1 code implementation • 25 Feb 2025 • Yunfeng Li, Bo wang, Ye Li
To alleviate this problem, we propose LightFC-X, a family of lightweight convolutional RGB-X trackers that explores a unified convolutional architecture for lightweight multimodal tracking.
1 code implementation • 24 Jan 2025 • Xiaohao Xu, Tianyi Zhang, Shibo Zhao, Xiang Li, Sibo Wang, Yongqi Chen, Ye Li, Bhiksha Raj, Matthew Johnson-Roberson, Sebastian Scherer, Xiaonan Huang
We aim to redefine robust ego-motion estimation and photorealistic 3D reconstruction by addressing a critical limitation: the reliance on noise-free data in existing models.
no code implementations • 11 Dec 2024 • Yingxin Li, Ye Li, Yuan Meng, Xinzhu Ma, Zihan Geng, Shutao Xia, Zhi Wang
However, these approaches often produce biased distributions of important tokens due to the influence of accumulated attention scores or positional encoding.
no code implementations • 7 Dec 2024 • Xianliang Xu, Ye Li, Zhongyi Huang
Neural operators are aiming at approximating operators mapping between Banach spaces of functions, achieving much success in the field of scientific computing.
1 code implementation • 17 Oct 2024 • Ye Li, Wenzhao Zheng, Xiaonan Huang, Kurt Keutzer
We further propose a virtual configuration optimization method by minimizing the expected projection error between original cameras and virtual cameras.
1 code implementation • 8 Sep 2024 • Xinran Li, Xiaomao Fan, Qingyang Wu, Xiaojiang Peng, Ye Li
MaTAV is with the advantages of aligning unimodal features to ensure consistency across different modalities and handling long input sequences to better capture contextual multimodal information.
no code implementations • 7 Sep 2024 • Cheng Wan, Chenjie Xie, Longfei Liu, Dan Wu, Ye Li
Continuous blood pressure (BP) monitoring is essential for timely diagnosis and intervention in critical care settings.
no code implementations • 7 Sep 2024 • Ye Li, Ting Du, Yiwen Pang, Zhongyi Huang
Solving Singularly Perturbed Differential Equations (SPDEs) poses computational challenges arising from the rapid transitions in their solutions within thin regions.
no code implementations • 1 Sep 2024 • Ting Wang, Ye Li, Rongjun Cheng, Guojian Zou, Takao Dantsujic, Dong Ngoduy
Physics-informed deep learning (PIDL)-based models have recently garnered remarkable success in traffic state estimation (TSE).
no code implementations • 15 Aug 2024 • Zekai Guo, Lihui Chai, Shengjun Huang, Ye Li
The success of DL-FWI relies significantly on the quantity and diversity of the datasets.
1 code implementation • 11 Aug 2024 • Zhuoyan Liu, Bo wang, Ye Li
As for the detrimental effect of underwater color cast noise, recent underwater object detectors make network architecture or training complex, which also hinders their application and deployment on underwater vehicle platforms.
no code implementations • 1 Aug 2024 • Xianliang Xu, Ting Du, Wang Kong, Ye Li, Zhongyi Huang
In this work, we provide the convergence analysis of natural gradient descent (NGD) in training two-layer PINNs, demonstrating that the learning rate can be $\mathcal{O}(1)$, and at this rate, the convergence rate is independent of the Gram matrix.
1 code implementation • 6 Jul 2024 • Ye Li, Chen Tang, Yuan Meng, Jiajun Fan, Zenghao Chai, Xinzhu Ma, Zhi Wang, Wenwu Zhu
We introduce PRANCE, a Vision Transformer compression framework that jointly optimizes the activated channels and reduces tokens, based on the characteristics of inputs.
no code implementations • 3 Jul 2024 • Xianliang Xu, Ting Du, Wang Kong, Ye Li, Zhongyi Huang
In this paper, we provide convergence analysis for the IGD in training over-parameterized two-layer PINNs.
no code implementations • 3 Jul 2024 • Shuqiang Wang, Tong Zhou, Yanyan Shen, Ye Li, Guoheng Huang, Yong Hu
Additionally, a multi-scale Transformer denoising module is constructed to leverage multi-scale convolution blocks and cross-attention-based diffusion Transformer blocks for conditional guidance to generate subject-adaptive SR EEG.
no code implementations • 26 Jun 2024 • Zengding Liu, Chen Chen, Jiannong Cao, Minglei Pan, Jikui Liu, Nan Li, Fen Miao, Ye Li
This paper pioneers the exploration of LLMs for cuffless BP measurement, providing a potential solution to enhance the accuracy of cuffless BP measurement.
