1 code implementation • Findings (ACL) 2022 • Wei Xiang, Bang Wang, Lu Dai, Yijun Mo
Prior studies use one attention mechanism to improve contextual semantic representation learning for implicit discourse relation recognition (IDRR).
1 code implementation • COLING 2022 • Wei Xiang, Zhenglin Wang, Lu Dai, Bang Wang
As the first trial of using this new paradigm for IDRR, this paper develops a Connective-cloze Prompt (ConnPrompt) to transform the relation prediction task as a connective-cloze task.
no code implementations • 11 Jan 2025 • Zhen Hong, Bowen Wang, Haoran Duan, Yawen Huang, Xiong Li, Zhenyu Wen, Xiang Wu, Wei Xiang, Yefeng Zheng
In this paper, we introduce SP-SLAM, a novel neural RGB-D SLAM system that performs tracking and mapping in real-time.
Simultaneous Localization and Mapping
Surface Reconstruction
no code implementations • 20 Dec 2024 • Phu Lai, Wei Xiang, William Damario Lukito, Khoa Tran Phan, Peng Cheng, Chang Liu, Guoqiang Mao
Cell-free massive multiple-input multiple-output (CFmMIMO) coordinates a great number of distributed access points (APs) with central processing units (CPUs), effectively reducing interference and ensuring uniform service quality for user equipment (UEs).
no code implementations • 26 Nov 2024 • Juefei He, Yuexing Peng, Wei Li, Junchuan Yu, Daqing Ge, Wei Xiang
Relic landslide, formed over a long period, possess the potential for reactivation, making them a hazardous geological phenomenon.
1 code implementation • 26 Sep 2024 • Chuanhong Zhan, Wei Xiang, Chao Liang, Bang Wang
Existing script event prediction task forcasts the subsequent event based on an event script chain.
no code implementations • 16 Aug 2024 • Shuaijun Ma, Peng Wei, Sa Xiao, Jianquan Wang, Wanbin Tang, Wei Xiang
Simulation results demonstrate that the proposed blind detector exhibits a significant enhancement in symbol detection performance compared to its traditional counterparts.
1 code implementation • 31 May 2024 • Cheng Liu, Wei Xiang, Bang Wang
Event Causality Identification (ECI) aims to detect whether there exists a causal relation between two events in a document.
1 code implementation • 29 May 2024 • Songtao Liu, Bang Wang, Wei Xiang, Han Xu, Minghua Xu
BICo enables the concepts to flow across levels of the schema tree and enriches concept representations with multi-granularity semantics.
1 code implementation • 17 May 2024 • Chao Liang, Wei Xiang, Bang Wang
Motivated from such considerations, this paper proposes an In-Context Contrastive Learning (ICCL) model that utilizes contrastive learning to enhance the effectiveness of both positive and negative demonstrations.
no code implementations • 8 May 2024 • Bing Zhu, Zixin He, Weiyi Xiong, Guanhua Ding, Jianan Liu, Tao Huang, Wei Chen, Wei Xiang
However, mmWave radar relies on the collection of reflected signals from the target, and the radar signals containing information is difficult to be fully applied.
no code implementations • 26 Apr 2024 • Renqiang Luo, Tao Tang, Feng Xia, Jiaying Liu, Chengpei Xu, Leo Yu Zhang, Wei Xiang, Chengqi Zhang
Recent advancements in machine learning and deep learning have brought algorithmic fairness into sharp focus, illuminating concerns over discriminatory decision making that negatively impacts certain individuals or groups.
