Search Results for author: Yi Fang

Found 80 papers, 17 papers with code

How Secure Are Large Language Models (LLMs) for Navigation in Urban Environments?

no code implementations14 Feb 2024 Congcong Wen, Jiazhao Liang, Shuaihang Yuan, Hao Huang, Yi Fang

In the field of robotics and automation, navigation systems based on Large Language Models (LLMs) have recently shown impressive performance.

Autonomous Driving Few-Shot Learning +1

Differentiable Registration of Images and LiDAR Point Clouds with VoxelPoint-to-Pixel Matching

1 code implementation NeurIPS 2023 Junsheng Zhou, Baorui Ma, Wenyuan Zhang, Yi Fang, Yu-Shen Liu, Zhizhong Han

To address these problems, we propose to learn a structured cross-modality latent space to represent pixel features and 3D features via a differentiable probabilistic PnP solver.

MemoryCompanion: A Smart Healthcare Solution to Empower Efficient Alzheimer's Care Via Unleashing Generative AI

no code implementations20 Nov 2023 Lifei Zheng, Yeonie Heo, Yi Fang

With the rise of Large Language Models (LLMs), notably characterized by GPT frameworks, there emerges a catalyst for novel healthcare applications.

Chatbot Prompt Engineering +1

NeuralGF: Unsupervised Point Normal Estimation by Learning Neural Gradient Function

1 code implementation NeurIPS 2023 Qing Li, Huifang Feng, Kanle Shi, Yue Gao, Yi Fang, Yu-Shen Liu, Zhizhong Han

Specifically, we introduce loss functions to facilitate query points to iteratively reach the moving targets and aggregate onto the approximated surface, thereby learning a global surface representation of the data.

VisPercep: A Vision-Language Approach to Enhance Visual Perception for People with Blindness and Low Vision

no code implementations31 Oct 2023 Yu Hao, Fan Yang, Hao Huang, Shuaihang Yuan, Sundeep Rangan, John-Ross Rizzo, Yao Wang, Yi Fang

By combining the prompt and input image, a large vision-language model (i. e., InstructBLIP) generates detailed and comprehensive descriptions of the environment and identifies potential risks in the environment by analyzing the environmental objects and scenes, relevant to the prompt.

Language Modelling Prompt Engineering +1

Neural Gradient Learning and Optimization for Oriented Point Normal Estimation

1 code implementation17 Sep 2023 Qing Li, Huifang Feng, Kanle Shi, Yi Fang, Yu-Shen Liu, Zhizhong Han

We propose Neural Gradient Learning (NGL), a deep learning approach to learn gradient vectors with consistent orientation from 3D point clouds for normal estimation.

Revisiting Fine-Tuning Strategies for Self-supervised Medical Imaging Analysis

no code implementations20 Jul 2023 Muhammad Osama Khan, Yi Fang

In this paper, we present the first comprehensive study that discovers effective fine-tuning strategies for self-supervised learning in medical imaging.

Self-Supervised Learning

Soft Prompt Tuning for Augmenting Dense Retrieval with Large Language Models

1 code implementation17 Jul 2023 Zhiyuan Peng, Xuyang Wu, Qifan Wang, Yi Fang

We design a filter to select high-quality example document-query pairs in the prompt to further improve the quality of weak tagged queries.

Retrieval TAG +1

SHS-Net: Learning Signed Hyper Surfaces for Oriented Normal Estimation of Point Clouds

1 code implementation CVPR 2023 Qing Li, Huifang Feng, Kanle Shi, Yue Gao, Yi Fang, Yu-Shen Liu, Zhizhong Han

In this work, we introduce signed hyper surfaces (SHS), which are parameterized by multi-layer perceptron (MLP) layers, to learn to estimate oriented normals from point clouds in an end-to-end manner.

LP-DIF: Learning Local Pattern-Specific Deep Implicit Function for 3D Objects and Scenes

no code implementations CVPR 2023 Meng Wang, Yu-Shen Liu, Yue Gao, Kanle Shi, Yi Fang, Zhizhong Han

To capture geometry details, current mainstream methods divide 3D shapes into local regions and then learn each one with a local latent code via a decoder, where the decoder shares the geometric similarities among different local regions.

