no code implementations • 17 May 2016 • Li Yu, Cyril Joly, Guillaume Bresson, Fabien Moutarde
This paper presents a metric global localization in the urban environment only with a monocular camera and the Google Street View database.
no code implementations • 11 Oct 2016 • Yifan Hou, Pan Zhou, Ting Wang, Li Yu, Yuchong Hu, Dapeng Wu
In this respect, the key challenge is how to realize personalized course recommendation as well as to reduce the computing and storage costs for the tremendous course data.
no code implementations • 23 Sep 2018 • Chenying Wang, Li Yu, Shengwei Wang
High efficiency video coding (HEVC) suffers high encoding computational complexity, partly attributed to the rate-distortion optimization quad-tree search in CU partition decision.
no code implementations • MIDL 2019 • Zhuo Kuang, Xianbo Deng, Li Yu, Hang Zhang, Xian lin, Hui Ma
Guiding by the morphological features of the skull, a skeleton-based region proposal method is proposed to make candidate boxes more concentrated in key regions and reduce invalid boxes.
no code implementations • ECCV 2020 • Yao Zhou, Guowei Wan, Shenhua Hou, Li Yu, Gang Wang, Xiaofei Rui, Shiyu Song
We present a visual localization framework based on novel deep attention aware features for autonomous driving that achieves centimeter level localization accuracy.
no code implementations • 16 Jul 2020 • Li Yu, Hisham Abuella, Md Zobaer Islam, John F. O'Hara, Christopher Crick, Sabit Ekin
In this paper, we demonstrate the ability to recognize hand gestures in a non-contact, wireless fashion using only incoherent light signals reflected from a human subject.
no code implementations • 6 Aug 2020 • Vikas Kumar, Shivansh Rao, Li Yu
Facial expression recognition from videos in the wild is a challenging task due to the lack of abundant labelled training data.
Ranked #7 on Facial Expression Recognition (FER) on Acted Facial Expressions In The Wild (AFEW) (using extra training data)
Facial Expression Recognition Facial Expression Recognition (FER)
no code implementations • 20 Nov 2020 • Li Yu
This generalizes the Hochster's formula for the moment-angle manifold over a simple convex polytope.
Algebraic Topology Geometric Topology 57S12 (Primary) 57N65, 57S17, 57S25 (Secondary)
no code implementations • CVPR 2021 • ShiYang Yan, Li Yu, Yuan Xie
We propose a novel attention scheme which projects the image and text embedding into a common space and optimises the attention weights directly towards the evaluation metrics.
no code implementations • 13 Oct 2021 • Zhongyao Hu, Bo Chen, Wen-An Zhang, Li Yu
For this criterion, it is proved that the fusion results are not affected by the fusion structure, and thus the fusion performance can be guaranteed.
no code implementations • 27 Oct 2021 • Zhongyao Hu, Bo Chen, Yuchen Zhang, Li Yu
When considering linear dynamic systems, a conservative estimation error covariance with adjustable parameters is constructed by matrix inequality, and then an optimal filter gain is derived by minimizing its trace.
no code implementations • 28 Dec 2021 • Xuanying Chen, Zhining Liu, Li Yu, Sen Li, Lihong Gu, Xiaodong Zeng, Yize Tan, Jinjie Gu
This bias deteriorates the performance of the response model and misleads the linear programming process, dramatically degrading the performance of the resulting allocation policy.
no code implementations • 17 Mar 2022 • Li Yu, Kareem Metwaly, James Z. Wang, Vishal Monga
Detecting and evaluating surface coating defects is important for marine vessel maintenance.
no code implementations • 1 Jun 2022 • Yuchen Zhang, Bo Chen, Li Yu, Daniel W. C. Ho
By merging these subsystem-level stability conditions and the optimization-based estimator gain design, the distributed, stable and optimal estimators are proposed.
