48 citations · 210 across the 26 of their papers we have counts for
26 papers
TMac: Temporal Multi-Modal Graph Learning for Acoustic Event Classification
Meng Liu, Ke Liang, Dayu Hu +6
Audiovisual data is everywhere in this digital age, which raises higher requirements for the deep learning models developed on them. To well handle the information of the multi-mod…
ICAFusion: Iterative Cross-Attention Guided Feature Fusion for Multispectral Object Detection
Jifeng Shen, Yifei Chen, Yue Liu +3
Effective feature fusion of multispectral images plays a crucial role in multi-spectral object detection. Previous studies have demonstrated the effectiveness of feature fusion usi…
Decentralised Governance-Driven Architecture for Designing Foundation Model based Systems: Exploring the Role of Blockchain in Responsible AI
Yue Liu, Qinghua Lu, Liming Zhu +1
Foundation models including large language models (LLMs) are increasingly attracting interest worldwide for their distinguished capabilities and potential to perform a wide variety…
Holographic Complexity of Rotating Quantum Black Holes
Bin Chen, Yuefeng Liu, Boyang Yu
We study holographic complexity for the rotating quantum BTZ black holes (quBTZ), the BTZ black holes with corrections from bulk quantum fields. Using double holography, the combin…
Distributed Trust Through the Lens of Software Architecture
Sin Kit Lo, Yue Liu, Guangsheng Yu +3
Distributed trust is a nebulous concept that has evolved from different perspectives in recent years. While one can attribute its current prominence to blockchain and cryptocurrenc…
Analytical reconstructions of full-scan multiple source-translation computed tomography under large field of views
Zhisheng Wang, Yue Liu, Shunli Wang +3
This paper is to investigate the high-quality analytical reconstructions of multiple source-translation computed tomography (mSTCT) under an extended field of view (FOV). Under the…
NLUT: Neural-based 3D Lookup Tables for Video Photorealistic Style Transfer
Yaosen Chen, Han Yang, Yuexin Yang +4
Video photorealistic style transfer is desired to generate videos with a similar photorealistic style to the style image while maintaining temporal consistency. However, existing m…
Poisson Conjugate Prior for PHD Filtering based Track-Before-Detect Strategies in Radar Systems
Haiyi Mao, Cong Peng, Yue Liu +3
A variety of filters with track-before-detect (TBD) strategies have been developed and applied to low signal-to-noise ratio (SNR) scenarios, including the probability hypothesis de…
Uncorrelated Amplitude and Frequency Variations of the Harmonics in SX Phoenicis Star XX Cygni
Jia-Shu Niu, Yue Liu, Hui-Fang Xue
Harmonics are quite common in pulsating stars, and they are always considered to mimic the behaviors of their independent parent pulsation modes and not taken as the key informatio…
Swin MAE: Masked Autoencoders for Small Datasets
Zi'an Xu, Yin Dai, Fayu Liu +5
The development of deep learning models in medical image analysis is majorly limited by the lack of large-sized and well-annotated datasets. Unsupervised learning does not require…
Decentralized Gradient Tracking with Local Steps
Yue Liu, Tao Lin, Anastasia Koloskova +1
Gradient tracking (GT) is an algorithm designed for solving decentralized optimization problems over a network (such as training a machine learning model). A key feature of GT is a…
Reform and Practice of Computer Application Technology Major Construction and Development in Higher Vocational Colleges in China -- Taking Jiangxi Vocational College of Applied Technology as An Example
Yufei Xie, Yue Liu, Fan Zou
This study takes the development path of computer application technology specialty construction in Higher Vocational Colleges under the background of high-level higher vocational s…
A Survey of Deep Graph Clustering: Taxonomy, Challenge, Application, and Open Resource
Yue Liu, Jun Xia, Sihang Zhou +7
Graph clustering, which aims to divide nodes in the graph into several distinct clusters, is a fundamental yet challenging task. Benefiting from the powerful representation capabil…
High Dynamic Range Image Quality Assessment Based on Frequency Disparity
Yue Liu, Zhangkai Ni, Shiqi Wang +2
In this paper, a novel and effective image quality assessment (IQA) algorithm based on frequency disparity for high dynamic range (HDR) images is proposed, termed as local-global f…
UPST-NeRF: Universal Photorealistic Style Transfer of Neural Radiance Fields for 3D Scene
Yaosen Chen, Qi Yuan, Zhiqiang Li +5
3D scenes photorealistic stylization aims to generate photorealistic images from arbitrary novel views according to a given style image while ensuring consistency when rendering fr…
PatchDropout: Economizing Vision Transformers Using Patch Dropout
Yue Liu, Christos Matsoukas, Fredrik Strand +2
Vision transformers have demonstrated the potential to outperform CNNs in a variety of vision tasks. But the computational and memory requirements of these models prohibit their us…
Reflected Entropy in AdS/WCFT
Bin Chen, Yuefeng Liu, Boyang Yu
Reflected entropy is a newly proposed notion in quantum information. It has important implications in holography. In this work, we study the reflected entropy in the framework of t…
A Pattern Language for Blockchain Governance
Yue Liu, Qinghua Lu, Guangsheng Yu +3
Blockchain technology has been used to build next-generation applications taking advantage of its decentralised nature. Nevertheless, there are some serious concerns about the trus…
Deep Graph Clustering via Dual Correlation Reduction
Yue Liu, Wenxuan Tu, Sihang Zhou +4
Deep graph clustering, which aims to reveal the underlying graph structure and divide the nodes into different groups, has attracted intensive attention in recent years. However, w…
Out-of-Distribution Generalization Analysis via Influence Function
Haotian Ye, Chuanlong Xie, Yue Liu +1
The mismatch between training and target data is one major challenge for current machine learning systems. When training data is collected from multiple domains and the target doma…
Blockchain-based Federated Learning for Device Failure Detection in Industrial IoT
Weishan Zhang, Qinghua Lu, Qiuyu Yu +6
Device failure detection is one of most essential problems in industrial internet of things (IIoT). However, in conventional IIoT device failure detection, client devices need to u…
Video Moment Retrieval via Natural Language Queries
Xinli Yu, Mohsen Malmir, Cynthia He +2
In this paper, we propose a novel method for video moment retrieval (VMR) that achieves state of the arts (SOTA) performance on R@1 metrics and surpassing the SOTA on the high IoU…
A Blockchain-based Platform Architecture for Multimedia Data Management
Yue Liu, Qinghua Lu, Chunsheng Zhu +1
Massive amounts of multimedia data (i.e., text, audio, video, graphics and animation) are being generated everyday. Conventionally, multimedia data are managed by the platforms mai…
Real-time Human Activity Recognition Using Conditionally Parametrized Convolutions on Mobile and Wearable Devices
Xin Cheng, Lei Zhang, Yin Tang +3
Recently, deep learning has represented an important research trend in human activity recognition (HAR). In particular, deep convolutional neural networks (CNNs) have achieved stat…