3D Reconstruction 3D Shape Representation

HSurf-Net: Normal Estimation for 3D Point Clouds by Learning Hyper Surfaces

1 code implementation13 Oct 2022 Qing Li, Yu-Shen Liu, Jin-San Cheng, Cheng Wang, Yi Fang, Zhizhong Han

To address these issues, we introduce hyper surface fitting to implicitly learn hyper surfaces, which are represented by multi-layer perceptron (MLP) layers that take point features as input and output surface patterns in a high dimensional feature space.

Surface Normals Estimation

Learning Consistency-Aware Unsigned Distance Functions Progressively from Raw Point Clouds

1 code implementation6 Oct 2022 Junsheng Zhou, Baorui Ma, Yu-Shen Liu, Yi Fang, Zhizhong Han

In this paper, we propose a novel method to learn consistency-aware unsigned distance functions directly from raw point clouds.

Surface Reconstruction

Understanding the Impact of Image Quality and Distance of Objects to Object Detection Performance

no code implementations17 Sep 2022 Yu Hao, Haoyang Pei, Yixuan Lyu, Zhongzheng Yuan, John-Ross Rizzo, Yao Wang, Yi Fang

We further assess the impact of the distance of an object to the camera on the detection accuracy and show that higher spatial resolution enables a greater detection range.

Object object-detection +1

Dynamic Write-Voltage Design and Read-Voltage Optimization for MLC NAND Flash Memory

no code implementations3 Sep 2022 Runbin Cai, Yi Fang, Zhifang Shi, Lin Dai, Guojun Han

To mitigate the impact of noise and interference on multi-level-cell (MLC) flash memory with the use of low-density parity-check (LDPC) codes, we propose a dynamic write-voltage design scheme considering the asymmetric property of raw bit error rate (RBER), which can obtain the optimal write voltage by minimizing a cost function.

Detect and Approach: Close-Range Navigation Support for People with Blindness and Low Vision

no code implementations17 Aug 2022 Yu Hao, Junchi Feng, John-Ross Rizzo, Yao Wang, Yi Fang

These functions enable the system to suggest an initial navigation path, continuously update the path as the user moves, and offer timely recommendation about the correction of the user's path.

Object Object Localization

Perceptual Quality Assessment of Omnidirectional Images

no code implementations6 Jul 2022 Huiyu Duan, Guangtao Zhai, Xiongkuo Min, Yucheng Zhu, Yi Fang, Xiaokang Yang

The original and distorted omnidirectional images, subjective quality ratings, and the head and eye movement data together constitute the OIQA database.

Image Quality Assessment

Reconfigurable Intelligent Surface-aided $M$-ary FM-DCSK System: a New Design for Noncoherent Chaos-based Communication

no code implementations16 Jun 2022 Huan Ma, Yi Fang, Pingping Chen, Yonghui Li

In this paper, we propose two reconfigurable intelligent surface-aided $M$-ary frequency-modulated differential chaos shift keying (RIS-$M$-FM-DCSK) schemes.

The low-entropy hydration shell at the binding site of spike RBD determines the contagiousness of SARS-CoV-2 variants

no code implementations27 Apr 2022 Lin Yang, Shuai Guo, Chengyu Houc, Jiacheng Lia, Liping Shi, Chenchen Liao, Rongchun Shi, Xiaoliang Ma, Bing Zheng, Yi Fang, Lin Ye, Xiaodong He

The low-entropy level of hydration shells at the binding site of a spike protein is found to be an important indicator of the contagiousness of the coronavirus.

Multi-organ Segmentation Network with Adversarial Performance Validator

no code implementations16 Apr 2022 HaoYu Fang, Yi Fang, Xiaofeng Yang

The proposed network organically converts the 2D-coarse result to 3D high-quality segmentation masks in a coarse-to-fine manner, allowing joint optimization to improve segmentation accuracy.

Computed Tomography (CT) Organ Segmentation +2

3D-OAE: Occlusion Auto-Encoders for Self-Supervised Learning on Point Clouds

1 code implementation26 Mar 2022 Junsheng Zhou, Xin Wen, Baorui Ma, Yu-Shen Liu, Yue Gao, Yi Fang, Zhizhong Han

To address this problem, we present a novel and efficient self-supervised point cloud representation learning framework, named 3D Occlusion Auto-Encoder (3D-OAE), to facilitate the detailed supervision inherited in local regions and global shapes.