1 code implementation • 24 Jun 2024 • Xiaohao Xu, Tianyi Zhang, Sibo Wang, Xiang Li, Yongqi Chen, Ye Li, Bhiksha Raj, Matthew Johnson-Roberson, Xiaonan Huang
Embodied agents require robust navigation systems to operate in unstructured environments, making the robustness of Simultaneous Localization and Mapping (SLAM) models critical to embodied agent autonomy.
1 code implementation • 11 Jun 2024 • Yunfeng Li, Bo wang, Jiuran Sun, Xueyi Wu, Ye Li
The spatial cross-attention is used to overcome the problem of spatial misalignment of between RGB and sonar images.
no code implementations • 10 Jun 2024 • Jian Xu, Chaojie Ji, Yankai Cao, Ye Li, Ruxin Wang
Single domain generalization (Single-DG) intends to develop a generalizable model with only one single training domain to perform well on other unknown target domains.
1 code implementation • 28 May 2024 • Xiaohao Xu, Ye Li, Tianyi Zhang, Jinrong Yang, Matthew Johnson-Roberson, Xiaonan Huang
Constructing large-scale labeled datasets for multi-modal perception model training in autonomous driving presents significant challenges.
no code implementations • 23 May 2024 • Yuyan Zhou, Ye Li, Lei Feng, Sheng-Jun Huang
Recent studies showed that the generalization of neural networks is correlated with the sharpness of the loss landscape, and flat minima suggests a better generalization ability than sharp minima.
1 code implementation • 6 May 2024 • Yunfeng Li, Bo wang, Ye Li, Zhiwen Yu, Liang Wang
The former does not fully exploit the potential of using only RGB and TIR information of the template or search region for channel and spatial feature fusion, and the latter lacks direct interaction between the template and search area, which limits the model's ability to fully exploit the original semantic information of both modalities.
Ranked #10 on
Rgb-T Tracking
on RGBT210
1 code implementation • 25 Mar 2024 • Ye Li, Lingdong Kong, Hanjiang Hu, Xiaohao Xu, Xiaonan Huang
However, prevailing driving datasets predominantly utilize single-LiDAR systems and collect data devoid of adverse conditions, failing to capture the complexities of real-world environments accurately.
1 code implementation • 26 Feb 2024 • Shiwen Ni, Minghuan Tan, Yuelin Bai, Fuqiang Niu, Min Yang, BoWen Zhang, Ruifeng Xu, Xiaojun Chen, Chengming Li, Xiping Hu, Ye Li, Jianping Fan
In this paper, we contribute a new benchmark, the first Multilingual-oriented quiZ on Intellectual Property (MoZIP), for the evaluation of LLMs in the IP domain.
1 code implementation • 12 Feb 2024 • Xiaohao Xu, Tianyi Zhang, Sibo Wang, Xiang Li, Yongqi Chen, Ye Li, Bhiksha Raj, Matthew Johnson-Roberson, Xiaonan Huang
To this end, we propose a novel, customizable pipeline for noisy data synthesis, aimed at assessing the resilience of multi-modal SLAM models against various perturbations.
1 code implementation • 10 Jan 2024 • Ye Li
This paper presents Graph-of-Thought (GoT), a new model for workflow automation that enhances the flexibility and efficiency of Large Language Models (LLMs) in complex task execution.
no code implementations • 22 Dec 2023 • Siqi Chen, Bin Shan, Ye Li
Physics-informed neural networks (PINNs) have shown promising potential for solving partial differential equations (PDEs) using deep learning.
1 code implementation • 6 Dec 2023 • Zhuoyan Liu, Bo wang, Lizhi Wang, Chenyu Mao, Ye Li
Multimodal semantic segmentation is developing rapidly, but the modality of RGB-Polarization remains underexplored.
Ranked #1 on
Semantic Segmentation
on UPLight
no code implementations • 13 Nov 2023 • Ruiquan Ge, Xiangyang Hu, Rungen Huang, Gangyong Jia, Yaqi Wang, Renshu Gu, Changmiao Wang, Elazab Ahmed, Linyan Wang, Juan Ye, Ye Li
In TTMFN, we present a two-stream multimodal co-attention transformer module to take full advantage of the complex relationships between different modalities and the potential connections within the modalities.
no code implementations • 11 Oct 2023 • Ye Li, Chen Wang
In contrast, at the height of the global financial crisis, more than 2. 2% of market value is from dividends in the next year, implying a duration of 46 years.
1 code implementation • 9 Oct 2023 • Yunfeng Li, Bo wang, Xueyi Wu, Zhuoyan Liu, Ye Li
Although single object trackers have achieved advanced performance, their large-scale models hinder their application on limited resources platforms.
no code implementations • 9 Sep 2023 • Zhuoyan Liu, Bo wang, Ye Li, Jiaxian He, Yunfeng Li
In this paper, we propose a plug-and-play Underwater joint image enhancement Module (UnitModule) that provides the input image preferred by the detector.
