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-articleJuly 2024
Multi-object behavior recognition based on object detection for dense crowds
Expert Systems with Applications: An International Journal (EXWA), Volume 248, Issue CAug 2024https://doi.org/10.1016/j.eswa.2024.123397AbstractIn recent years, research on multi-object behavior recognition methods based on pose estimation has made progress. However, in dense scenes, multi-object behavior recognition faces problems such as heavy occlusion, many small-scale objects, and ...
Highlights- The parallel branch structure for classification and location is proposed.
- The feature fusion mechanism improves the detectability of small objects.
- The dynamic weights generated by the object number optimize feature learning.
- research-articleJuly 2024
Deep learning model for human-intuitive shoeprint reconstruction
- Muhammad Hassan,
- Yan Wang,
- Di Wang,
- Wei Pang,
- Daixi Li,
- You Zhou,
- Dong Xu,
- Sami ur-Rahman,
- Amin ur Rahman,
- Ahmed Ameen Fateh,
- Peiwu Qin
Expert Systems with Applications: An International Journal (EXWA), Volume 249, Issue PCSep 2024https://doi.org/10.1016/j.eswa.2024.123704AbstractShoeprint reconstruction is essential in forensic science, but it is also challenging due to various inconsistencies in the patterns, textures, sizes, abrasions, etc. of shoeprints. The computational reconstruction of sharper and more complete ...
Highlights- An end-to-end deep learning model focuses on shoeprint reconstruction for forensics.
- Reconstruction of existing patterns together with the generation of missing regions.
- Missing regions reconstruction is specifically designed based ...
- research-articleJune 2024
Decomposition-based Synthesis for Applying Divide-and-Conquer-like Algorithmic Paradigms
ACM Transactions on Programming Languages and Systems (TOPLAS), Volume 46, Issue 2Article No.: 8, Pages 1–59https://doi.org/10.1145/3648440Algorithmic paradigms such as divide-and-conquer (D&C) are proposed to guide developers in designing efficient algorithms, but it can still be difficult to apply algorithmic paradigms to practical tasks. To ease the usage of paradigms, many research ...
- short-paperJune 2024
WiP: Towards Light Adaptation of Large Language Models For Personal Hardware
EdgeFM '24: Proceedings of the Workshop on Edge and Mobile Foundation ModelsJune 2024, Pages 30–32https://doi.org/10.1145/3662006.3662065The large language models (LLMs) that everyone is using are not deployed locally. Users need to send relatively private and important data to LLM when using it. Handing over private and important data to LLM will cause people to worry, especially now ...
- research-articleMay 2024
Engaging the Elderly in Exercise with Agents: A Gamified Stationary Bike System for Sarcopenia Management
AAMAS '24: Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent SystemsMay 2024, Pages 2818–2820This paper introduces a portable, gamified exercise system with an embedded agent, specifically designed to aid the elderly in lower-body workouts using stationary bikes. The system integrates a custom-made Internet of Things (IoT) sensing unit, a ...
-
- research-articleJuly 2024
Layer-wise surface quality improvement in laser powder bed fusion through surface anomaly detection and control
Computers and Industrial Engineering (CINE), Volume 191, Issue CMay 2024https://doi.org/10.1016/j.cie.2024.110098AbstractThe inferior inner surface in the laser powder bed fusion process (LPBF) deteriorated mechanical performance of the final product and even has the potential to lead to process failure. This study proposed an online monitoring system with layer-...
Graphical abstractDisplay Omitted
Highlights- Proposed layer-wise image-based online monitoring for laser powder bed fusion.
- Introduced a deep learning-based S d metric to evaluate the inner surface quality.
- Implemented an intelligent proportional controller for layer-wise ...
- research-articleJuly 2024
E3WD: A three-way decision model based on ensemble learning
Information Sciences: an International Journal (ISCI), Volume 667, Issue CMay 2024https://doi.org/10.1016/j.ins.2024.120487AbstractThree-way decision model is an effective way to deal with complex decision problems. However, since the three-way decision models now proposed are all based on a single decision criterion, the decision results typically reflect only one ...
Highlights- A new three-way decision model based on ensemble thinking is put forward.
- The core and candidate sets for a particular set are given based on set operations.
- The HCS, MCS and LCS are constructed by using K-means algorithm.
- A ...
- research-articleApril 2024
Newtonian Program Analysis of Probabilistic Programs
Proceedings of the ACM on Programming Languages (PACMPL), Volume 8, Issue OOPSLA1Article No.: 105, Pages 305–333https://doi.org/10.1145/3649822Due to their quantitative nature, probabilistic programs pose non-trivial challenges for designing compositional and efficient program analyses. Many analyses for probabilistic programs rely on iterative approximation. This article presents an ...
- research-articleApril 2024
PAC learning halfspaces in non-interactive local differential privacy model with public unlabeled data
Journal of Computer and System Sciences (JCSS), Volume 141, Issue CMay 2024https://doi.org/10.1016/j.jcss.2023.103496AbstractIn this paper, we study the problem of PAC learning halfspaces in the non-interactive local differential privacy model (NLDP). To breach the barrier of exponential sample complexity, previous results studied a relaxed setting where the server has ...
