papers

Publications (36)

cs.CV2019

Color Recognition for Rubik's Cube Robot

Shenglan Liu, Dong Jiang, Lin Feng +6

In this paper, we proposed three methods to solve color recognition of Rubik's cube, which includes one offline method and two online methods. Scatter balance \& extreme learning m…

cs.SD2019

Bottom-up Broadcast Neural Network For Music Genre Classification

Caifeng Liu, Lin Feng, Guochao Liu +2

Music genre recognition based on visual representation has been successfully explored over the last years. Recently, there has been increasing interest in attempting convolutional…

cs.CR2022

Artificial Intelligence Security Competition (AISC)

Yinpeng Dong, Peng Chen, Senyou Deng +49

The security of artificial intelligence (AI) is an important research area towards safe, reliable, and trustworthy AI systems. To accelerate the research on AI security, the Artifi…

cs.CV2024

GMSR:Gradient-Guided Mamba for Spectral Reconstruction from RGB Images

Xinying Wang, Zhixiong Huang, Sifan Zhang +3

Mainstream approaches to spectral reconstruction (SR) primarily focus on designing Convolution- and Transformer-based architectures. However, CNN methods often face challenges in h…

cs.LG2019

Hierarchic Neighbors Embedding

Shenglan Liu, Yang Yu, Yang Liu +3

Manifold learning now plays a very important role in machine learning and many relevant applications. Although its superior performance in dealing with nonlinear data distribution,…

cs.CR2023

Vulnerable Smart Contract Function Locating Based on Multi-Relational Nested Graph Convolutional Network

Haiyang Liu, Yuqi Fan, Lin Feng +1

The immutable and trustable characteristics of blockchain enable smart contracts to be applied in various fields. Unfortunately, smart contracts are subject to various vulnerabilit…

cs.CV2020

FSD-10: A Dataset for Competitive Sports Content Analysis

Shenlan Liu, Xiang Liu, Gao Huang +6

Action recognition is an important and challenging problem in video analysis. Although the past decade has witnessed progress in action recognition with the development of deep lea…

cs.NI2013

A Coverage Strategy for Wireless Sensor Networks in a Three-dimensional Environment

Lin Feng, Tie Qiu, Zhenlong Sun +2

Coverage is one of the fundamental issues in wireless sensor networks (WSNs). It reflects the ability of WSNs to detect the fields of interest. In a real sensor networks applicatio…

cs.LG2019

The Similarity-Consensus Regularized Multi-view Learning for Dimension Reduction

Xiangzhu Meng, Huibing Wang, Lin Feng

During the last decades, learning a low-dimensional space with discriminative information for dimension reduction (DR) has gained a surge of interest. However, it's not accessible…

cs.LG2018

Rough extreme learning machine: a new classification method based on uncertainty measure

Lin Feng, Shuliang Xu, Feilong Wang +1

Extreme learning machine (ELM) is a new single hidden layer feedback neural network. The weights of the input layer and the biases of neurons in hidden layer are randomly generated…

cs.CV2017

Hand Gesture Recognition with Leap Motion

Youchen Du, Shenglan Liu, Lin Feng +2

The recent introduction of depth cameras like Leap Motion Controller allows researchers to exploit the depth information to recognize hand gesture more robustly. This paper propose…

cond-mat.mtrl-sci2012

Stable magnetostructural coupling with tunable magnetoresponsive effects in hexagonal phase-transition ferromagnets

Enke Liu, Wenhong Wang, Lin Feng +8

The magnetostructural coupling between the structural and the magnetic transition plays a crucial role in magnetoresponsive effects in a martensitic-transition system. A combinatio…

cs.CV2024

End-to-End Streaming Video Temporal Action Segmentation with Reinforce Learning

Jinrong Zhang, Wujun Wen, Shenglan Liu +3

The streaming temporal action segmentation (STAS) task, a supplementary task of temporal action segmentation (TAS), has not received adequate attention in the field of video unders…

cs.LG2019

Multi-view Locality Low-rank Embedding for Dimension Reduction

Lin Feng, Xiangzhu Meng, Huibing Wang

During the last decades, we have witnessed a surge of interests of learning a low-dimensional space with discriminative information from one single view. Even though most of them c…

cs.SI2021

Deep graph convolution neural network with non-negative matrix factorization for community discovery

Shuliang Xu, Shenglan Liu, Lin Feng

Community discovery is an important task for graph mining. Owing to the nonstructure, the high dimensionality, and the sparsity of graph data, it is not easy to obtain an appropria…

cs.CV2018

Multi-view Reconstructive Preserving Embedding for Dimension Reduction

Huibing Wang, Lin Feng, Adong Kong +1

With the development of feature extraction technique, one sample always can be represented by multiple features which locate in high-dimensional space. Multiple features can re ect…

math.OC2025

A Generalized Energy-Based Adaptive Gradient Method for Optimization

Lin Feng, Hailiang Liu

Adaptive Gradient Descent with Energy (AEGD) is a variant of Gradient Descent (GD) designed to address step size sensitivity through an energy-based formulation. AEGD is notable fo…

cs.SD2017

Music Genre Classification with Paralleling Recurrent Convolutional Neural Network

Lin Feng, Shenlan Liu, Jianing Yao

Deep learning has been demonstrated its effectiveness and efficiency in music genre classification. However, the existing achievements still have several shortcomings which impair…

cs.CV2024

Underwater Variable Zoom: Depth-Guided Perception Network for Underwater Image Enhancement

