Latest news
A novel approach to Open Set Domain Adaptation leverages unknown exploration, enhancing classification boundaries and improving model adaptability.
Fine-tuned Segment Anything Model (SAM) achieves state-of-the-art lung segmentation in X-ray images. Presented at CIARP 2024.
Our innovative TransferAttn framework enhances Vision Transformers for Unsupervised Domain Adaptation in videos, achieving groundbreaking results in action recognition.
Research areas
The research conducted by our laboratory is deeply rooted in solving practical problems, enabling impactful contributions to academia and industry.
Machine Learning
Develop algorithms that learn and identify complex patterns in data, improving performance in tasks such as classification and prediction.
Deep Learning
Explore deep neural networks to solve complex problems in visual and sequential data, with a focus on pattern recognition and automation.
Natural Language Processing
Create models that understand and generate text in natural language, applying sentiment analysis, automatic translation, and intelligent interfaces.
Computer Vision
Develop systems that analyze and interpret visual data, with images and videos, applied to object recognition and movement analysis.
Recommendation Systems
Create personalized systems that recommend content or products, using collaborative filtering techniques and machine learning-based models.
Location
Partners
LaSID maintains strategic collaborations with leading academic institutions and industry partners, leveraging these relationships to secure competitive funding for high-quality research projects.
Affiliation
