Chen

We propose a novel approach that integrates under-parameterized RANSAC (UPRANSAC) with Hough Transform to detect vanishing points (VPs) from un-calibrated monocular images.

Classification of Single-View Object Point Clouds

no code implementations18 Dec 2020 Zelin Xu, Ke Chen, KangJun Liu, Changxing Ding, YaoWei Wang, Kui Jia

By adapting existing ModelNet40 and ScanNet datasets to the single-view, partial setting, experiment results can verify the necessity of object pose estimation and superiority of our PAPNet to existing classifiers.

3D Object Classification 6D Pose Estimation using RGB +5

Catalytically Potent and Selective Clusterzymes for Modulation of Neuroinflammation Through Single-Atom Substitutions

no code implementations17 Dec 2020 Haile Liu, Yonghui Li, Si Sun, Qi Xin, Shuhu Liu, Xiaoyu Mu, Xun Yuan, Ke Chen, Hao Wang, Kalman Varga, Wenbo Mi, Jiang Yang, Xiao-Dong Zhang

Emerging artificial enzymes with reprogrammed and augmented catalytic activity and substrate selectivity have long been pursued with sustained efforts.

Biological Physics Medical Physics

Towards Uncovering the Intrinsic Data Structures for Unsupervised Domain Adaptation using Structurally Regularized Deep Clustering

2 code implementations8 Dec 2020 Hui Tang, Xiatian Zhu, Ke Chen, Kui Jia, C. L. Philip Chen

To address this issue, we are motivated by a UDA assumption of structural similarity across domains, and propose to directly uncover the intrinsic target discrimination via constrained clustering, where we constrain the clustering solutions using structural source regularization that hinges on the very same assumption.

Clustering Deep Clustering +3

LINDT: Tackling Negative Federated Learning with Local Adaptation

no code implementations23 Nov 2020 Hong Lin, Lidan Shou, Ke Chen, Gang Chen, Sai Wu

On occasion of NFL recovery, the framework makes adaptation to the federated model on each client's local data by learning a Layer-wise Intertwined Dual-model.

Federated Learning

Feature Importance Ranking for Deep Learning

1 code implementation NeurIPS 2020 Maksymilian Wojtas, Ke Chen

During learning, the operator is trained for a supervised learning task via optimal feature subset candidates generated by the selector that learns predicting the learning performance of the operator working on different optimal subset candidates.

Combinatorial Optimization Feature Importance +1

CAD-PU: A Curvature-Adaptive Deep Learning Solution for Point Set Upsampling

1 code implementation10 Sep 2020 Jiehong Lin, Xian Shi, Yuan Gao, Ke Chen, Kui Jia

Point set is arguably the most direct approximation of an object or scene surface, yet its practical acquisition often suffers from the shortcoming of being noisy, sparse, and possibly incomplete, which restricts its use for a high-quality surface recovery.

Point Set Upsampling

POP909: A Pop-song Dataset for Music Arrangement Generation

1 code implementation17 Aug 2020 Ziyu Wang, Ke Chen, Junyan Jiang, Yiyi Zhang, Maoran Xu, Shuqi Dai, Xianbin Gu, Gus Xia

The main body of the dataset contains the vocal melody, the lead instrument melody, and the piano accompaniment for each song in MIDI format, which are aligned to the original audio files.

Music Generation

MusPy: A Toolkit for Symbolic Music Generation

2 code implementations5 Aug 2020 Hao-Wen Dong, Ke Chen, Julian McAuley, Taylor Berg-Kirkpatrick

MusPy provides easy-to-use tools for essential components in a music generation system, including dataset management, data I/O, data preprocessing and model evaluation.

Management Music Generation

Music SketchNet: Controllable Music Generation via Factorized Representations of Pitch and Rhythm

1 code implementation4 Aug 2020 Ke Chen, Cheng-i Wang, Taylor Berg-Kirkpatrick, Shlomo Dubnov

Drawing an analogy with automatic image completion systems, we propose Music SketchNet, a neural network framework that allows users to specify partial musical ideas guiding automatic music generation.