Representation Learning Self-Supervised Learning

DIANES: A DEI Audit Toolkit for News Sources

no code implementations21 Mar 2022 Xiaoxiao Shang, Zhiyuan Peng, Qiming Yuan, Sabiq Khan, Lauren Xie, Yi Fang, Subramaniam Vincent

Professional news media organizations have always touted the importance that they give to multiple perspectives.

Cultural Vocal Bursts Intensity Prediction

Deep Partial Multiplex Network Embedding

no code implementations5 Mar 2022 Qifan Wang, Yi Fang, Anirudh Ravula, Ruining He, Bin Shen, Jingang Wang, Xiaojun Quan, Dongfang Liu

Network embedding is an effective technique to learn the low-dimensional representations of nodes in networks.

Link Prediction Network Embedding +1

Space Layout of Low-entropy Hydration Shells Guides Protein Binding

no code implementations22 Feb 2022 Lin Yang, Shuai Guo, Chengyu Hou, Chencheng Liao, Jiacheng Li, Liping Shi, Xiaoliang Ma, Shenda Jiang, Bing Zheng, Yi Fang, Lin Ye, Xiaodong He

According to an analysis of determined protein complex structures, shape matching between the largest low-entropy hydration shell region of a protein and that of its partner at the binding sites is revealed as a regular pattern.

A Multi-task Learning Framework for Product Ranking with BERT

no code implementations10 Feb 2022 Xuyang Wu, Alessandro Magnani, Suthee Chaidaroon, Ajit Puthenputhussery, Ciya Liao, Yi Fang

The proposed model utilizes domain-specific BERT with fine-tuning to bridge the vocabulary gap and employs multi-task learning to optimize multiple objectives simultaneously, which yields a general end-to-end learning framework for product search.

Information Retrieval Multi-Task Learning +1

WebFormer: The Web-page Transformer for Structure Information Extraction

no code implementations1 Feb 2022 Qifan Wang, Yi Fang, Anirudh Ravula, Fuli Feng, Xiaojun Quan, Dongfang Liu

Structure information extraction refers to the task of extracting structured text fields from web pages, such as extracting a product offer from a shopping page including product title, description, brand and price.

Deep Attention document understanding +1

Network-Aware 5G Edge Computing for Object Detection: Augmenting Wearables to "See" More, Farther and Faster

no code implementations25 Dec 2021 Zhongzheng Yuan, Tommy Azzino, Yu Hao, Yixuan Lyu, Haoyang Pei, Alain Boldini, Marco Mezzavilla, Mahya Beheshti, Maurizio Porfiri, Todd Hudson, William Seiple, Yi Fang, Sundeep Rangan, Yao Wang, J. R. Rizzo

The vision evaluation is combined with a detailed full-stack wireless network simulation to determine the distribution of throughputs and delays with real navigation paths and ray-tracing from new high-resolution 3D models in an urban environment.

Edge-computing object-detection +1

Deps-SAN: Neural Machine Translation with Dependency-Scaled Self-Attention Network

no code implementations23 Nov 2021 Ru Peng, Nankai Lin, Yi Fang, Shengyi Jiang, Tianyong Hao, BoYu Chen, Junbo Zhao

However, succeeding researches pointed out that limited by the uncontrolled nature of attention computation, the NMT model requires an external syntax to capture the deep syntactic awareness.

Machine Translation NMT +1

3D Meta-Segmentation Neural Network

no code implementations8 Oct 2021 Yu Hao, Yi Fang

Based on the learned information of task distribution, our meta part segmentation learner is able to dynamically update the part segmentation learner with optimal parameters which enable our part segmentation learner to rapidly adapt and have great generalization ability on new part segmentation tasks.

3D Part Segmentation 3D Point Cloud Part Segmentation +2

Meta-Learning 3D Shape Segmentation Functions

no code implementations8 Oct 2021 Yu Hao, Hao Huang, Shuaihang Yuan, Yi Fang

We show in experiments that our meta-learning approach, denoted as Meta-3DSeg, leads to improvements on unsupervised 3D shape segmentation over the conventional designs of deep neural networks for 3D shape segmentation functions.

