Article
Computer Science, Theory & Methods
Ratnabali Pal, Arif Ahmed Sekh, Debi Prosad Dogra, Samarjit Kar, Partha Pratim Roy, Dilip K. Prasad
Summary: Handling a large volume of video data captured through closed-circuit television manually is challenging due to the time-consuming nature of manual analysis and the dynamic conditions of surveillance videos. Therefore, computer vision-based automatic surveillance scene analysis is performed in unsupervised ways, with topic modelling emerging as a key method for this purpose.
ACM COMPUTING SURVEYS
(2021)
Article
Automation & Control Systems
Marissa A. Weis, Kashyap Chitta, Yash Sharma, Wieland Brendel, Matthias Bethge, Andreas Geiger, Alexander S. Ecker
Summary: The study compares the perceptual abilities of four object-centric approaches, finding that architectures with unconstrained latent representations learn more powerful representations. Despite performing well on synthetic data, none of the current methods are able to gracefully handle the most challenging tracking scenarios.
JOURNAL OF MACHINE LEARNING RESEARCH
(2021)
Article
Computer Science, Theory & Methods
Blesson Varghese, Nan Wang, David Bermbach, Cheol-Ho Hong, Eyal De Lara, Weisong Shi, Christopher Stewart
Summary: Edge computing is the future of the internet, leveraging computing resources near users, sensors, and data stores to provide faster services. Benchmarking the performance of such complex systems is crucial, as their operational conditions are expected to change significantly. Edge performance benchmarking has gained momentum as a research field in the past five years.
ACM COMPUTING SURVEYS
(2022)
Article
Computer Science, Information Systems
Jie Guo, Rui Gong, Yuling Ma, Meng Liu, Xiaoming Xi, Xiushan Nie, Yilong Yin
Summary: This paper reviews the research on micro-video analysis, covering methods, features, datasets, and evaluation metrics related to micro-video classification, prediction, and recommendation. The challenges of micro-video analysis are also analyzed.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Physics, Multidisciplinary
Huy D. Le, Tuyen Ngoc Le, Jing-Wein Wang, Yu-Shan Liang
Summary: This paper proposes a novel background initialization method using singular spectrum analysis, which decomposes color channel spatio-temporal data to obtain stable and dynamic components for reconstructing a color background image. Experimental results demonstrate the effectiveness of the proposed method in achieving good color background image reconstruction.
Article
Computer Science, Artificial Intelligence
Jian-Xiang Rong, Lei Zhang, Hua Huang, Fang-Lue Zhang
Summary: This paper presents an online video background identification method using IMU data to estimate camera motion. By analyzing the rotation projection and translation projection of 2D feature points, background feature points can be identified.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2022)
Article
Energy & Fuels
Guillermo Felix, Juan J. Rios, Alexis Tirado, Mikhail A. Varfolomeev, Chengdong Yuan, Jorge Ancheyta
Summary: A methodology to estimate kinetic parameters using the Monte Carlo algorithm and sensitivity analysis is described. The approach is applied to the experimental data reported in the literature for slurry-phase hydrocracking of heavy oil with ionic liquids. It is demonstrated that the reported values of kinetic parameters can be optimized to reduce the average absolute error. Simulations with the Monte Carlo algorithm help find the best initial guess for further optimization of parameters.
Article
Computer Science, Artificial Intelligence
Sarah A. Abdu, Ahmed H. Yousef, Ashraf Salem
Summary: This research provides a comprehensive overview of the latest updates in the field of video sentiment analysis, categorizing thirty-five state-of-the-art models based on the architecture used in each model. It concludes that the most powerful architecture in multimodal sentiment analysis task is the Multi-Modal Multi-Utterance based architecture.
INFORMATION FUSION
(2021)
Article
Computer Science, Artificial Intelligence
Juan Han, Kit Ian Kou, Jifei Miao
Summary: In this study, a quaternion-based DMD method called Q-DMD is proposed to tackle the challenging problem of scene background initialization in computer vision. This method preserves the inherent color structure of color images and videos, and performs better than the exact DMD method on benchmark datasets.