Privacy Amplification via Shuffling: Unified, Simplified, and Tightened
Proceedings of the VLDB Endowment (PVLDB), Volume 17, Issue 8Pages 1870–1883https://doi.org/10.14778/3659437.3659444The shuffle model of differential privacy provides promising privacy-utility balances in decentralized, privacy-preserving data analysis. However, the current analyses of privacy amplification via shuffling lack both tightness and generality. To address ...
- research-articleApril 2024
Towards Unsupervised Referring Expression Comprehension with Visual Semantic Parsing
Knowledge-Based Systems (KNBS), Volume 285, Issue CFeb 2024https://doi.org/10.1016/j.knosys.2023.111318AbstractReferring Expression Comprehension (REC) is a task that involves grounding a specific object in an image based on a given referring query in the form of bounding boxes. Existing fully-supervised or weakly-supervised REC methods rely on either ...
Highlights- Recognize the rich semantics contained in images.
- Construct pseudo region-query pairs as training data.
- Present a fine-grained multi-modality fusion decoder for REC.
- research-articleFebruary 2024
MVIndEmo: a dataset for micro video public-induced emotion prediction on social media
AbstractDistinct from the realm of perceived emotion research, induced emotion pertains to the emotional responses engendered within content consumers. This facet has garnered considerable attention and finds extensive application in the analysis of ...
- research-articleApril 2024
Personalized and privacy-preserving federated heterogeneous medical image analysis with PPPML-HMI
Computers in Biology and Medicine (CBIM), Volume 169, Issue CFeb 2024https://doi.org/10.1016/j.compbiomed.2023.107861AbstractHeterogeneous data is endemic due to the use of diverse models and settings of devices by hospitals in the field of medical imaging. However, there are few open-source frameworks for federated heterogeneous medical image analysis with ...
Highlights- A robust and generalizable privacy-preserving personalized federal learning method for heterogeneous medical image analysis.
- A novel decentralized cyclic secure aggregation mechanism with homomorphic encryption.
- PPPML-HMI has ...
- research-articleJuly 2024
Research on Architecture of Intelligent Power Plant based on Digital Twin Technology
PEAI 2024: 2024 International Conference on Power Electronics and Artificial IntelligenceJanuary 2024, Pages 863–868https://doi.org/10.1145/3674225.3674381With the development of society, the industrial structure of China's electric power industry is constantly optimized and upgraded. in order to achieve the goal of "carbon peak, carbon neutralization", there is an urgent need to solve the problem of ...
- research-articleJanuary 2024
Real-time Cyber-Physical Security Solution Leveraging an Integrated Learning-Based Approach
ACM Transactions on Sensor Networks (TOSN), Volume 20, Issue 2Article No.: 27, Pages 1–22https://doi.org/10.1145/3582009Cyber-Physical Systems (CPS) has emerged as a paradigm that connects cyber and physical worlds, which provides unprecedented opportunities to realize intelligent applications such as smart home, smart cities, and smart manufacturing. However, CPS faces a ...
- research-articleFebruary 2024
Gradient complexity and non-stationary views of differentially private empirical risk minimization
Theoretical Computer Science (TCSC), Volume 982, Issue CJan 2024https://doi.org/10.1016/j.tcs.2023.114259AbstractIn this paper, we study the Differentially Private Empirical Risk Minimization (DP-ERM) problem, considering both convex and non-convex loss functions. For cases where DP-ERM involves smooth (strongly) convex loss functions with or without non-...
Communication Efficient and Provable Federated Unlearning
Proceedings of the VLDB Endowment (PVLDB), Volume 17, Issue 5Pages 1119–1131https://doi.org/10.14778/3641204.3641220We study federated unlearning, a novel problem to eliminate the impact of specific clients or data points on the global model learned via federated learning (FL). This problem is driven by the right to be forgotten and the privacy challenges in FL. We ...
- research-articleJanuary 2024
Multi-slice spiral computed tomography diagnosis of juxta-papillary duodenal diverticulum and its relationship with biliopancreatic diseases
Technology and Health Care (TAHC), Volume 32, Issue 12024, Pages 1–8https://doi.org/10.3233/THC-220742BACKGROUND:Juxta-papillary duodenal diverticula (JPDD) are common but are usually asymptomatic, and they are often diagnosed by coincidence.
OBJECTIVE:To analyse the anatomy and classification of JPDD and its relationship with biliary and ...
- research-articleJanuary 2024
Global semantic enhancement network for video captioning
AbstractVideo captioning aims to briefly describe the content of a video in accurate and fluent natural language, which is a hot research topic in multimedia processing. As a bridge between video and natural language, video captioning is a challenging ...
Highlights- A video captioning framework called global semantic enhancement network is proposed.
- It highlights features of informative frames in aggregated video representations.
- It enhances semantic correlations between video and language ...
- review-articleJanuary 2024
A systematic mapping study of bug reproduction and localization
Information and Software Technology (INST), Volume 165, Issue CJan 2024https://doi.org/10.1016/j.infsof.2023.107338Abstract Context:Identifying the root cause of a software bug and fixing it is challenging. One reason for this is that many bugs are not reproducible during bug fixing.
Objective:We aim to provide an overview of existing works on bug reproduction and ...
Highlights- Systematic mapping of 134 primary studies.
- Bug localization and reproduction are mostly studied for Java and C programs.
- Most approaches were tested in experimental settings rather than active projects.