Explanipedia

Enhancing YOLOv7 for underwater image object detection: a research study Open

Tao Yao, Xianhua Duan, Ke Lü, D. Ni · 2025

Enhancing Black-Litterman Portfolio via Hybrid Forecasting Model Combining Multivariate Decomposition and Noise Reduction Open

Ziye Yang, Ke Lü, Yan Wang, Jerome Yen · 2025

Modern portfolio construction demands robust methods for integrating data-driven insights into asset allocation. The Black-Litterman model offers a powerful Bayesian approach to adjust equilibrium returns using investor views to form a pos…

UPFP-SG: A New Benchmark for Unilateral Peripheral Facial Paralysis Severity Grading Open

Wei Liang Gan, Ruiqi Zhao, Ke Lü, Yuxuan Li, Guohong Hu , et al. · 2025

Unilateral facial palsy, a common type of facial paralysis, profoundly impacts individuals' daily functionality and quality of life. The current clinical diagnosis of facial paralysis primarily relies on the subjective judgment of doctors,…

Multi-Scale Feature Extraction for Liver Tumor Segmentation: From Module Design to Model Construction Open

Jinlin Ma, Kai Zhang, Ziping Ma, Ke Lü · 2025

Identification of Polarization Curve Parameters for a 5-Mw Alkaline Electrolyzer Based on a Hybrid Adaptive Differential Evolution–Levenberg–Marquardt Algorithm Open

Yuan Zhu, C. N. Zhang, Wenda Ma, Ke Lü · 2025

The Optimal Crew Allocation Scheme of Intercity Railway EMU: A Case Study of Guangzhou-Qingyuan Intercity Open

Huibing Cheng, Ke Lü, Wenjie Liu, Qi Liu, Yi Liu , et al. · 2025

Multimodal PEAR Chain-of-Thought Reasoning for Multimodal Sentiment Analysis Open

Yan Li, Xiangyuan Lan, Haifeng Chen, Ke Lü, Dongmei Jiang · 2024

Multimodal sentiment analysis aims to predict sentiments from multimodal signals such as audio, video, and text. Existing methods often rely on Pre-trained Language Models (PLMs) to extract semantic information from textual data, lacking a…

SciQAG: A Framework for Auto-Generated Science Question Answering Dataset with Fine-grained Evaluation Open

Yuwei Wan, Aswathy Ajith, Yixuan Liu, Ke Lü, Clara Grazian , et al. · 2024

We introduce SciQAG, a novel framework for automatically generating high-quality science question-answer pairs from a large corpus of scientific literature based on large language models (LLMs). SciQAG consists of a QA generator and a QA e…

Semi-supervised Object Detection for Remote Sensing Images via Pseudo Labeling and Consistency Learning Open

Yuqiu Li, Jian Xue, Ke Lü · 2023

Object detection for remote sensing images (RSI) has made significant progress in recent years. However, existing supervised methods typically require a large amount of labeled data, whose acquisition, and particularly that of RSI, can be …

G-Rep: Gaussian Representation for Arbitrary-Oriented Object Detection Open

Liping Hou, Ke Lü, Xue Yang, Yuqiu Li, Jian Xue · 2023

Typical representations for arbitrary-oriented object detection tasks include the oriented bounding box (OBB), the quadrilateral bounding box (QBB), and the point set (PointSet). Each representation encounters problems that correspond to i…

Multi-Scale Vision Transformer for Defect Object Detection Open

Liangshan Lou, Ke Lü, Jian Xue · 2023

Defect object detection for printed circuit boards (PCBs) is one of the most important tasks in the field of industrial inspections. For this task, deep learning-based object detection algorithms are generally used. Regardless of whether o…

Shape-Adaptive Selection and Measurement for Oriented Object Detection Open

Liping Hou, Ke Lü, Jian Xue, Yuqiu Li · 2022

The development of detection methods for oriented object detection remains a challenging task. A considerable obstacle is the wide variation in the shape (e.g., aspect ratio) of objects. Sample selection in general object detection has bee…

TransZero: Attribute-Guided Transformer for Zero-Shot Learning Open

Shiming Chen, Ziming Hong, Yang Liu, Guo-Sen Xie, Baigui Sun , et al. · 2022

Zero-shot learning (ZSL) aims to recognize novel classes by transferring semantic knowledge from seen classes to unseen ones. Semantic knowledge is learned from attribute descriptions shared between different classes, which are strong prio…

Exploring Visual Context for Weakly Supervised Person Search Open

Yichao Yan, Jinpeng Li, Shengcai Liao, Jie Qin, Bingbing Ni , et al. · 2022

Person search has recently emerged as a challenging task that jointly addresses pedestrian detection and person re-identification. Existing approaches follow a fully supervised setting where both bounding box and identity annotations are a…

FEAFA+: An Extended Well-Annotated Dataset for Facial Expression Analysis and 3D Facial Animation Open

Wei Gan, Jian Xue, Ke Lü, Yanfu Yan, Pengcheng Gao , et al. · 2021

Nearly all existing Facial Action Coding System-based datasets that include facial action unit (AU) intensity information annotate the intensity values hierarchically using A--E levels. However, facial expressions change continuously and s…

Dual Optical Path Based Adaptive Compressive Sensing Imaging System Open

Hongliang Li, Ke Lü, Jian Xue, Feng Dai, Yongdong Zhang · 2021

Compressive Sensing (CS) has proved to be an effective theory in the field of image acquisition. However, in order to distinguish the difference between the measurement matrices, the CS imaging system needs to have a higher signal sampling…