1 code implementation • 27 Feb 2024 • Wei Xiang, Haoteng Yin, He Wang, Xiaogang Jin
Pedestrian trajectory prediction is the key technology in many applications for providing insights into human behavior and anticipating human future motions.
no code implementations • 22 Jan 2024 • Jordan Shipard, Arnold Wiliem, Kien Nguyen Thanh, Wei Xiang, Clinton Fookes
To address this issue, we propose Zoom-shot, a novel method for transferring the zero-shot capabilities of CLIP to any pre-trained vision encoder.
no code implementations • 11 Jan 2024 • Yu Zheng, Huan Yee Koh, Ming Jin, Lianhua Chi, Haishuai Wang, Khoa T. Phan, Yi-Ping Phoebe Chen, Shirui Pan, Wei Xiang
However, real-world time series data is usually not well-structured, posting significant challenges to existing approaches: (1) The existence of missing values in multivariate time series data along variable and time dimensions hinders the effective modeling of interwoven spatial and temporal dependencies, resulting in important patterns being overlooked during model training; (2) Anomaly scoring with irregularly-sampled observations is less explored, making it difficult to use existing detectors for multivariate series without fully-observed values.
no code implementations • 4 Dec 2023 • Stephanie Baker, Wei Xiang
In this work, we explore state-of-the-art literature on RAI and XAI technologies.
1 code implementation • 6 Oct 2023 • Qingguo Liu, Pan Gao, Kang Han, Ningzhong Liu, Wei Xiang
In particular, we integrate both CNN and Transformer components into the SR network, where we first use the CNN modulated by the degradation information to extract local features, and then employ the degradation-aware Transformer to extract global semantic features.
1 code implementation • 14 Sep 2023 • Bang Wang, Zhenglin Wang, Wei Xiang, Yijun Mo
Implicit discourse relation recognition (IDRR) aims at recognizing the discourse relation between two text segments without an explicit connective.
no code implementations • 2 Aug 2023 • Yiming Zhou, Yuexing Peng, Junchuan Yu, Daqing Ge, Wei Xiang
To extract accurate semantic features, a hyper-pixel-wise contrastive learning augmented segmentation network (HPCL-Net) is proposed, which augments the local salient feature extraction from boundaries of landslides through HPCL and fuses heterogeneous information in the semantic space from high-resolution remote sensing images and digital elevation model data.
no code implementations • 23 Jul 2023 • Qingren Yao, Yuan Zhou, Chang Tang, Wei Xiang
For hyperspectral image change detection (HSI-CD), one key challenge is to reduce band redundancy, as only a few bands are crucial for change detection while other bands may be adverse to it.
no code implementations • 19 Jul 2023 • Yulan Gao, Ziqiang Ye, Yue Xiao, Wei Xiang
These methods are designed to minimize the cost incurred by the worst-case participant and ensure the long-term fairness of FL in hierarchical Internet of Things (HieIoT) networks.
no code implementations • 19 Jul 2023 • Wei Xiang, Chuanhong Zhan, Bang Wang
We use the probabilities of predicted events to evaluate the assumption rationality for the final event causality decision.
1 code implementation • 17 Jul 2023 • Yu Zheng, Huan Yee Koh, Ming Jin, Lianhua Chi, Khoa T. Phan, Shirui Pan, Yi-Ping Phoebe Chen, Wei Xiang
To overcome these limitations, we propose a novel method, correlation-aware spatial-temporal graph learning (termed CST-GL), for time series anomaly detection.
no code implementations • 15 Jun 2023 • Lu Yu, Wei Xiang, Kang Han
To address this challenge, we propose the Edit-DiffNeRF framework, which is composed of a frozen diffusion model, a proposed delta module to edit the latent semantic space of the diffusion model, and a NeRF.
1 code implementation • 18 May 2023 • Wei Xiang, Chao Liang, Bang Wang
Although an auxiliary task is not used to directly output final prediction, we argue that during the joint training some of its learned features can be useful to boost the main task.
no code implementations • 15 Mar 2023 • Pan Gao, Xinlang Chen, Rong Quan, Wei Xiang
We employ a recurrent neural network among adjacent prediction stages to model their correlations, and exploit a discriminator at the end of each stage to supervise the output saliency map.
1 code implementation • CVPR 2023 • Lu Yu, Wei Xiang
Recent studies have proposed to prune transformers in an unexplainable manner, which overlook the relationship between internal units of the model and the target class, thereby leading to inferior performance.