1 code implementation • 4 Apr 2023 • Xiao He, Ye Li, Jian Tan, Bin Wu, Feifei Li
Extensive experiments on real-world benchmark datasets for downstream time series anomaly detection and forecasting tasks demonstrate that OneShotSTL is from 10 to over 1, 000 times faster than the state-of-the-art methods, while still providing comparable or even better accuracy.
1 code implementation • CVPR 2023 • Ping Chen, Xingpeng Zhang, Ye Li, Ju Tao, Bin Xiao, Bing Wang, Zongjie Jiang
Inspired by the transfer learning, we designed the Delta Age AdaIN (DAA) operation to obtain the feature difference with each age, which obtains the style map of each age through the learned values representing the mean and standard deviation.
no code implementations • 3 Mar 2023 • Ye Li, Song-Can Chen, Sheng-Jun Huang
Physics-informed neural networks (PINNs) have effectively been demonstrated in solving forward and inverse differential equation problems, but they are still trapped in training failures when the target functions to be approximated exhibit high-frequency or multi-scale features.
no code implementations • 28 Jan 2023 • Liming Wang, Hong Xie, Ye Li, Jian Tan, John C. S. Lui
Template mining is one of the foundational tasks to support log analysis, which supports the diagnosis and troubleshooting of large scale Web applications.
no code implementations • 9 Jan 2023 • Huanyu Bian, Zhilong Jia, Menghan Dou, Yuan Fang, Lei LI, Yiming Zhao, Hanchao Wang, Zhaohui Zhou, Wei Wang, Wenyu Zhu, Ye Li, Yang Yang, Weiming Zhang, Nenghai Yu, Zhaoyun Chen, Guoping Guo
Therefore, based on VQNet 1. 0, we further propose VQNet 2. 0, a new generation of unified classical and quantum machine learning framework that supports hybrid optimization.
2 code implementations • 4 Jan 2023 • Yunfeng Li, Bo wang, Ye Li, Zhuoyan Liu, Wei Huo, Yueming Li, Jian Cao
The UOHT training paradigm is designed to train the sample-imbalanced underwater tracker so that the tracker is exposed to a great number of underwater domain training samples and learns the feature expressions.
no code implementations • 21 Dec 2022 • Ye Li, Junyu Chen, Se-In Jang, Kuang Gong, Quanzheng Li
Inspired by the recent success of Transformers for Natural Language Processing and vision Transformer for Computer Vision, many researchers in the medical imaging community have flocked to Transformer-based networks for various main stream medical tasks such as classification, segmentation, and estimation.
no code implementations • 13 Dec 2022 • Changwei Gong, Changhong Jing, Ye Li, Xinan Liu, Zuxin Chen, Shuqiang Wang
And models of functional addiction circuits developed from functional imaging are an effective tool for discovering and verifying addiction circuits.
no code implementations • 8 Dec 2022 • Ye Li, Yiwen Pang, Bin Shan
Neural networks, especially the recent proposed neural operator models, are increasingly being used to find the solution operator of differential equations.
no code implementations • 7 Dec 2022 • Jiashu Lou, Leyi Cui, Ye Li
In this paper, we propose a bidirectional LSTM neural network based on an attention mechanism, which is based on two popular assets, gold and bitcoin.
1 code implementation • 30 Nov 2022 • Bin Shan, Ye Li, Shengjun Huang
Although physics-informed neural networks(PINNs) have progressed a lot in many real applications recently, there remains problems to be further studied, such as achieving more accurate results, taking less training time, and quantifying the uncertainty of the predicted results.
no code implementations • 15 Nov 2022 • Runji Lin, Ye Li, Xidong Feng, Zhaowei Zhang, Xian Hong Wu Fung, Haifeng Zhang, Jun Wang, Yali Du, Yaodong Yang
Firstly, we propose prompt tuning for offline RL, where a context vector sequence is concatenated with the input to guide the conditional policy generation.
1 code implementation • 7 Sep 2022 • Se-In Jang, Tinsu Pan, Ye Li, Pedram Heidari, Junyu Chen, Quanzheng Li, Kuang Gong
In this work, we proposed an efficient spatial and channel-wise encoder-decoder transformer, Spach Transformer, that can leverage spatial and channel information based on local and global MSAs.
no code implementations • 5 May 2022 • Zhi Qi, Hong Xie, Ye Li, Jian Tan, Feifei Li, John C. S. Lui
LPC-AD is motivated by the ever-increasing needs for fast and accurate MTS anomaly detection methods to support fast troubleshooting in cloud computing, micro-service systems, etc.
no code implementations • 15 Mar 2022 • Ye Li, Jianan Cui, Junyu Chen, Guodong Zeng, Scott Wollenweber, Floris Jansen, Se-In Jang, Kyungsang Kim, Kuang Gong, Quanzheng Li
Our hypothesis is that by explicitly providing the local relative noise level of the input image to a deep convolutional neural network (DCNN), the DCNN can outperform itself trained on image appearance only.
no code implementations • 27 Jan 2022 • Peng Wei, Kun Guo, Ye Li, Jue Wang, Wei Feng, Shi Jin, Ning Ge, Ying-Chang Liang
Mobile edge computing (MEC) is considered a novel paradigm for computation-intensive and delay-sensitive tasks in fifth generation (5G) networks and beyond.