1 code implementation • 28 Jun 2022 • Nannan Wu, Li Yu, Xin Yang, Kwang-Ting Cheng, Zengqiang Yan
In this paper, we present a privacy-preserving FL method named FedIIC to combat class imbalance from two perspectives: feature learning and classifier learning.
2 code implementations • 29 Jun 2022 • Xian lin, Li Yu, Kwang-Ting Cheng, Zengqiang Yan
Specifically, to fully explore the benefits of transformers in long-range dependency establishment, a cross-scale global transformer (CGT) module is introduced to jointly utilize multiple small-scale feature maps for richer global features with lower computational complexity.
1 code implementation • 29 Jun 2022 • Xian lin, Li Yu, Kwang-Ting Cheng, Zengqiang Yan
To our best knowledge, this is the first work on transformer pruning for medical image analysis tasks.
no code implementations • 11 Jul 2022 • Zhaowei Chang, Jianhua Zhang, Pan Tang, Lei Tian, Li Yu, Guangyi Liu, Liang Xia
In this letter, the reflection coefficient of the THz channel is researched based on extensive measurement campaigns.
no code implementations • 3 Aug 2022 • Rusheng Wang, Bo Chen, Zhongyao Hu, Li Yu
This paper studies the event-triggered distributed fusion estimation problems for a class of nonlinear networked multisensor fusion systems without noise statistical characteristics.
no code implementations • 17 Sep 2022 • Yutong Sun, Jianhua Zhang, Li Yu, Zhen Zhang, Ping Zhang
Inspired by task-oriented semantic communication and machine learning (ML) powered environment-channel mapping methods, this work aims to provide a new view of the environment from the semantic level, which defines the propagation environment semantics (PES) as a limited set of propagation environment semantic symbols (PESS) for diverse application tasks.
no code implementations • 25 Oct 2022 • Li Yu, Wenshuai Chang, Shiyu Wu, Moncef Gabbouj
In this work, we propose a transformer-based compressed video quality enhancement (TVQE) method, consisting of Swin-AutoEncoder based Spatio-Temporal feature Fusion (SSTF) module and Channel-wise Attention based Quality Enhancement (CAQE) module.
no code implementations • 30 Dec 2022 • Bo Chen, Pindi Weng, Daniel W. C. Ho, Li Yu
This paper is concerned with the problem of secure multi-sensors fusion estimation for cyber-physical systems, where sensor measurements may be tampered with by false data injection (FDI) attacks.
no code implementations • 14 Jan 2023 • Md Zobaer Islam, Li Yu, Hisham Abuella, John F. O'Hara, Christopher Crick, Sabit Ekin
In this study, we present a wireless (non-contact) gesture recognition method using only incoherent light wave signals reflected from a human subject.
no code implementations • 19 Jan 2023 • Zheming Wang, Raphaël M. Jungers, Mihály Petreczky, Bo Chen, Li Yu
In this paper, we propose an algorithm for deciding stability of switched linear systems under arbitrary switching based purely on observed output data.
no code implementations • 6 Feb 2023 • Wangzhuo Yang, Bo Chen, Yijun Shen, Jiong Liu, Li Yu
To overcome these challenges, a multi-layer multi-fusion strategy framework is proposed in this paper, i. e., the server adopts the network layer parameters of each client upload model as the basic unit of fusion for information-sharing calculation.
no code implementations • 17 Apr 2023 • Zhongyao Hu, Bo Chen, Rusheng Wang, Li Yu
A posterior-based SET mechanism is proposed, which determines whether to transmit data by the effect of the measurement on the posterior estimate.
no code implementations • 7 May 2023 • Zhengqin Li, Li Yu, Mikhail Okunev, Manmohan Chandraker, Zhao Dong
For training, we significantly enhance the OpenRooms public dataset of photorealistic synthetic indoor scenes with around 360K HDR environment maps of much higher resolution and 38K video sequences, rendered with GPU-based path tracing.
2 code implementations • 9 May 2023 • Nannan Wu, Li Yu, Xuefeng Jiang, Kwang-Ting Cheng, Zengqiang Yan
Federated noisy label learning (FNLL) is emerging as a promising tool for privacy-preserving multi-source decentralized learning.
