Large language models (LLMs) have demonstrated strong capabilities in generating executable code from natural language descriptions. However, general-purpose models often struggle …
A automação está transformando o mundo do trabalho, e o setor florestal não é exceção. Sensores, drones e algoritmos agora fazem parte do manejo de florestas, da análise de riscos …
Neste artigo, exploramos o crescente panorama das realidades sintéticas, detalhando seu impacto, avanços tecnológicos e os dilemas éticos. Realidades sintéticas são construções …
Fully-unsupervised Person and Vehicle Re-Identification have received increasing attention due to their broad applicability in surveillance, forensics, event understanding, and …
Synthetic realities are digital creations or augmentations that are contextually generated through the use of Artificial Intelligence (AI) methods, leveraging extensive amounts of …
Self-supervised learning deals with problems that have little or no available labeled data. Recent work has shown impressive results when underlying classes have significant …
Person Re-Identification (ReID) across non-overlapping cameras is a challenging task and, for this reason, most works in the prior art rely on supervised feature learning from a …
Most pictures shared online are accompanied by a temporal context (i.e., the moment they were taken) that aids their understanding and the history behind them. Claiming that these …
Portuguese tile panels, or azulejos, are one of Portugal’s cultural icons, and a representative cultural heritage of this country. Portugal’s museums currently have a large …
We present a novel method for synthesizing texture over a 3D model from 2D photographs of the modeled object. By considering an optimization approach, we subdivide the mesh into …