1 code implementation • 19 Nov 2021 • Junyu Chen, Eric C. Frey, Yufan He, William P. Segars, Ye Li, Yong Du
Recently Vision Transformer architectures have been proposed to address the shortcomings of ConvNets and have produced state-of-the-art performances in many medical imaging applications.
Ranked #1 on
Medical Image Registration
on OASIS
1 code implementation • 17 Apr 2021 • Junyu Chen, Ye Li, Licia P. Luna, Hyun Woo Chung, Steven P. Rowe, Yong Du, Lilja B. Solnes, Eric C. Frey
The results demonstrated that the proposed method provides fast and robust lesion and bone segmentation for QBSPECT/CT.
1 code implementation • 13 Apr 2021 • Junyu Chen, Yufan He, Eric C. Frey, Ye Li, Yong Du
However, the performances of ConvNets are still limited by lacking the understanding of long-range spatial relations in an image.
Ranked #4 on
Medical Image Registration
on OASIS
no code implementations • 11 Dec 2020 • Ye Li, Kangning Yin, Jie Liang, Chunyu Wang, Guangqiang Yin
To solve these problems, we propose a Multi-task Joint Framework for real-time person search (MJF), which optimizes the person detection, feature extraction and identity comparison respectively.
no code implementations • 26 Oct 2020 • Guosheng Cui, Ruxin Wang, Dan Wu, Ye Li
In recent years, semi-supervised multi-view nonnegative matrix factorization (MVNMF) algorithms have achieved promising performances for multi-view clustering.
no code implementations • 1 Sep 2020 • Bram Ruijsink, Esther Puyol-Anton, Ye Li, Wenja Bai, Eric Kerfoot, Reza Razavi, Andrew P. King
SemiQCSeg can be an efficient approach for training segmentation networks for medical image data when labelled datasets are scarce.
5 code implementations • ICLR 2021 • Lee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang, Jialin Liu, Paul Bennett, Junaid Ahmed, Arnold Overwijk
In this paper, we identify that the main bottleneck is in the training mechanisms, where the negative instances used in training are not representative of the irrelevant documents in testing.
Ranked #7 on
Passage Retrieval
on Natural Questions
1 code implementation • 3 May 2020 • Ruxin Wang, Shuyuan Chen, Chaojie Ji, Jianping Fan, Ye Li
In this paper, we formulate a boundary-aware context neural network (BA-Net) for 2D medical image segmentation to capture richer context and preserve fine spatial information.
no code implementations • 17 Apr 2020 • Ruxin Wang, Shuyuan Chen, Chaojie Ji, Ye Li
In this paper, we formulate a cascaded context enhancement neural network for automatic skin lesion segmentation.
no code implementations • 24 Feb 2020 • Ye Li, Guangqiang Yin, Chunhui Liu, Xiaoyu Yang, Zhiguo Wang
Triplet loss processes batch construction in a complicated and fussy way and converges slowly.
no code implementations • 14 Feb 2020 • Xing Yong Kek, Cheng Siong Chin, Ye Li
Although works have been done in using HPSS as input representation for CNN model in ASC task, this paper further investigate the possibility on leveraging the separated harmonic component and percussive component by curating 2 CNNs which tries to understand harmonic audio and percussive audio in their natural form, one specialized in extracting deep features in time biased domain and another specialized in extracting deep features in frequency biased domain, respectively.
1 code implementation • 6 Dec 2019 • Junyu Chen, Ye Li, Yong Du, Eric C. Frey
In this work, we present a novel image registration method for creating highly anatomically detailed anthropomorphic phantoms from a single digital phantom.
1 code implementation • 24 Oct 2019 • Peter H. Charlton, Jorge Mariscal Harana, Samuel Vennin, Ye Li, Phil Chowienczyk, and Jordi Alastruey
The database, containing PWs from 4, 374 virtual subjects, was verified by comparing the simulated PWs and derived indexes with corresponding in vivo data.
no code implementations • 30 Apr 2019 • Jinqiang Bai, Zhaoxiang Liu, Yimin Lin, Ye Li, Shiguo Lian, Dijun Liu
Based on the detected ground, the optimal walkable direction is computed and the user is then informed via converted beep sound.