- Functional Brain Connectivity Studies
- Genetics and Neurodevelopmental Disorders
- Autism Spectrum Disorder Research
- Video Surveillance and Tracking Methods
- Domain Adaptation and Few-Shot Learning
- Advanced Image and Video Retrieval Techniques
- COVID-19 diagnosis using AI
- Anomaly Detection Techniques and Applications
- Advanced Neural Network Applications
- Human Pose and Action Recognition
- Advanced Data Compression Techniques
- Advanced Clustering Algorithms Research
- Data Management and Algorithms
- Multimodal Machine Learning Applications
Hamad bin Khalifa University
2023-2024
M S Ramaiah University of Applied Sciences
2023
Mohamed bin Zayed University of Artificial Intelligence
2022
The video classification task has gained significant success in the recent years. Specifically, topic more attention after emergence of deep learning models as a successful tool for automatically classifying videos. In recognition importance and to summarize this task, paper presents very comprehensive concise review on topic. There are several existing reviews survey papers related scientific literature. However, do not include state-of-art works, they also have some limitations. To provide...
Self-Supervised Learning (SSL) has enhanced the learning process of semantic representations from images. SSL reduced need for annotating or labelling data by relying less on class labels during training phase. techniques dependent Constrative (CL) are acquiring prevalence because their low dependency labels. Different CL methods producing state-of-the-art results datasets which used as benchmarks Supervised Learning. In this survey, we provide a review CL-based including SimCLR, MoCo, BYOL,...
This work proposes a novel Split and Kernel-Merge Clustering (S-KMC), nonparametric clustering algorithm that combines the strengths of hierarchical clustering, partitional density-based clustering. It consists two main phases: Splitting Merging. In phase, ranking-based operator is used to divide data into optimal subclusters. Merging kernel function estimates density these subclusters after projecting them onto straight line passing through their centers, facilitating merging operation....
Abstract Autism Spectrum Disorder is a neurodevelopmental condition characterized by difficulties with social interaction, verbal and nonverbal communication, interests, hobbies, stereotyped, constrained behavior. In order to automate the identification of brain disorders marked deficiencies repeated behaviors, machine learning deep approaches have become very significant. paper, we proposed implemented models convolution neural network (CNN) for classifying subjects ASD. Data from Brain...
Object Detection (OD) in aerial images has gained much attention due to its applications search and rescue, town planning, agriculture yield prediction etc. Recently introduced large-scale dataset, iSAID enabled the researchers advance OD tasks on satellite images. Unfortunately, available pipelines ready-to-train architectures are well-tailored configured be used with dealing natural In this work, we study that directly using object detectors, specifically vanilla Faster RCNN FPN is...