Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleAugust 2024
DeforT: Deformable transformer for visual tracking
AbstractMost trackers formulate visual tracking as common classification and regression (i.e., bounding box regression) tasks. Correlation features that are computed through depth-wise convolution or channel-wise multiplication operations are input into ...
- research-articleJune 2024
Immersive Computing: What to Expect in a Decade?
IEEE Internet Computing (IEEECS_INTERNET), Volume 28, Issue 3May-June 2024, Pages 46–54https://doi.org/10.1109/MIC.2024.3388808Computing technology is advancing at an unprecedented speed, reshaping both our daily lives and the global landscape. In this article, we delve into the profound impact of immersive technology on society, focusing on how it can represent and interact with ...
- research-articleJuly 2024
Identification of hub genes in calcific aortic valve disease
- Qian-Cheng Lai,
- Jie Zheng,
- Jian Mou,
- Chun-Yan Cui,
- Qing-Chen Wu,
- Syed M Musa Rizvi,
- Ying Zhang,
- Tian -Mei Li,
- Ying-Bo Ren,
- Qing Liu,
- Qun Li,
- Cheng Zhang
Computers in Biology and Medicine (CBIM), Volume 172, Issue CApr 2024https://doi.org/10.1016/j.compbiomed.2024.108214AbstractCalcific aortic valve disease (CAVD) is a heart valve disorder characterized primarily by calcification of the aortic valve, resulting in stiffness and dysfunction of the valve. CAVD is prevalent among aging populations and is linked to factors ...
Highlights- CAVD is a central link to many chronic diseases.
- Integration of four microarray datasets using Robust Rank Aggregation (RRA) method and Support Vector Machine (SVM) method to identify DEGs involved in CAVD.
- Performing functional ...
- research-articleMay 2024
Dynamic context modeling based lightweight high-resolution network for dense prediction
Engineering Applications of Artificial Intelligence (EAAI), Volume 129, Issue CMar 2024https://doi.org/10.1016/j.engappai.2023.107642AbstractRecent research shows that high-resolution networks can provide representative multi-scale features for vision tasks. However, high-resolution-based architectures are weak in capturing spatial long-range information, and they are computationally ...
Highlights- We present a novel efficient architecture for dense prediction, called Dynamic-HRNet.
- Dynamic-HRNet consists of two key components, including a DSC and an ACM.
- Two lightweight blocks are designed as the basic building units of ...
- research-articleApril 2024
Distributed Quantum Machine Learning: Federated and Model-Parallel Approaches
IEEE Internet Computing (IEEECS_INTERNET), Volume 28, Issue 2March-April 2024, Pages 65–72https://doi.org/10.1109/MIC.2024.3361288In this article, we explore two types of distributed quantum machine learning (DQML) methodologies: quantum federated learning and quantum model-parallel learning. We discuss the challenges encountered in DQML, propose potential solutions, and highlight ...
-
- research-articleMarch 2024
BAN-ima: A Box Adaptive Network With Iterative Mixed Attention for Visual Tracking
IEEE Transactions on Consumer Electronics (ITOCE), Volume 70, Issue 1Feb. 2024, Pages 2365–2377https://doi.org/10.1109/TCE.2024.3374239Recent anchor-free trackers that leverage the remarkably expressive capacity of the fully convolutional network have drawn considerable attention within the field of tracking. However, the independence of feature extraction and feature fusion in existing ...
- research-articleMarch 2024
Dynamic scene deblurring via receptive field attention generative adversarial network
Computers and Graphics (CGRS), Volume 116, Issue CNov 2023, Pages 354–362https://doi.org/10.1016/j.cag.2023.09.004AbstractDynamic scene deblurring has important practical significance, and some deep learning deblurring methods have outstanding performance in this domain. However, simple network structures cannot effectively extract feature information to remove ...
Graphical abstractDisplay Omitted
Highlights- The receptive field attention block extracts and learns deep features.
- The dual-scale discriminator to evaluate the output at different scales.
- Highly non-uniform motion is calculated by non-uniform loss function.
- Multiple loss ...
- research-articleFebruary 2024
Prediction of influent wastewater quality based on wavelet transform and residual LSTM
Applied Soft Computing (APSC), Volume 148, Issue CNov 2023https://doi.org/10.1016/j.asoc.2023.110858AbstractAccurate prediction on influent wastewater quality is of great importance to energy saving and chemical dosage reduction of wastewater treatment plants (WWTPs). However, the existing methods ignore the data noise caused by water sensors working ...
Highlights- This paper proposes a novel approach called wt-ResLSTM for the prediction on influent wastewater quality.
- The wt-ResLSTM approach considers both noise removal and transient uncertainty in recent fluctuations of wastewater quality.
- ...
- research-articleOctober 2023
Lite-FENet: Lightweight multi-scale feature enrichment network for few-shot segmentation
Knowledge-Based Systems (KNBS), Volume 278, Issue COct 2023https://doi.org/10.1016/j.knosys.2023.110887AbstractCurrent methods for few-shot segmentation focus on extracting information from support and query targets, however, most of these methods not only suffer from high model complexity but also fail to capture long-range interactions between query ...
Highlights- A lightweight multi-scale feature enrichment network named Lite-FENet for FSS is proposed.
- Lite-FENet enhances multi-scale feature interactions under low computational cost.
- A lightweight and efficient Spatial Interaction Module (...