Music Generation

Pyramid: A Layered Model for Nested Named Entity Recognition

2 code implementations ACL 2020 Jue Wang, Lidan Shou, Ke Chen, Gang Chen

Its hidden state at layer l represents an l-gram in the input text, which is labeled only if its corresponding text region represents a complete entity mention.

named-entity-recognition Named Entity Recognition +2

A Generalized Asymmetric Dual-front Model for Active Contours and Image Segmentation

no code implementations14 Jun 2020 Da Chen, Jack Spencer, Jean-Marie Mirebeau, Ke Chen, Minglei Shu, Laurent D. Cohen

The Voronoi diagram-based dual-front active contour models are known as a powerful and efficient way for addressing the image segmentation and domain partitioning problems.

Image Segmentation Semantic Segmentation

MVLidarNet: Real-Time Multi-Class Scene Understanding for Autonomous Driving Using Multiple Views

no code implementations9 Jun 2020 Ke Chen, Ryan Oldja, Nikolai Smolyanskiy, Stan Birchfield, Alexander Popov, David Wehr, Ibrahim Eden, Joachim Pehserl

We show that our multi-view, multi-stage, multi-class approach is able to detect and classify objects while simultaneously determining the drivable space using a single LiDAR scan as input, in challenging scenes with more than one hundred vehicles and pedestrians at a time.

Autonomous Driving object-detection +2

Compositional Few-Shot Recognition with Primitive Discovery and Enhancing

no code implementations12 May 2020 Yixiong Zou, Shanghang Zhang, Ke Chen, Yonghong Tian, Yao-Wei Wang, José M. F. Moura

Inspired by such capability of humans, to imitate humans' ability of learning visual primitives and composing primitives to recognize novel classes, we propose an approach to FSL to learn a feature representation composed of important primitives, which is jointly trained with two parts, i. e. primitive discovery and primitive enhancing.

Few-Shot Image Classification Few-Shot Learning +1

Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering

2 code implementations CVPR 2020 Hui Tang, Ke Chen, Kui Jia

To alleviate this risk, we are motivated by the assumption of structural domain similarity, and propose to directly uncover the intrinsic target discrimination via discriminative clustering of target data.

Clustering Deep Clustering +1

A Framework for End-to-End Learning on Semantic Tree-Structured Data

1 code implementation13 Feb 2020 William Woof, Ke Chen

In this paper, we propose a novel framework for end-to-end learning on generic semantic tree-structured data of arbitrary topology and heterogeneous data types, such as data expressed in JSON, XML and so on.

Continuous Melody Generation via Disentangled Short-Term Representations and Structural Conditions

1 code implementation5 Feb 2020 Ke Chen, Gus Xia, Shlomo Dubnov

Automatic music generation is an interdisciplinary research topic that combines computational creativity and semantic analysis of music to create automatic machine improvisations.

Disentanglement Music Generation

Improving Semantic Analysis on Point Clouds via Auxiliary Supervision of Local Geometric Priors

no code implementations14 Jan 2020 Lulu Tang, Ke Chen, Chaozheng Wu, Yu Hong, Kui Jia, Zhi-Xin Yang

Existing deep learning algorithms for point cloud analysis mainly concern discovering semantic patterns from global configuration of local geometries in a supervised learning manner.

W-PoseNet: Dense Correspondence Regularized Pixel Pair Pose Regression

no code implementations26 Dec 2019 Zelin Xu, Ke Chen, Kui Jia

Solving 6D pose estimation is non-trivial to cope with intrinsic appearance and shape variation and severe inter-object occlusion, and is made more challenging in light of extrinsic large illumination changes and low quality of the acquired data under an uncontrolled environment.

