Yang Ji

Previewing Does Matter: Class-incremental Learning via Task-aware Expandable Representation

Linjie Li, Zhenyu Wu, Huiyu Xiao, Jiayi Liu et autres

cn (code pays fourni par la source)

MoTE: Mixture of task-specific experts for pre-trained model-based Class-incremental learning

Linjie Li, Zhenyu Wu, Yang Ji

cn, cl (code pays fourni par la source)

MoTE: Mixture of Task-specific Experts for Pre-Trained ModelBased Class-incremental Learning

Linjie Li, Zhenyu Wu, Yang Ji

Class-incremental learning (CIL) requires deep learning models to continuously acquire new knowledge from streaming data while preserving previously learned information. Recently, CIL based on pre-trained models (PTMs) has achieved remarkable success. However, prompt-based approaches suffer from prompt overwriting, while adapter-based methods face …

TaE: Task-Aware Expandable Representation for Long Tail Class Incremental Learning

Linjie Li, Zhenyu Wu, Jiaming Liu, Yang Ji

cn (code pays fourni par la source)

Belt and Road Initiative: Boosting Financial Service Efficiency in the Real Economy？

Yang Ji, J.‐M. FU, Jia Li

cn (code pays fourni par la source)

Structural connectivity estimates are accurate: the outcome of diffusion-simulated connectivity (DiSCo) challenge

Gabriel Girard, Jonathan Rafael‐Patiño, Raphaël Truffet, Dogu Baran Aydogan et autres

The estimation of structural connectivity from DW-MRI is a challenging task, in part due to false-positive connections. Building on previous efforts, the MICCAI-CDMRI Diffusion-Simulated Connectivity (DiSCo) challenge was organized with the aim of evaluating connectivity methods using large-scale synthetic datasets obtained from …

Tractography passes the test: Results from the diffusion-simulated connectivity (disco) challenge

Gabriel Girard, Jonathan Rafael‐Patiño, Raphaël Truffet, Dogu Baran Aydogan et autres

Estimating structural connectivity from diffusion-weighted magnetic resonance imaging is a challenging task, partly due to the presence of false-positive connections and the misestimation of connection weights. Building on previous efforts, the MICCAI-CDMRI Diffusion-Simulated Connectivity (DiSCo) challenge was carried out to evaluate state-of-the-art …

ch, fr, fi, us, it, ca, pl, es, cn, mx, au (code pays fourni par la source)

Underwater Image Enhancement Based on Color Correction and Detail Enhancement

Zeju Wu, Yang Ji, Lijun Song, Jianyuan Sun

To solve the problems of underwater image color deviation, low contrast, and blurred details, an algorithm based on color correction and detail enhancement is proposed. First, the improved nonlocal means denoising algorithm is used to denoise the underwater image. The combination of …

cn, gb (code pays fourni par la source)

A Survival Analysis based Volatility and Sparsity Modeling Network for Student Dropout Prediction v1

Feng Pan, Bingyao Huang, Chunhong Zhang, Xinning Zhu et autres

Student Dropout Prediction (SDP) is of pivotal significance in mitigating withdrawals in Massive Open Online Courses. Research in these areas are usually carried out using deep learning to detect complex nonlinear patterns in students' learning sequences. However, the volatility and sparsity of …

cn (code pays fourni par la source)

Usm-Unet:U-Net and Unsharp Masking Based Underwater Image Restoration Algorithm

Zeju Wu, Yang Ji, Lijun Song, Jianyuan Sun et autres

cn, gb (code pays fourni par la source)

Several special cases of a square problem

Yang Ji

Here is a square problem: in a unit square, is there a point with four rational distances to the vertices? A probability argument suggests a negative answer. This paper proves several special cases of the square problem: if the point sits on …

Separation of Discipline and Education — Exploration of a New Model of Strict Discipline and Training for Criminals

Yang Ji, Zhao Zhengwei

三仓出版社主要从事中文国际开源期刊的出版与发行，期刊领域涵盖工程技术、数学与物理、人文社会、信息科学、经济与管理、医药卫生、农业、地球环境等学科，借助互联网思维及现代信息技术，立足国内高校及研究机构的科研需求，力图推动中国学术界知识的交流与传播，可期刊发表、发表论文、快速发表，见刊快。三仓出版社欢迎广大科研学者加入我们，参与审稿，合作办刊，投稿荐稿，与中文期刊一同成长壮大。如果您对期刊有任何的意见或者建议，请联系service@sciscanpub.com.