92 citations · 260 across the 17 of their papers we have counts for
19 papers
An overview of 3D Vision-Language Models
Márcus Lobo, Vitor Matias, Afonso Paiva +3
Vision-Language Models (VLMs) are reshaping computer vision by aligning visual and textual embeddings, allowing models to recognize visual concepts and reason about them using natu…
3D-MRL: Nested Multimodal 3D Representations via Matryoshka Representation Learning
Márcus Lobo, Vitor Matias, Jeová Farias +1
Vision-Language Models align point clouds with image and text embeddings, enabling zero-shot recognition, retrieval, and open-vocabulary understanding of 3D shapes. Existing multim…
Improving Data Quality with Training Dynamics of Gradient Boosting Decision Trees
Moacir Antonelli Ponti, Lucas de Angelis Oliveira, Mathias Esteban +3
Real world datasets contain incorrectly labeled instances that hamper the performance of the model and, in particular, the ability to generalize out of distribution. Also, each exa…
Implementing simple spectral denoising for environmental audio recordings
Fábio Felix Dias, Moacir Antonelli Ponti, Rosane Minghim
This technical report details changes applied to a noise filter to facilitate its application and improve its results. The filter is applied to denoise natural sounds recorded in t…
YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone
Edresson Casanova, Julian Weber, Christopher Shulby +3
YourTTS brings the power of a multilingual approach to the task of zero-shot multi-speaker TTS. Our method builds upon the VITS model and adds several novel modifications for zero-…
Training Deep Networks from Zero to Hero: avoiding pitfalls and going beyond
Moacir Antonelli Ponti, Fernando Pereira dos Santos, Leo Sampaio Ferraz Ribeiro +1
Training deep neural networks may be challenging in real world data. Using models as black-boxes, even with transfer learning, can result in poor generalization or inconclusive res…