 Ranked #1 on 6D Pose Estimation using RGBD on LineMOD (Mean ADD-S metric)

6D Pose Estimation 6D Pose Estimation using RGBD +1

Cascading Convolutional Color Constancy

1 code implementation24 Dec 2019 Huanglin Yu, Ke Chen, Kaiqi Wang, Yanlin Qian, Zhao-Xiang Zhang, Kui Jia

Regressing the illumination of a scene from the representations of object appearances is popularly adopted in computational color constancy.

Color Constancy

Geometry-Aware Generation of Adversarial Point Clouds

2 code implementations24 Dec 2019 Yuxin Wen, Jiehong Lin, Ke Chen, C. L. Philip Chen, Kui Jia

Regularizing the targeted attack loss with our proposed geometry-aware objectives results in our proposed method, Geometry-Aware Adversarial Attack ($GeoA^3$).

Adversarial Attack Fairness

Towards Further Understanding of Sparse Filtering via Information Bottleneck

1 code implementation20 Oct 2019 Fabio Massimo Zennaro, Ke Chen

In this paper we examine a formalization of feature distribution learning (FDL) in information-theoretic terms relying on the analytical approach and on the tools already used in the study of the information bottleneck (IB).

Geometry-aware Generation of Adversarial and Cooperative Point Clouds

no code implementations25 Sep 2019 Yuxin Wen, Jiehong Lin, Ke Chen, Kui Jia

Recent studies show that machine learning models are vulnerable to adversarial examples.


Learning-Based Video Game Development in MLP@UoM: An Overview

no code implementations27 Aug 2019 Ke Chen

In general, video games not only prevail in entertainment but also have become an alternative methodology for knowledge learning, skill acquisition and assistance for medical treatment as well as health care in education, vocational/military training and medicine.

BIG-bench Machine Learning

Fast Fourier Color Constancy and Grayness Index for ISPA Illumination Estimation Challenge

no code implementations6 Aug 2019 Yanlin Qian, Ke Chen, Huanglin Yu

We briefly introduce two submissions to the Illumination Estimation Challenge, in the Int'l Workshop on Color Vision, affiliated to the 11th Int'l Symposium on Image and Signal Processing and Analysis.

Color Constancy

Semi-Supervised Few-Shot Learning for Dual Question-Answer Extraction

no code implementations8 Apr 2019 Jue Wang, Ke Chen, Lidan Shou, Sai Wu, Sharad Mehrotra

In this paper, we redefine the problem as question-answer extraction, and present SAMIE: Self-Asking Model for Information Ixtraction, a semi-supervised model which dually learns to ask and to answer questions by itself.

Clustering Few-Shot Learning

ShopSign: a Diverse Scene Text Dataset of Chinese Shop Signs in Street Views

2 code implementations25 Mar 2019 Chongsheng Zhang, Guowen Peng, Yuefeng Tao, Feifei Fu, Wei Jiang, George Almpanidis, Ke Chen

Hence, we collect and annotate the ShopSign dataset to advance research in Chinese scene text detection and recognition.

Scene Text Detection Text Detection

Tooth morphometry using quasi-conformal theory

no code implementations7 Jan 2019 Gary P. T. Choi, Hei Long Chan, Robin Yong, Sarbin Ranjitkar, Alan Brook, Grant Townsend, Ke Chen, Lok Ming Lui

We deploy our framework on a dataset of human premolars to analyze the tooth shape variation among genders and ancestries.

General Classification

The Effect of Explicit Structure Encoding of Deep Neural Networks for Symbolic Music Generation

1 code implementation20 Nov 2018 Ke Chen, Weilin Zhang, Shlomo Dubnov, Gus Xia, Wei Li

With recent breakthroughs in artificial neural networks, deep generative models have become one of the leading techniques for computational creativity.

Music Generation

Learning to Play General Video-Games via an Object Embedding Network

1 code implementation14 Mar 2018 William Woof, Ke Chen

Deep reinforcement learning (DRL) has proven to be an effective tool for creating general video-game AI.

