Search Results for author: Ke Chen

Found 64 papers, 23 papers with code

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 Model distillation

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

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.

Electron Microscopy 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 Point Cloud Segmentation +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.

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

3D Object Classification on Partial Point Clouds: A Practical Perspective

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

As a 3D counterpart of object classification in images, object point cloud classification is fundamental to 3D scene understanding, and has drawn great research attention since the release of benchmarking datasets, such as the ModelNet and the ShapeNet.

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.

Deep Clustering Image Classification +2

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.

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.

NER Nested Named Entity Recognition

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.

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 +1

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 Video Recognition

Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering

1 code implementation 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.

Deep Clustering Unsupervised Domain Adaptation

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.

Music Generation

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

1 code implementation14 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

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

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

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).

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.

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.

Few-Shot Learning

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

1 code implementation25 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 Scene 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 +2

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

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

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.

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.

Information Retrieval Topic Models

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 Object Detection

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 +1

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 +1

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.