COMPUTER VISION AND IMAGE UNDERSTANDING
(2022)
Article
Computer Science, Artificial Intelligence
Zhengzhong Tu, Yilin Wang, Neil Birkbeck, Balu Adsumilli, Alan C. Bovik
Summary: In recent years, the popularity of user-generated content (UGC) videos on the Internet has increased, leading to a need for accurate video quality assessment (VQA) models. This study contributes to advancing the UGC-VQA problem by evaluating leading blind VQA features and models, providing new insights on subjective video quality studies and objective VQA model design.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2021)
Article
Automation & Control Systems
Gabriel M. Tavares, Rafael S. Oyamada, Sylvio Barbon Junior, Paolo Ceravolo
Summary: This study provides a comprehensive survey and benchmark on event log encoding by comparing 27 methods, from different natures, in terms of expressivity, scalability, correlation, and domain agnosticism. It sheds light on issues, concerns, and future research directions regarding the use of encoding methods to bridge the gap between machine learning models and process mining.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Automation & Control Systems
Linhao Li, Zhen Wang, Qinghua Hu, Yongfeng Dong
Summary: The article introduces a new video sparsity model and dictionary learning operation for foreground detection in intelligent video surveillance, showcasing superior performance compared to current techniques in most cases.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2021)
Article
Engineering, Electrical & Electronic
Wenjun Zhou, Yuheng Deng, Bo Peng, Sheng Xiang, Shun'ichi Kaneko
Summary: Background information is crucial for advanced computer vision applications. In this study, a novel Co-occurrence Spatial-Temporal (CoST) model is proposed for background initialization in high-dynamic complex scenes. The CoST model utilizes a co-occurrence pixel-block structure to achieve a spatial-temporal model and can generate the background adaptively without being affected by high-dynamic complex scenes. Experimental results demonstrate the efficiency of CoST compared to state-of-the-art algorithms.
SIGNAL PROCESSING-IMAGE COMMUNICATION
(2023)
Article
Computer Science, Artificial Intelligence
Xianye Ben, Yi Ren, Junping Zhang, Su-Jing Wang, Kidiyo Kpalma, Weixiao Meng, Yong-Jin Liu
Summary: This survey paper explores the importance of micro-expression analysis and its applications in different fields. The paper highlights the differences between micro-expressions and conventional expressions and provides a systematic research structure, covering various aspects of the field. Additionally, the paper introduces and releases a new dataset, performs a comprehensive evaluation of representative methods, and discusses potential future research directions.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Physics, Multidisciplinary
Kosuke Mitarai, Yasunari Suzuki, Wataru Mizukami, Yuya O. Nakagawa, Keisuke Fujii
Summary: This paper proposes an efficient perturbative approach for benchmarking variational quantum algorithms and performs the largest scale benchmark of hardware-efficient-type ansatzes applied to VQE for one-dimensional hydrogen chains.
PHYSICAL REVIEW RESEARCH
(2022)
Article
Computer Science, Information Systems
Mario Rosario Guarracino, Lucia Maddalena
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2019)
Article
Computer Science, Artificial Intelligence
Ilaria Granata, Mario R. Guarracino, Valery A. Kalyagin, Lucia Maddalena, Ichcha Manipur, Panos M. Pardalos
ANNALS OF MATHEMATICS AND ARTIFICIAL INTELLIGENCE
(2020)
Article
Computer Science, Artificial Intelligence
Lucia Maddalena, Marco Gori, Sankar K. Pal
PATTERN RECOGNITION LETTERS
(2020)
Article
Biochemical Research Methods
Ichcha Manipur, Ilaria Granata, Lucia Maddalena, Mario R. Guarracino
BMC BIOINFORMATICS
(2020)
Article
Computer Science, Artificial Intelligence
Maurizio Giordano, Lucia Maddalena, Mario Manzo, Mario Rosario Guarracino
Summary: This paper explores the effects of maliciously altering training data on graph-level embedding techniques, and provides in-depth observations and studies on methods, resources, experimental settings, and performance results.
ANNALS OF MATHEMATICS AND ARTIFICIAL INTELLIGENCE
(2023)
Article
Multidisciplinary Sciences
Ilaria Granata, Ichcha Manipur, Maurizio Giordano, Lucia Maddalena, Mario Rosario Guarracino
Summary: Studies on tumor metabolic alterations are important for understanding the mechanisms and consequences of tumorigenesis. TumorMet is a repository of tumor metabolic networks extracted from context-specific Genome-Scale Metabolic Models, which serves as a benchmark for graph machine learning algorithms and network analyses. Met2Graph is an R package that allows easy generation of different types of metabolic graphs for downstream analysis.
Correction
Multidisciplinary Sciences
Ilaria Granata, Ichcha Manipur, Maurizio Giordano, Lucia Maddalena, Mario Rosario Guarracino
Review
Computer Science, Artificial Intelligence
Lucia Maddalena, Laura Antonelli, Alexandra Albu, Aroj Hada, Mario Rosario Guarracino
Summary: This review provides an overview of methods, software, data, and evaluation metrics for the automatic analysis of label-free microscopy imaging. The latest methods for cell segmentation, event detection, and tracking are reviewed, and lists of publicly available software and datasets are provided. The review also summarizes the most frequently adopted metrics for evaluating the methods and gives insights on open challenges and future research directions.