- research-articleOctober 2023
SurfaceNet: Fault-Tolerant Quantum Networks With Surface Codes
IEEE Network: The Magazine of Global Internetworking (IEEENETW), Volume 38, Issue 1Jan. 2024, Pages 155–162https://doi.org/10.1109/MNET.2023.3326291Quantum networks serve as the means to transmit information, encoded in quantum bits or qubits, between quantum processors that are physically separated. Given the instability of qubits, the design of such networks is challenging, necessitating a careful ...
- research-articleOctober 2023
MUD-PQFed: Towards Malicious User Detection on model corruption in Privacy-preserving Quantized Federated learning
Computers and Security (CSEC), Volume 133, Issue COct 2023https://doi.org/10.1016/j.cose.2023.103406AbstractThe use of cryptographic privacy-preserving techniques in Federated Learning (FL) inadvertently induces a security dilemma because tampered local model parameters are encrypted and thus prevented from auditing. This work firstly ...
- research-articleSeptember 2023
Collocated Clothing Synthesis with GANs Aided by Textual Information: A Multi-Modal Framework
ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), Volume 20, Issue 1Article No.: 26, Pages 1–25https://doi.org/10.1145/3614097Synthesizing realistic images of fashion items which are compatible with given clothing images, as well as conditioning on multiple modalities, brings novel and exciting applications together with enormous economic potential. In this work, we propose a ...
- research-articleSeptember 2023
Privacy-Preserving Data Integrity Verification for Secure Mobile Edge Storage
IEEE Transactions on Mobile Computing (ITMV), Volume 22, Issue 9Sept. 2023, Pages 5463–5478https://doi.org/10.1109/TMC.2022.3174867Mobile edge computing (MEC) is proposed as an extension of cloud computing in the scenarios where the end devices desire better services in terms of response time. Because the edges are usually owned by individuals or small organizations with limited ...
- research-articleAugust 2023
Scalable Differentially Private Model Publishing Via Private Iterative Sample Selection
IEEE Transactions on Dependable and Secure Computing (TDSC), Volume 21, Issue 4July-Aug. 2024, Pages 2494–2506https://doi.org/10.1109/TDSC.2023.3309089Model publishing and deployment are essential for artificial intelligence applications. A major challenge in model publishing is efficiently distributing the models in a scalable way without violating the privacy of sensitive data. With the wide adoption ...
- research-articleJuly 2023
Miss-gradient boosting regression tree: a novel approach to imputing water treatment data
Applied Intelligence (KLU-APIN), Volume 53, Issue 19Oct 2023, Pages 22917–22937https://doi.org/10.1007/s10489-023-04828-6AbstractComplete data on wastewater quality are essential for managing and monitoring wastewater treatment processes. Most management and monitoring methods involve the use of voluminous training data for imputation, but the problem is that the sensors ...
- research-articleJuly 2023
User satisfaction-based energy-saving computation offloading in fog computing networks
The Journal of Supercomputing (JSCO), Volume 80, Issue 1Jan 2024, Pages 620–641https://doi.org/10.1007/s11227-023-05484-wAbstractIn order to enhance resource allocation in fog computing networks and establish an energy-aware service, this paper proposes a user satisfaction-based energy-saving computation offloading mechanism that jointly optimizes service decision, task ...
- research-articleMay 2023
Travel Time Distribution Estimation by Learning Representations Over Temporal Attributed Graphs
- Wanyi Zhou,
- Xiaolin Xiao,
- Yue-Jiao Gong,
- Jia Chen,
- Jun Fang,
- Naiqiang Tan,
- Nan Ma,
- Qun Li,
- Chai Hua,
- Sang-Woon Jeon,
- Jun Zhang
IEEE Transactions on Intelligent Transportation Systems (ITS-TRANSACTIONS), Volume 24, Issue 5May 2023, Pages 5069–5081https://doi.org/10.1109/TITS.2023.3247884Travel time estimation is a crucial task in practical transportation applications, while providing the reliability of estimation is important in many working scenarios. Most existing studies do not consider the dynamics of traffic status for different ...
- research-articleMay 2023
Understanding Location Privacy of the Point-of-Interest Aggregate Data via Practical Attacks and Defenses
IEEE Transactions on Dependable and Secure Computing (TDSC), Volume 20, Issue 3May-June 2023, Pages 2433–2449https://doi.org/10.1109/TDSC.2022.3184279Location-based services have significantly affected mobile users’ everyday life, and location privacy has become essential. Some applications (e.g., location-based recommendation, mobility analytics) do not need the raw location data, and the ...
- research-articleApril 2023
Image motion deblurring via attention generative adversarial network
Computers and Graphics (CGRS), Volume 111, Issue CApr 2023, Pages 122–132https://doi.org/10.1016/j.cag.2023.01.007AbstractImage motion deblurring methods based on deep learning have achieved promising performance. However, these methods ignore the global dependence of structural features, which leads to the problem of incomplete structure or the introduction of ...
Graphical abstractDisplay Omitted
Highlights- The residual module and the cascaded criss-cross attention module are combined.
- The dual-scale discriminator is adopted to provide a larger receptive field.
- A multi-component loss function constraint strategy is proposed.
- research-articleJanuary 2023
HRNeXt: High-Resolution Context Network for Crowd Pose Estimation
IEEE Transactions on Multimedia (TOM), Volume 252023, Pages 1521–1528https://doi.org/10.1109/TMM.2023.3248144Occlusion handling in crowded scenes is an intractable challenge for human pose estimation. To address this problem, we propose two novel feed-forward network structures named Global Feed-Forward Network (GFFN) and Dynamic Feed-Forward Network (DFFN), ...