3D Shape Reconstruction Meta-Learning +1

3D Unsupervised Region-Aware Registration Transformer

no code implementations7 Oct 2021 Yu Hao, Yi Fang

This paper concerns the research problem of point cloud registration to find the rigid transformation to optimally align the source point set with the target one.

3D Shape Reconstruction Point Cloud Registration +1

Contrastive Learning of 3D Shape Descriptor with Dynamic Adversarial Views

no code implementations29 Sep 2021 Shuaihang Yuan, Yi Fang

In addition, CoLAV introduces a novel mechanism for the dynamic generation of shape-instance-dependent adversarial views as positive pairs to adversarially train robust contrastive learning models towards the learning of more informative 3D shape representation.

3D Shape Classification 3D Shape Recognition +4

3D Meta-Registration: Meta-learning 3D Point Cloud Registration Functions

no code implementations29 Sep 2021 Yu Hao, Yi Fang

Learning robust 3D point cloud registration functions with deep neural networks has emerged as a powerful paradigm in recent years, offering promising performance in producing spatial geometric transformations for each pair of 3D point clouds.

Meta-Learning Point Cloud Registration

3D Point Cloud Completion with Geometric-Aware Adversarial Augmentation

no code implementations21 Sep 2021 Mengxi Wu, Hao Huang, Yi Fang

In contrast to the PGD-k attack, our method generates adversarial samples that keep the geometric features in clean samples and contain few outliers.

Point Cloud Classification Point Cloud Completion

ContinuityLearner: Geometric Continuity Feature Learning for Lane Segmentation

no code implementations7 Aug 2021 HaoYu Fang, Jing Zhu, Yi Fang

Lane segmentation is a challenging issue in autonomous driving system designing because lane marks show weak textural consistency due to occlusion or extreme illumination but strong geometric continuity in traffic images, from which general convolution neural networks (CNNs) are not capable of learning semantic objects.

Autonomous Driving Segmentation

Learn to Learn Metric Space for Few-Shot Segmentation of 3D Shapes

no code implementations7 Jul 2021 Xiang Li, Lingjing Wang, Yi Fang

To achieve this, we treat the shape segmentation as a point labeling problem in the metric space.

Meta-Learning Segmentation

Residual Networks as Flows of Velocity Fields for Diffeomorphic Time Series Alignment

no code implementations22 Jun 2021 Hao Huang, Boulbaba Ben Amor, Xichan Lin, Fan Zhu, Yi Fang

Our ResNet-TW (Deep Residual Network for Time Warping) tackles the alignment problem by compositing a flow of incremental diffeomorphic mappings.

Time Series Time Series Alignment

G-VAE, a Geometric Convolutional VAE for ProteinStructure Generation

no code implementations22 Jun 2021 Hao Huang, Boulbaba Ben Amor, Xichan Lin, Fan Zhu, Yi Fang

In this work, we introduce a joint geometric-neural networks approach for comparing, deforming and generating 3D protein structures.

Dual Attention Guided Gaze Target Detection in the Wild

1 code implementation CVPR 2021 Yi Fang, Jiapeng Tang, Wang Shen, Wei Shen, Xiao Gu, Li Song, Guangtao Zhai

In the third stage, we use the generated dual attention as guidance to perform two sub-tasks: (1) identifying whether the gaze target is inside or out of the image; (2) locating the target if inside.

A New Frequency-Bin-Index LoRa System for High-Data-Rate Transmission: Design and Performance Analysis

no code implementations29 Mar 2021 Huan Ma, Yi Fang, Guofa Cai, Guojun Han, Yonghui Li

To further improve the system flexibility, we formulate a generalized modulation scheme and propose scheme II by treating the SFB groups as an additional type of transmission entity.

Correction to the photometric magnitudes of the Gaia Early Data Release 3

no code implementations4 Jan 2021 Lin Yang, HaiBo Yuan, Ruoyi Zhang, Zexi Niu, Yang Huang, Fuqing Duan, Yi Fang

In this letter, we have carried out an independent validation of the Gaia EDR3 photometry using about 10, 000 Landolt standard stars from Clem & Landolt (2013).