Three-Stream Convolutional Networks for Video-based Person Re-Identification

no code implementations22 Nov 2017 Zeng Yu, Tianrui Li, Ning Yu, Xun Gong, Ke Chen, Yi Pan

This paper aims to develop a new architecture that can make full use of the feature maps of convolutional networks.

Video-Based Person Re-Identification

Recurrent Color Constancy

no code implementations ICCV 2017 Yanlin Qian, Ke Chen, Jarno Nikkanen, Joni-Kristian Kamarainen, Jiri Matas

We introduce a novel formulation of temporal color constancy which considers multiple frames preceding the frame for which illumination is estimated.

Color Constancy

Multi-Label Zero-Shot Human Action Recognition via Joint Latent Ranking Embedding

no code implementations15 Sep 2017 Qian Wang, Ke Chen

Our framework holistically tackles the issue of unknown temporal boundaries between different actions for multi-label learning and exploits the side information regarding the semantic relationship between different human actions for knowledge transfer.

Action Recognition Multi-Label Learning +3

Implicit Gradient Neural Networks with a Positive-Definite Mass Matrix for Online Linear Equations Solving

no code implementations17 Mar 2017 Ke Chen

Motivated by the advantages achieved by implicit analogue net for solving online linear equations, a novel implicit neural model is designed based on conventional explicit gradient neural networks in this letter by introducing a positive-definite mass matrix.

Convolutional Low-Resolution Fine-Grained Classification

no code implementations15 Mar 2017 Dingding Cai, Ke Chen, Yanlin Qian, Joni-Kristian Kämäräinen

Successful fine-grained image classification methods learn subtle details between visually similar (sub-)classes, but the problem becomes significantly more challenging if the details are missing due to low resolution.

Classification Fine-Grained Image Classification +2

Deploying learning materials to game content for serious education game development: A case study

no code implementations4 Aug 2016 Harits Ar Rosyid, Matt Palmerlee, Ke Chen

Unlike previous work where experts in education have to be used heavily, we proposed a novel approach that works toward minimizing the efforts of education experts in mapping learning materials to content space.

On the Use of Sparse Filtering for Covariate Shift Adaptation

1 code implementation22 Jul 2016 Fabio Massimo Zennaro, Ke Chen

We provide a theoretical analysis of sparse filtering by evaluating the conditions required to perform covariate shift adaptation.

Deep Structured-Output Regression Learning for Computational Color Constancy

no code implementations13 Jul 2016 Yanlin Qian, Ke Chen, Joni-Kristian Kamarainen, Jarno Nikkanen, Jiri Matas

Computational color constancy that requires esti- mation of illuminant colors of images is a fundamental yet active problem in computer vision, which can be formulated into a regression problem.

Color Constancy regression

Zero-Shot Visual Recognition via Bidirectional Latent Embedding

no code implementations7 Jul 2016 Qian Wang, Ke Chen

In the top-down stage, semantic representations of unseen-class labels in a given label vocabulary are then embedded to the same latent space to preserve the semantic relatedness between all different classes via our proposed semi-supervised Sammon mapping with the guidance of landmarks.

Action Recognition Temporal Action Localization

Multi-Label Zero-Shot Learning via Concept Embedding

no code implementations1 Jun 2016 Ubai Sandouk, Ke Chen

Thus, our approach allows both seen and unseen labels during the concept embedding learning to be used in the aforementioned instance mapping, which makes multi-label ZSL more flexible and suitable for real applications.

Multi-label zero-shot learning

Efficient Feature-based Image Registration by Mapping Sparsified Surfaces

no code implementations20 May 2016 Chun Pang Yung, Gary P. T. Choi, Ke Chen, Lok Ming Lui

For each high resolution image or video frame, we compute an optimal coarse triangulation which captures the important features of the image.