1 code implementation • IEEE Signal Processing Letters 2023 • Li Yu, Junyang Li, Farhad Pakdaman, Miaogen Ling, Moncef Gabbouj
No-Reference Image Quality Assessment aims to evaluate the perceptual quality of an image, according to human perception.
no code implementations • 3 Jun 2023 • Zibing Shen, Jianhua Zhang, Li Yu, Yuxiang Zhang, Zhen Zhang, Xidong Hu
A common and accurate dataset is essential for the research of AI communication.
no code implementations • 14 Jun 2023 • Tong Li, Li Yu, Yibo Ma, Tong Duan, Wenzhen Huang, Yan Zhou, Depeng Jin, Yong Li, Tao Jiang
We show that the decline in carbon efficiency leads to a carbon efficiency trap, estimated to cause additional carbon emissions of 23. 82 +- 1. 07 megatons in China.
no code implementations • 6 Sep 2023 • Tianchi Cai, Jiyan Jiang, Wenpeng Zhang, Shiji Zhou, Xierui Song, Li Yu, Lihong Gu, Xiaodong Zeng, Jinjie Gu, Guannan Zhang
We further show that this method is guaranteed to converge to the optimal policy, which cannot be achieved by previous value-based reinforcement learning methods for marketing budget allocation.
1 code implementation • 9 Sep 2023 • Xian lin, Zengqiang Yan, Xianbo Deng, Chuansheng Zheng, Li Yu
Following CSA, 2D convolution is utilized for feature refinement through CFFN.
1 code implementation • 13 Sep 2023 • Xian lin, Yangyang Xiang, Li Zhang, Xin Yang, Zengqiang Yan, Li Yu
Segment anything model (SAM), an eminent universal image segmentation model, has recently gathered considerable attention within the domain of medical image segmentation.
no code implementations • 8 Oct 2023 • Ziqiao Shang, Li Yu
Recently how to introduce large amounts of unlabeled facial images in the wild into supervised Facial Action Unit (AU) detection frameworks has become a challenging problem.
no code implementations • 14 Dec 2023 • Qibo Chen, Weizhong Jin, Shuchang Li, Mengdi Liu, Li Yu, Jian Jiang, Xiaozheng Wang
Text prompts are crucial for generalizing pre-trained open-set object detection models to new categories.
1 code implementation • 20 Dec 2023 • Nannan Wu, Zhaobin Sun, Zengqiang Yan, Li Yu
Specifically, noise estimation at each client is accomplished through the Gaussian mixture model and then incorporated into model aggregation in a layer-wise manner to up-weight high-quality clients.
no code implementations • 5 Feb 2024 • Li Yu, Yanjun Gao, Farhad Pakdaman, Moncef Gabbouj
In response to these challenges, we propose a panoramic image inpainting framework that consists of a Face Generator, a Cube Generator, a side branch, and two discriminators.
no code implementations • 8 Feb 2024 • Yuxin Xie, Li Yu, Farhad Pakdaman, Moncef Gabbouj
Noisy images are a challenge to image compression algorithms due to the inherent difficulty of compressing noise.
no code implementations • 19 Mar 2024 • Heng Wang, Jianhua Zhang, Gaofeng Nie, Li Yu, Zhiqiang Yuan, Tongjie Li, Jialin Wang, Guangyi Liu
Digital twin channel (DTC) is the real-time mapping of a wireless channel from the physical world to the digital world, which is expected to provide significant performance enhancements for the sixth-generation (6G) air-interface design.
1 code implementation • 20 Mar 2024 • Xian lin, Yangyang Xiang, Zhehao Wang, Kwang-Ting Cheng, Zengqiang Yan, Li Yu
Specifically, based on SAM, SAMCT is further equipped with a U-shaped CNN image encoder, a cross-branch interaction module, and a task-indicator prompt encoder.