Article
Multidisciplinary Sciences
Lusine Khachatryan, Yang Xiang, Artem Ivanov, Enrico Glaab, Garrett Graham, Ilaria Granata, Maurizio Giordano, Lucia Maddalena, Marina Piccirillo, Ichcha Manipur, Giacomo Baruzzo, Marco Cappellato, Batiste Avot, Adrian Stan, James Battey, Giuseppe Lo Sasso, Stephanie Boue, Nikolai V. Ivanov, Manuel C. Peitsch, Julia Hoeng, Laurent Falquet, Barbara Di Camillo, Mario R. Guarracino, Vladimir Ulyantsev, Nicolas Sierro, Carine Poussin
Summary: A recent challenge aimed to explore computational metagenomics methods for diagnosing inflammatory bowel disease (IBD) using metagenomics data. Participants were provided with training and test data from IBD and non-IBD subjects, either in raw read format or processed profiles. The majority of participants achieved better than random predictions in classifying IBD, Ulcerative Colitis (UC), and Crohn's Disease (CD) versus non-IBD. However, distinguishing between UC and CD remains challenging. The results and methodologies used will be shared with the scientific community to advance IBD research.
SCIENTIFIC REPORTS
(2023)
Article
Multidisciplinary Sciences
Laura Antonelli, Federica Polverino, Alexandra Albu, Aroj Hada, Italia A. Asteriti, Francesca Degrassi, Giulia Guarguaglini, Lucia Maddalena, Mario R. Guarracino
Summary: This study presents a dataset named ALFI, consisting of label-free microscopy images and annotations, for detection and tracking of cultured living nontransformed and cancer human cells. The dataset is valuable for testing and comparing methods in identifying different cellular events and discriminating cellular phenotypes.
Article
Biochemical Research Methods
Ichcha Manipur, Maurizio Giordano, Marina Piccirillo, Seetharaman Parashuraman, Lucia Maddalena
Summary: The ability to identify and characterize protein-protein interactions and their internal modular organization through network analysis is crucial for understanding biological processes at the molecular level. It can enhance our understanding of disease pathology and aid in personalized medicine. This review provides an overview of computational methods for detecting protein complexes and functional modules in protein-protein interaction networks, along with their applications. It also proposes a systematic reformulation of existing taxonomies and new categories, reviews recent literature, and offers links to relevant resources.
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS
(2023)
Article
Biochemical Research Methods
Ichcha Manipur, Mario Manzo, Ilaria Granata, Maurizio Giordano, Lucia Maddalena, Mario Rosario Guarracino
Summary: The increasing importance of structured data, especially in the biomedical field, has led to the need for reducing complexity through projections into a more manageable space. The latest methods for learning features on graphs focus on node and edge neighborhoods. To bridge the gap between handcrafted features and a generalized model, this study proposes a neural embedding framework called Netpro2vec, which utilizes probability distribution representations to look at basic node descriptions beyond degree.
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS
(2022)
Proceedings Paper
Engineering, Biomedical
Lucia Maddalena, Ilaria Granata, Maurizio Giordano, Mario Manzo, Mario Rosario Guarracino
Summary: Early diagnosis of neurodegenerative diseases is crucial for delaying the onset of symptoms. This study focuses on using non-invasive techniques to aid in diagnosing Alzheimer's disease. Utilizing machine learning techniques for better integration of omics and imaging data can lead to improved classification results.
PROCEEDINGS OF THE 15TH INTERNATIONAL JOINT CONFERENCE ON BIOMEDICAL ENGINEERING SYSTEMS AND TECHNOLOGIES (BIOIMAGING), VOL 2
(2021)
Correction
Biochemical Research Methods
Ichcha Manipur, Ilaria Granata, Lucia Maddalena, Mario R. Guarracino
BMC BIOINFORMATICS
(2020)
Proceedings Paper
Engineering, Biomedical
Lucia Maddalena, Ilaria Granata, Ichcha Manipur, Mario Manzo, Mario R. Guarracino
PROCEEDINGS OF THE 13TH INTERNATIONAL JOINT CONFERENCE ON BIOMEDICAL ENGINEERING SYSTEMS AND TECHNOLOGIES, VOL 2: BIOIMAGING
(2020)