Image Registration

Towards Understanding Sparse Filtering: A Theoretical Perspective

no code implementations29 Mar 2016 Fabio Massimo Zennaro, Ke Chen

In this paper we present a theoretical analysis to understand sparse filtering, a recent and effective algorithm for unsupervised learning.

Car Type Recognition with Deep Neural Networks

2 code implementations23 Feb 2016 Heikki Huttunen, Fatemeh Shokrollahi Yancheshmeh, Ke Chen

In this paper we study automatic recognition of cars of four types: Bus, Truck, Van and Small car.

Vocal Bursts Type Prediction

Learning Constructive Primitives for Online Level Generation and Real-time Content Adaptation in Super Mario Bros

no code implementations27 Oct 2015 Peizhi Shi, Ke Chen

Also the adaptive content can be generated in real time by dynamically selecting proper constructive primitives via an adaptation criterion, e. g., dynamic difficulty adjustment (DDA).

A Total Fractional-Order Variation Model for Image Restoration with Non-homogeneous Boundary Conditions and its Numerical Solution

no code implementations6 Sep 2015 Jianping Zhang, Ke Chen

In this paper we analyze and test a fractional-order derivative based total $\alpha$-order variation model, which can outperform the currently popular high order regularization models.

Image Restoration

Learning Contextualized Semantics from Co-occurring Terms via a Siamese Architecture

no code implementations17 Jun 2015 Ubai Sandouk, Ke Chen

By means of pattern aggregation and probabilistic topic models, our Siamese architecture captures contextualized semantics from the co-occurring descriptive terms via unsupervised learning, which leads to a concept embedding space of the terms in context.

Descriptive Information Retrieval +2

Unsupervised Visual Alignment With Similarity Graphs

no code implementations CVPR 2015 Fatemeh Shokrollahi Yancheshmeh, Ke Chen, Joni-Kristian Kamarainen

In this work, we adopt the feature basedapproach, but to overcome the aforementioned drawbacks define visual similarity as an assignment problem which is solved by fast approximation and non-linear optimization. From pair-wise image similarities we construct an image graph which is used to step-wise align,``morph'', an image to another by graph traveling.

Image Categorization MORPH +2

Learning Contextualized Music Semantics from Tags via a Siamese Network

no code implementations29 Apr 2015 Ubai Sandouk, Ke Chen

We conduct experiments on three public music tag collections -namely, CAL500, MagTag5K and Million Song Dataset- and compare our approach to a number of state-of-the-art semantics learning approaches.

Information Retrieval Music Information Retrieval +3

Rapid Skill Capture in a First-Person Shooter

no code implementations5 Nov 2014 David Buckley, Ke Chen, Joshua Knowles

Various aspects of computer game design, including adaptive elements of game levels, characteristics of 'bot' behavior, and player matching in multiplayer games, would ideally be sensitive to a player's skill level.

Learning-Based Procedural Content Generation

no code implementations29 Aug 2013 Jonathan Roberts, Ke Chen

Procedural content generation (PCG) has recently become one of the hottest topics in computational intelligence and AI game researches.

Cumulative Attribute Space for Age and Crowd Density Estimation

no code implementations CVPR 2013 Ke Chen, Shaogang Gong, Tao Xiang, Chen Change Loy

A number of computer vision problems such as human age estimation, crowd density estimation and body/face pose (view angle) estimation can be formulated as a regression problem by learning a mapping function between a high dimensional vector-formed feature input and a scalarvalued output.

Age Estimation Crowd Counting +2

Extracting Speaker-Specific Information with a Regularized Siamese Deep Network

no code implementations NeurIPS 2011 Ke Chen, Ahmad Salman

Speech conveys different yet mixed information ranging from linguistic to speaker-specific components, and each of them should be exclusively used in a specific task.

Speaker Recognition

Regularized Boost for Semi-Supervised Learning

no code implementations NeurIPS 2007 Ke Chen, Shihai Wang

Semi-supervised inductive learning concerns how to learn a decision rule from a data set containing both labeled and unlabeled data.

Ensemble Learning

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