Zhixiong Huang, Xinying Wang, Chengpei Xu +2

Underwater scenes intrinsically involve degradation problems owing to heterogeneous ocean elements. Prevailing underwater image enhancement (UIE) methods stick to straightforward f…

cs.RO2024

Non-contact Dexterous Micromanipulation with Multiple Optoelectronic Robots

Yongyi Jia, Shu Miao, Ao Wang +4

Micromanipulation systems leverage automation and robotic technologies to improve the precision, repeatability, and efficiency of various tasks at the microscale. However, current…

cs.LG2021

A unified framework based on graph consensus term for multi-view learning

Xiangzhu Meng, Lin Feng, Chonghui Guo

In recent years, multi-view learning technologies for various applications have attracted a surge of interest. Due to more compatible and complementary information from multiple vi…

eess.SY2026

Input-to-State Stable Bundle Koopman Neural ODEs for Learning Controlled Dynamics under Environmental Constraints

Lin Feng

We propose ISS-BKNO, a unified framework that integrates Koopman operator identification, Neural ordinary differential equations (ODEs), fiber bundle geometry, and input-to-state s…

eess.SY2026

Safe Data-Driven Control and Dynamical Learning via Constrained Neural Architectures and Koopman Operators

Lin Feng, Xin He

The deployment of learning-based models in safety-critical control systems demands mathematical guarantees that standard regression architectures cannot provide. This paper present…

physics.app-ph2021

High-responsivity, High-detectivity Photomultiplication Organic Photodetector Realized by a Metal-Insulator-Semiconductor Tunneling Junction

Linlin Shi, Ning Li, Ting Ji +10

Organic photodetectors (OPDs) possess bright prospects in applications of medical imaging and wearable electronics due to the advantages such as low cost, good biocompatibility, an…

cs.CV2025

Convolutional Feature Noise Reduction for 2D Cardiac MR Image Segmentation

Hong Zheng, Nan Mu, Han Su +2

Noise reduction constitutes a crucial operation within Digital Signal Processing. Regrettably, it frequently remains neglected when dealing with the processing of convolutional fea…

cs.LG2020

Multi-view Low-rank Preserving Embedding: A Novel Method for Multi-view Representation

Xiangzhu Meng, Lin Feng, Huibing Wang

In recent years, we have witnessed a surge of interest in multi-view representation learning, which is concerned with the problem of learning representations of multi-view data. Wh…

cs.CV2016

Perceptual uniform descriptor and Ranking on manifold: A bridge between image representation and ranking for image retrieval

Shenglan Liu, Jun Wu, Lin Feng +4

Incompatibility of image descriptor and ranking is always neglected in image retrieval. In this paper, manifold learning and Gestalt psychology theory are involved to solve the inc…

cs.CV2019

A fast online cascaded regression algorithm for face alignment

Lin Feng, Caifeng Liu, Shenglan Liu +1

Traditional face alignment based on machine learning usually tracks the localizations of facial landmarks employing a static model trained offline where all of the training data is…

cs.CV2017

Neural method for Explicit Mapping of Quasi-curvature Locally Linear Embedding in image retrieval

Shenglan Liu, Jun Wu, Lin Feng +1

This paper proposed a new explicit nonlinear dimensionality reduction using neural networks for image retrieval tasks. We first proposed a Quasi-curvature Locally Linear Embedding…

eess.SY2026

Environment-Aware Stable Neural Koopman Dynamics Learning for Input-Driven Systems under Environmental Constraints

Lin Feng

Constructing predictive models of nonlinear dynamical systems from measurement data is a longstanding problem in systems identification and control. Although Neural ordinary differ…

cs.CV2016

Three Tiers Neighborhood Graph and Multi-graph Fusion Ranking for Multi-feature Image Retrieval: A Manifold Aspect

Shenglan Liu, Muxin Sun, Lin Feng +2

Single feature is inefficient to describe content of an image, which is a shortcoming in traditional image retrieval task. We know that one image can be described by different feat…

cs.CV2023

Streaming Video Temporal Action Segmentation In Real Time

Wujun Wen, Yunheng Li, Zhuben Dong +3

Temporal action segmentation (TAS) is a critical step toward long-term video understanding. Recent studies follow a pattern that builds models based on features instead of raw vide…

cs.SI2021

Self-Supervised Deep Graph Embedding with High-Order Information Fusion for Community Discovery

Shuliang Xu, Shenglan Liu, Lin Feng

Deep graph embedding is an important approach for community discovery. Deep graph neural network with self-supervised mechanism can obtain the low-dimensional embedding vectors of…

cs.LG2021

Multimodal-Aware Weakly Supervised Metric Learning with Self-weighting Triplet Loss

Huiyuan Deng, Xiangzhu Meng, Lin Feng

In recent years, we have witnessed a surge of interests in learning a suitable distance metric from weakly supervised data. Most existing methods aim to pull all the similar sample…

cs.CV2018

Perceptual Visual Interactive Learning

Shenglan Liu, Xiang Liu, Yang Liu +4

Supervised learning methods are widely used in machine learning. However, the lack of labels in existing data limits the application of these technologies. Visual interactive learn…

cs.NI2013

A Localization Strategy Based on N-times Trilateral Centroid with Weight

Tie Qiu, Yu Zhou, Feng Xia +2

Localization based on received signal strength indication (RSSI) is a low cost and low complexity technology, and it is widely applied in distance-based localization of wireless se…