no code implementations • 12 Apr 2024 • Yujie Li, Yanbin Wang, Haitao Xu, Bin Liu, Jianguo Sun, Zhenhao Guo, Wenrui Ma
Unlike data-driven classifiers, TMDC, guided by Bayesian principles, utilizes the conditional likelihood from diffusion models to determine the class probabilities of input images, thereby insulating against the influences of data shift and the limitations of adversarial training.
1 code implementation • 18 Feb 2024 • Yujie Li, Yanbin Wang, Haitao Xu, Zhenhao Guo, Zheng Cao, Lun Zhang
To address this gap, this paper introduces URLBERT, the first pre-trained representation learning model applied to a variety of URL classification or detection tasks.
no code implementations • 22 Dec 2023 • Yujie Li, Xin Yang, Hao Wang, Xiangkun Wang, Tianrui Li
This paper studies the problem of continual learning in an open-world scenario, referred to as Open-world Continual Learning (OwCL).
no code implementations • 19 Dec 2023 • Yujie Li, Zezhi Shao, Yongjun Xu, Qiang Qiu, Zhaogang Cao, Fei Wang
Complex spatial dependencies in transportation networks make traffic prediction extremely challenging.
no code implementations • 27 Nov 2022 • Bowen Cai, Yujie Li, Yuqin Liang, Rongfei Jia, Binqiang Zhao, Mingming Gong, Huan Fu
However, a drawback is that the synthesized views through Neural Fields Rendering (NFR) cannot reflect the simulated lighting details on R3DMs in PBR pipelines, especially when object interactions in the 3D scene creation cause local shadows.
no code implementations • 8 Aug 2022 • Longzhao Huang, Yujie Li, Xu Wang, Haoyu Wang, Ahmed Bouridane, Ahmad Chaddad
We propose a differential residual model (DRNet) combined with a new loss function to make use of the difference information of two eye images.
no code implementations • 5 Jun 2022 • Ahmad Chaddad, Jiali Li, Qizong Lu, Yujie Li, Idowu Paul Okuwobi, Camel Tanougast, Christian Desrosiers, Tamim Niazi
With AI, new radiomic models using the deep learning techniques will be also described.
no code implementations • 11 Oct 2021 • Sikai Chen, Jiqian Dong, Runjia Du, Yujie Li, Samuel Labi
Deep learning (DL) based computer vision (CV) models are generally considered as black boxes due to poor interpretability.
no code implementations • IEEE 2021 • Yujie Li, Zhang Song, Sunkyoung Kang, Sungtae Jung, Wenpei Kang
We propose a Semi-supervised Auto-encoder Graph Network (SAGN) for the challenging DR diagnosis to relax this constraint.
no code implementations • 11 Oct 2021 • Shuya Zong, Sikai Chen, Majed Alinizzi, Yujie Li, Samuel Labi
Assessing collision risk is a critical challenge to effective traffic safety management.
no code implementations • 19 Dec 2020 • Xin Jin, Hongyu Zhang, XiaoDong Li, Haoyang Yu, Beisheng Liu, Shujiang Xie, Amit Kumar Singh, Yujie Li
To make this algorithm easy to use, we also designed and implemented an efficient general blind computing library based on CMP-SWHE.
1 code implementation • 12 Oct 2020 • Jiqian Dong, Sikai Chen, Paul Young Joun Ha, Yujie Li, Samuel Labi
Connected Autonomous Vehicle (CAV) Network can be defined as a collection of CAVs operating at different locations on a multilane corridor, which provides a platform to facilitate the dissemination of operational information as well as control instructions.
no code implementations • 12 Oct 2020 • Paul Young Joun Ha, Sikai Chen, Jiqian Dong, Runjia Du, Yujie Li, Samuel Labi
In addressing this objective, we duly recognize that one of the main challenges of RL-based CAV controllers is the variety and complexity of inputs that exist in the real world, such as the information provided to the CAV by other connected entities and sensed information.
no code implementations • 30 Sep 2020 • Jiqian Dong, Sikai Chen, Yujie Li, Runjia Du, Aaron Steinfeld, Samuel Labi
From a general perspective, its implementation can provide guidance to connectivity equipment manufacturers and CAV operators, regarding the default CR settings for CAVs or the recommended CR setting in a given traffic environment.
no code implementations • 9 Jan 2019 • Huimin Lu, Dong Wang, Yujie Li, Jianru Li, Xin Li, Hyoungseop Kim, Seiichi Serikawa, Iztok Humar
The Cognitive Ocean Network (CONet) will become the mainstream of future ocean science and engineering developments.
no code implementations • 4 Jun 2017 • Huimin Lu, Yujie Li, Min Chen, Hyoungseop Kim, Seiichi Serikawa
Specifically, we plan to develop an intelligent learning model called Brain Intelligence (BI) that generates new ideas about events without having experienced them by using artificial life with an imagine function.
no code implementations • 13 Feb 2017 • Huimin Lu, Yujie Li, Yudong Zhang, Min Chen, Seiichi Serikawa, Hyoungseop Kim
This paper aims to review the state-of-the-art techniques in underwater image processing by highlighting the contributions and challenges presented in over 40 papers.
no code implementations • 5 Oct 2015 • Huimin Lu, Yujie Li, Shota Nakashima, Seiichi Serikawa
Image contrast enhancement for outdoor vision is important for smart car auxiliary transport systems.