A Weibull‐distribution‐based hybrid total variation method for speckle reduction in ultrasound images Open

Wenchao Cui, Liangzhi Shao, Guoqiang Gong, Ke Lü, Shuifa Sun , et al. · 2021

Speckle reduction is still an intractable task in ultrasound imaging field. Ultrasound speckle is usually described as multiplicative noise with its statistics following a Rayleigh or Gaussian distribution. To employ these two distribution…

Clinical Outcomes and Safety of Different Treatment Modes for Local Recurrence of Rectal Cancer Open

Zhongzhu Tang, Luying Liu, Dong Liu, Lie Wu, Ke Lü , et al. · 2020

Surgery combined with chemoradiotherapy was a beneficial treatment mode for managing patients with locally recurrent, nonmetastatic rectal cancer. It was associated with better local disease control, no increase in toxicity, and prolonged …

Energy minimisation‐based multi‐class multi‐instance geometric primitives extraction from 3D point clouds Open

Liang Wang, Biying Yan, Fuqing Duan, Ke Lü · 2020

Geometric primitives contained in three‐dimensional (3D) point clouds can provide the meaningful and concise abstraction of 3D data, which plays a vital role in improving 3D vision‐based intelligent applications. However, how to efficientl…

Characters as Graphs: Recognizing Online Handwritten Chinese Characters via Spatial Graph Convolutional Network Open

Ji Gan, Weiqiang Wang, Ke Lü · 2020

Chinese is one of the most widely used languages in the world, yet online handwritten Chinese character recognition (OLHCCR) remains challenging. To recognize Chinese characters, one popular choice is to adopt the 2D convolutional neural n…

Adjuvant chemotherapy for locally advanced rectal cancer in elderly patients after neoadjuvant chemoradiotherapy and surgery Open

Quanquan Sun, Tongxin Liu, Peng Liu, Ke Lü, Na Zhang , et al. · 2020

The treatment strategy for elderly patients with locally advanced rectal cancer (LARC) remains controversial. The aim of this study was to identify the significance of adjuvant chemotherapy (AC) for elderly patients with LARC after neoadju…

Deep Hashing Based on VAE‐GAN for Efficient Similarity Retrieval Open

Guoqing Jin, Yongdong Zhang, Ke Lü · 2019

Inspired by the recent advances in generative networks, we propose a VAE-GAN based hashing framework for fast image retrieval. The method combines a Variational autoencoder (VAE) with a Generative adversarial network (GAN) to generate cont…

The Auto-focus Method for Scanning Acoustic Microscopy by Sparse Representation Open

Hao Liang, Ke Lü, Xiaokun Liu, Jian Xue · 2019

As an efficient non-destructive checking technique, scanning acoustic microscopy has been rapidly developed and widely used in nondestructive detection for composites, chip manufacturing, bio-pharmaceuticals and so on. Scanning acoustic mi…

Editorial: Deep learning for medical image analysis Open

Ke Lü, Fei Wang, Ling Shao, Weisheng Li · 2019

FEAFA: A Well-Annotated Dataset for Facial Expression Analysis and 3D Facial Animation Open

Yanfu Yan, Ke Lü, Jian Xue, Pengcheng Gao, Jiayi Lyu · 2019

Facial expression analysis based on machine learning requires large number of well-annotated data to reflect different changes in facial motion. Publicly available datasets truly help to accelerate research in this area by providing a benc…

Serum lncRNA-UFC1 as a potential biomarker for diagnosis and prognosis of pancreatic cancer. Open

Peng Liu, Quanquan Sun, Tongxin Liu, Ke Lü, Na Zhang , et al. · 2019

Early diagnosis is important to improve the prognosis of pancreatic cancer (PC). Identifying potential biomarkers is essential for the monitoring and treatment of PC. The long noncoding RNA (lncRNA) UFC1 has been identified as an oncogenic…

Action Recognition With Coarse-to-Fine Deep Feature Integration and Asynchronous Fusion Open

Weiyao Lin, Chongyang Zhang, Ke Lü, Bin Sheng, Jianxin Wu , et al. · 2018

Action recognition is an important yet challenging task in computer vision. In this paper, we propose a novel deep-based framework for action recognition, which improves the recognition accuracy by: 1) deriving more precise features for re…

Learning Correspondence Structures for Person Re-Identification Open

Weiyao Lin, Yang Shen, Junchi Yan, Mingliang Xu, Jianxin Wu , et al. · 2017

This paper addresses the problem of handling spatial misalignments due to camera-view changes or human-pose variations in person re-identification. We first introduce a boosting-based approach to learn a correspondence structure, which ind…

Evolution of Metal Surface Topography during Fatigue Open

Darong Zhu, Lu Xu, Fangbin Wang, Tao Liu, Ke Lü · 2017

Changes in surface topography reflect the state of fatigue damage. In this paper, a new method to characterize metal surface topography during fatigue has been proposed. Firstly, we acquired surface topography images based on machine visio…

A pilot study of using smart clothes for physicalworkload assessment Open

Liyun Yang, Ke Lü, Farhad Abtahi, Kaj Lindecrantz, Fernando Seoane , et al. · 2017

Ke Lü YOU? Author Swipe