1 code implementation • CVPR 2023 • Kang Han, Wei Xiang
Instead of encoding view directions to model view-dependent effects, we further propose to encode the rendering equation in the feature space by employing the anisotropic spherical Gaussian mixture predicted from the proposed multiscale representation.
no code implementations • 24 Feb 2023 • Zili Lu, Yuexing Peng, Wei Li, Junchuan Yu, Daqing Ge, Wei Xiang
An object-level contrastive learning (OCL) strategy is employed in the object classification sub-network featuring a siamese network to realize the global features extraction, and a sub-object-level contrastive learning (SOCL) paradigm is designed in the semantic segmentation sub-network to efficiently extract salient features from boundaries of landslides.
1 code implementation • 7 Feb 2023 • Jordan Shipard, Arnold Wiliem, Kien Nguyen Thanh, Wei Xiang, Clinton Fookes
In this work, we investigate the problem of Model-Agnostic Zero-Shot Classification (MA-ZSC), which refers to training non-specific classification architectures (downstream models) to classify real images without using any real images during training.
1 code implementation • 28 Oct 2022 • Lu Dai, Bang Wang, Wei Xiang, Yijun Mo
Recently, prompt-tuning has attracted growing interests in event argument extraction (EAE).
no code implementations • 27 Jul 2022 • Shixing Yu, Yiyang Ma, Wenhan Yang, Wei Xiang, Jiaying Liu
Extensive qualitative and quantitative evaluations, as well as ablation studies, demonstrate that, via introducing meta-learning in our framework in such a well-designed way, our method not only achieves superior performance to state-of-the-art frame interpolation approaches but also owns an extended capacity to support the interpolation at an arbitrary time-step.
no code implementations • 12 Jul 2022 • Lu Yu, Wei Xiang, Juan Fang, Yi-Ping Phoebe Chen, Lianhua Chi
To close these crucial gaps, we propose a novel vision transformer dubbed the eXplainable Vision Transformer (eX-ViT), an intrinsically interpretable transformer model that is able to jointly discover robust interpretable features and perform the prediction.
1 code implementation • 30 Jun 2022 • Bo Peng, Wei Xiang, Yue Jiang, Wei Wang, Jing Dong, Zhenan Sun, Zhen Lei, Siwei Lyu
There is a two-party game between DeepFake creators and defenders.
no code implementations • 10 Jun 2022 • Han Meng, Yuexing Peng, Wei Xiang, Xu Pang, Wenbo Wang
In this paper, a two-stream semantic feature fusion model, termed Multi-faceted Graph Attention Network (MF-GAT), is proposed to greatly improve the accuracy in the low SNR region of the heterogeneous radar network.
no code implementations • 13 May 2022 • Jianan Liu, Hao Li, Tao Huang, Euijoon Ahn, Kang Han, Adeel Razi, Wei Xiang, Jinman Kim, David Dagan Feng
However, the difference in degradation representations between synthetic and authentic LR images suppresses the quality of SR images reconstructed from authentic LR images.
no code implementations • 15 Apr 2022 • Han Meng, Yuexing Peng, Wenbo Wang, Peng Cheng, Yonghui Li, Wei Xiang
This paper proposes a knowledge-and-data-driven graph neural network-based collaboration learning model for reliable aircraft recognition in a heterogeneous radar network.
no code implementations • 13 Mar 2022 • Weiyi Xiong, Jianan Liu, Yuxuan Xia, Tao Huang, Bing Zhu, Wei Xiang
Deep learning-based instance segmentation enables real-time object identification from the radar detection points.
no code implementations • 8 Mar 2022 • Moyu Liu, Zihuai Lin, Pei Xiao, Wei Xiang
This system overall accuracy for the heart and respiration rate estimation can reach 99. 109% and 98. 581%, respectively.
no code implementations • 6 Mar 2022 • Wei Xiang, Bang Wang
As sentences are normally consist of multiple text segments, correct understanding of the theme of a discourse should take into consideration of the relations in between text segments.