Solar and Stellar Astrophysics Astrophysics of Galaxies

Leveraging an Efficient and Semantic Location Embedding to Seek New Ports of Bike Share Services

1 code implementation6 Nov 2020 YuAn Wang, Chenwei Wang, Yinan Ling, Keita Yokoyama, Hsin-Tai Wu, Yi Fang

Finally, we apply ESLE to seek new service ports for NTT DOCOMO's bike share services operated in Japan.

3D Meta-Registration: Learning to Learn Registration of 3D Point Clouds

no code implementations22 Oct 2020 Lingjing Wang, Yu Hao, Xiang Li, Yi Fang

In this paper, we propose a meta-learning based 3D registration model, named 3D Meta-Registration, that is capable of rapidly adapting and well generalizing to new 3D registration tasks for unseen 3D point clouds.

Meta-Learning Point Cloud Registration

3D Meta Point Signature: Learning to Learn 3D Point Signature for 3D Dense Shape Correspondence

no code implementations21 Oct 2020 Hao Huang, Lingjing Wang, Xiang Li, Yi Fang

In this paper, we propose a novel meta-learning based 3D point signature model, named 3Dmetapointsignature (MEPS) network, that is capable of learning robust point signatures in 3D shapes.

3D Dense Shape Correspondence Meta-Learning

Deep-3DAligner: Unsupervised 3D Point Set Registration Network With Optimizable Latent Vector

no code implementations29 Sep 2020 Lingjing Wang, Xiang Li, Yi Fang

Point cloud registration is the process of aligning a pair of point sets via searching for a geometric transformation.

Point Cloud Registration

Unsupervised Partial Point Set Registration via Joint Shape Completion and Registration

no code implementations11 Sep 2020 Xiang Li, Lingjing Wang, Yi Fang

To bridge the performance gaps between partial point set registration with full point set registration, we proposed to incorporate a shape completion network to benefit the registration process.

Robust Image Matching By Dynamic Feature Selection

no code implementations13 Aug 2020 Hao Huang, Jianchun Chen, Xiang Li, Lingjing Wang, Yi Fang

Recent works introduce convolutional neural networks (CNNs) to extract high-level feature maps and find correspondences through feature matching.

Decision Making feature selection +1

GP-Aligner: Unsupervised Non-rigid Groupwise Point Set Registration Based On Optimized Group Latent Descriptor

no code implementations25 Jul 2020 Lingjing Wang, Xiang Li, Yi Fang

More specifically, for a given group we first define an optimizable Group Latent Descriptor (GLD) to characterize the gruopwise relationship among a group of point sets.

Computational Efficiency

Design and Performance Analysis of a New STBC-MIMO LoRa System

no code implementations28 Jun 2020 Huan Ma, Guofa Cai, Yi Fang, Pingping Chen, Guojun Han

The result demonstrates that the diversity order of the system in the imperfect CSI scenario with fixed channel estimate error variance is zero.

Meta Deformation Network: Meta Functionals for Shape Correspondence

no code implementations26 Jun 2020 Daohan Lu, Yi Fang

We present a new technique named "Meta Deformation Network" for 3D shape matching via deformation, in which a deep neural network maps a reference shape onto the parameters of a second neural network whose task is to give the correspondence between a learned template and query shape via deformation.

DeepTracking-Net: 3D Tracking with Unsupervised Learning of Continuous Flow

no code implementations24 Jun 2020 Shuaihang Yuan, Xiang Li, Yi Fang

In this paper, we aim at handling the problem of 3D tracking, which provides the tracking of the consecutive frames of 3D shapes.

3DMotion-Net: Learning Continuous Flow Function for 3D Motion Prediction

no code implementations24 Jun 2020 Shuaihang Yuan, Xiang Li, Anthony Tzes, Yi Fang

To approach this problem, we propose a self-supervised approach that leverages the power of the deep neural network to learn a continuous flow function of 3D point clouds that can predict temporally consistent future motions and naturally bring out the correspondences among consecutive point clouds at the same time.

motion prediction

Unsupervised Learning of Global Registration of Temporal Sequence of Point Clouds

no code implementations17 Jun 2020 Lingjing Wang, Yi Shi, Xiang Li, Yi Fang

Global registration of point clouds aims to find an optimal alignment of a sequence of 2D or 3D point sets.

Few-shot Object Detection on Remote Sensing Images

no code implementations14 Jun 2020 Jingyu Deng, Xiang Li, Yi Fang

In this paper, we introduce a few-shot learning-based method for object detection on remote sensing images where only a few annotated samples are provided for the unseen object categories.

Few-Shot Learning Few-Shot Object Detection +2

Unsupervised Learning of 3D Point Set Registration

no code implementations11 Jun 2020 Lingjing Wang, Xiang Li, Yi Fang

Moreover, for a pair of source and target point sets, existing deep learning mechanisms require explicitly designed encoders to extract both deep spatial features from unstructured point clouds and their spatial correlation representation, which is further fed to a decoder to regress the desired geometric transformation for point set alignment.

Point Cloud Registration

Geometry-Aware Segmentation of Remote Sensing Images via Implicit Height Estimation

no code implementations10 Jun 2020 Xiang Li, Lingjing Wang, Yi Fang

Recent studies have shown the benefits of using additional elevation data (e. g., DSM) for enhancing the performance of the semantic segmentation of aerial images.

Segmentation Semantic Segmentation

Height estimation from single aerial images using a deep ordinal regression network

no code implementations4 Jun 2020 Xiang Li, Mingyang Wang, Yi Fang

Previous researches have extensively studied the problem of height estimation from aerial images based on stereo or multi-view image matching.

Change Detection Management +1

Arbicon-Net: Arbitrary Continuous Geometric Transformation Networks for Image Registration

1 code implementation NeurIPS 2019 Jianchun Chen, Lingjing Wang, Xiang Li, Yi Fang

To address this issue, we present an end-to-end trainable deep neural networks, named Arbitrary Continuous Geometric Transformation Networks (Arbicon-Net), to directly predict the dense displacement field for pairwise image alignment.

Image Registration

Density-Aware Convolutional Networks with Context Encoding for Airborne LiDAR Point Cloud Classification

no code implementations14 Oct 2019 Xiang Li, Mingyang Wang, Congcong Wen, Lingjing Wang, Nan Zhou, Yi Fang

Based on this convolution module, we further developed a multi-scale fully convolutional neural network with downsampling and upsampling blocks to enable hierarchical point feature learning.

3D Point Cloud Classification General Classification +1

Structure-Attentioned Memory Network for Monocular Depth Estimation

no code implementations10 Sep 2019 Jing Zhu, Yunxiao Shi, Mengwei Ren, Yi Fang, Kuo-Chin Lien, Junli Gu

To this end, we introduce a new Structure-Oriented Memory (SOM) module to learn and memorize the structure-specific information between RGB image domain and the depth domain.

Domain Adaptation Monocular Depth Estimation

Learning Object-specific Distance from a Monocular Image

no code implementations ICCV 2019 Jing Zhu, Yi Fang, Husam Abu-Haimed, Kuo-Chin Lien, Dongdong Fu, Junli Gu

Environment perception, including object detection and distance estimation, is one of the most crucial tasks for autonomous driving.

Autonomous Driving Object +2

Coherent Point Drift Networks: Unsupervised Learning of Non-Rigid Point Set Registration

3 code implementations7 Jun 2019 Lingjing Wang, Xiang Li, Jianchun Chen, Yi Fang

In contrast to previous efforts (e. g. coherent point drift), CPD-Net can learn displacement field function to estimate geometric transformation from a training dataset, consequently, to predict the desired geometric transformation for the alignment of previously unseen pairs without any additional iterative optimization process.

Non-Rigid Point Set Registration Networks

1 code implementation2 Apr 2019 Lingjing Wang, Jianchun Chen, Xiang Li, Yi Fang

In contrast, the proposed point registration neural network (PR-Net) actively learns the registration pattern as a parametric function from a training dataset, consequently predict the desired geometric transformation to align a pair of point sets.

Deep Cross-modality Adaptation via Semantics Preserving Adversarial Learning for Sketch-based 3D Shape Retrieval

no code implementations ECCV 2018 Jiaxin Chen, Yi Fang

Due to the large cross-modality discrepancy between 2D sketches and 3D shapes, retrieving 3D shapes by sketches is a significantly challenging task.