no code implementations • 18 Jan 2022 • Ying Wang, Yuexing Peng, Xinran Liu, Wei Li, George C. Alexandropoulos, Junchuan Yu, Daqing Ge, Wei Xiang
Extracting roads from high-resolution remote sensing images (HRSIs) is vital in a wide variety of applications, such as autonomous driving, path planning, and road navigation.
no code implementations • 27 Aug 2021 • Fanxin Xu, Xiangkui Li, Hang Yang, Yali Wang, Wei Xiang
In this work, an object detector based on YOLOF has been proposed to detect blood cell objects such as red blood cells, white blood cells and platelets.
no code implementations • 20 May 2021 • Li Wang, Wei Xiang, Ruhui Xue, Kaida Zou, Laili Zhu
In order to solve the above problems, Experiments show that our model has a certain improvement in accuracy compared with the current popular detection models on the COCO dataset, the designed attention mechanism module can capture contextual information well, improve detection accuracy, and use sepc network to help balance abstract and detailed information, and reduce the problem of semantic gap in the feature pyramid network.
1 code implementation • 20 May 2021 • Bo Cheng, Ruhui Xue, Hang Yang, Laili Zhu, Wei Xiang
We propose a deep learning model that can help radiologists and clinicians use chest X-rays to diagnose COVID-19 cases and show the diagnostic features of pneumonia.
1 code implementation • 20 Feb 2021 • Sofiane Kharbech, Eric Pierre Simon, Akram Belazi, Wei Xiang
The paper proposes a new technique that substantially improves blind digital modulation identification (DMI) algorithms that are based on higher-order statistics (HOS).
no code implementations • 21 Jan 2021 • Tianming Feng, Shuo Shi, Shushi Gu, Wei Xiang, Xuemai Gu
Using stochastic geometry, we derive an integral expression for the successful transmission probability (STP) in NC-JT scheme, and present an upper bound and a tight approximation for the STP of the C-JT scheme.
Information Theory Information Theory
1 code implementation • 23 Apr 2020 • Corey Lammie, Wei Xiang, Bernabé Linares-Barranco, Mostafa Rahimi Azghadi
Memristive devices have shown great promise to facilitate the acceleration and improve the power efficiency of Deep Learning (DL) systems.
Emerging Technologies
no code implementations • 22 Feb 2020 • Yuan Zhou, Tao Cao, Wei Xiang
As a promising technology in the Internet of Underwater Things, underwater sensor networks have drawn a widespread attention from both academia and industry.
no code implementations • 7 Feb 2020 • Lei Lei, Yue Tan, Glenn Dahlenburg, Wei Xiang, Kan Zheng
Microgrids (MGs) are small, local power grids that can operate independently from the larger utility grid.
no code implementations • 8 Jan 2020 • Corey Lammie, Wei Xiang, Mostafa Rahimi Azghadi
While hardware implementations of inference routines for Binarized Neural Networks (BNNs) are plentiful, current realizations of efficient BNN hardware training accelerators, suitable for Internet of Things (IoT) edge devices, leave much to be desired.
no code implementations • 19 Jun 2019 • Lei Lei, Huijuan Xu, Xiong Xiong, Kan Zheng, Wei Xiang, Xianbin Wang
By leveraging the concept of mobile edge computing (MEC), massive amount of data generated by a large number of Internet of Things (IoT) devices could be offloaded to MEC server at the edge of wireless network for further computational intensive processing.
1 code implementation • 15 May 2019 • Corey Lammie, Wei Xiang, Mostafa Rahimi Azghadi
Consequently, the performance and complexity of Artificial Neural Networks (ANNs) is burgeoning.
no code implementations • 28 Dec 2018 • Peng Wei, Yue Xiao, Wei Xiang
A novel basis signal optimization method is proposed for reducing the interference in the N-continuous orthogonal frequency division multiplexing (NC-OFDM) system.
no code implementations • 27 Jul 2017 • Wei Xiang, Dong-Qing Zhang, Heather Yu, Vassilis Athitsos
SSD is one of the state-of-the-art object detection algorithms, and it combines high detection accuracy with real-time speed.