3D Shape Classification 3D Shape Retrieval +2

Collaborative Memory Network for Recommendation Systems

5 code implementations29 Apr 2018 Travis Ebesu, Bin Shen, Yi Fang

We propose Collaborative Memory Networks (CMN), a deep architecture to unify the two classes of CF models capitalizing on the strengths of the global structure of latent factor model and local neighborhood-based structure in a nonlinear fashion.

Collaborative Filtering Recommendation Systems

MOEA/D with Angle-based Constrained Dominance Principle for Constrained Multi-objective Optimization Problems

no code implementations10 Feb 2018 Zhun Fan, Yi Fang, Wenji Li, Xinye Cai, Caimin Wei, Erik Goodman

The experimental results manifest that MOEA/D-ACDP is significantly better than the other four CMOEAs on these test instances and the real-world case, which indicates that ACDP is more effective for solving CMOPs.


ArbiText: Arbitrary-Oriented Text Detection in Unconstrained Scene

no code implementations30 Nov 2017 Daitao Xing, Zichen Li, Xin Chen, Yi Fang

Arbitrary-oriented text detection in the wild is a very challenging task, due to the aspect ratio, scale, orientation, and illumination variations.

Text Detection

3D-A-Nets: 3D Deep Dense Descriptor for Volumetric Shapes with Adversarial Networks

no code implementations28 Nov 2017 Mengwei Ren, Liang Niu, Yi Fang

In this paper, powered with a novel design of adversarial networks (3D-A-Nets), we have developed a novel 3D deep dense shape descriptor (3D-DDSD) to address the challenging issues of efficient and effective 3D volumetric data processing.

3D Shape Classification Clustering +1

Unsupervised 3D Reconstruction from a Single Image via Adversarial Learning

no code implementations26 Nov 2017 Lingjing Wang, Yi Fang

Recent advancements in deep learning opened new opportunities for learning a high-quality 3D model from a single 2D image given sufficient training on large-scale data sets.

3D Reconstruction

Variational Deep Semantic Hashing for Text Documents

2 code implementations11 Aug 2017 Suthee Chaidaroon, Yi Fang

Especially, deep generative models naturally combine the expressiveness of probabilistic generative models with the high capacity of deep neural networks, which is very suitable for text modeling.

Information Retrieval Retrieval +1

An Improved Epsilon Constraint-handling Method in MOEA/D for CMOPs with Large Infeasible Regions

no code implementations27 Jul 2017 Zhun Fan, Wenji Li, Xinye Cai, Han Huang, Yi Fang, Yugen You, Jiajie Mo, Caimin Wei, Erik Goodman

In order to evaluate the performance of MOEA/D-IEpsilon, a new set of CMOPs with two and three objectives is designed, having large infeasible regions (relative to the feasible regions), and they are called LIR-CMOPs.


Learning Barycentric Representations of 3D Shapes for Sketch-Based 3D Shape Retrieval

no code implementations CVPR 2017 Jin Xie, Guoxian Dai, Fan Zhu, Yi Fang

For 3D shapes, we then compute the Wasserstein barycenters of deep features of multiple projections to form a barycentric representation.

3D Shape Classification 3D Shape Retrieval +1

Learned Binary Spectral Shape Descriptor for 3D Shape Correspondence

no code implementations CVPR 2016 Jin Xie, Meng Wang, Yi Fang

Different from these real-valued local shape descriptors, in this paper, we propose to learn a novel binary spectral shape descriptor with the deep neural network for 3D shape correspondence.

DeepShape: Deep Learned Shape Descriptor for 3D Shape Matching and Retrieval

no code implementations CVPR 2015 Jin Xie, Yi Fang, Fan Zhu, Edward Wong

Then, by imposing the Fisher discrimination criterion on the neurons in the hidden layer, we developed a novel discriminative deep auto-encoder for shape feature learning.


3D Deep Shape Descriptor

no code implementations CVPR 2015 Yi Fang, Jin Xie, Guoxian Dai, Meng Wang, Fan Zhu, Tiantian Xu, Edward Wong

Shape descriptor is a concise yet informative representation that provides a 3D object with an identification as a member of some category.

3D Shape Classification 3D Shape Retrieval +1

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