4 citations · 8 across the 10 of their papers we have counts for
11 papers
Differentiable Lifting for Topological Neural Networks
Jorge Luiz Franco, Gabriel Duarte, Alexander Nikitin +3
Topological neural networks (TNNs) enable leveraging high-order structures on graphs (e.g., cycles and cliques) to boost the expressive power of message-passing neural networks. In…
Transformed Multi-view 3D Shape Features with Contrastive Learning
Márcus Vinícius Lobo Costa, Sherlon Almeida da Silva, Bárbara Caroline Benato +2
This paper addresses the challenges in representation learning of 3D shape features by investigating state-of-the-art backbones paired with both contrastive supervised and self-sup…
Towards Understanding 3D Vision: the Role of Gaussian Curvature
Sherlon Almeida da Silva, Davi Geiger, Luiz Velho +1
Recent advances in computer vision have predominantly relied on data-driven approaches that leverage deep learning and large-scale datasets. Deep neural networks have achieved rema…
The Role of Cyclopean-Eye in Stereo Vision
Sherlon Almeida da Silva, Davi Geiger, Luiz Velho +1
This work investigates the geometric foundations of modern stereo vision systems, with a focus on how 3D structure and human-inspired perception contribute to accurate depth recons…
Back to the Future Cyclopean Stereo: a human perception approach combining deep and geometric constraints
Sherlon Almeida da Silva, Davi Geiger, Luiz Velho +1
We innovate in stereo vision by explicitly providing analytical 3D surface models as viewed by a cyclopean eye model that incorporate depth discontinuities and occlusions. This geo…
Real-Time Anomaly Detection with Synthetic Anomaly Monitoring (SAM)
Emanuele Luzio, Moacir Antonelli Ponti
Anomaly detection is essential for identifying rare and significant events across diverse domains such as finance, cybersecurity, and network monitoring. This paper presents Synthe…
Decoupling Decision-Making in Fraud Prevention through Classifier Calibration for Business Logic Action
Emanuele Luzio, Moacir Antonelli Ponti, Christian Ramirez Arevalo +1
Machine learning models typically focus on specific targets like creating classifiers, often based on known population feature distributions in a business context. However, models…
Evaluation of Barlow Twins and VICReg self-supervised learning for sound patterns of bird and anuran species
Fábio Felix Dias, Moacir Antonelli Ponti, Mílton Cezar Ribeiro +1
Taking advantage of the structure of large datasets to pre-train Deep Learning models is a promising strategy to decrease the need for supervised data. Self-supervised learning met…
Dendrogram distance: an evaluation metric for generative networks using hierarchical clustering
Gustavo Sutter Carvalho, Moacir Antonelli Ponti
We present a novel metric for generative modeling evaluation, focusing primarily on generative networks. The method uses dendrograms to represent real and fake data, allowing for t…
Sketch-an-Anchor: Sub-epoch Fast Model Adaptation for Zero-shot Sketch-based Image Retrieval
Leo Sampaio Ferraz Ribeiro, Moacir Antonelli Ponti
Sketch-an-Anchor is a novel method to train state-of-the-art Zero-shot Sketch-based Image Retrieval (ZSSBIR) models in under an epoch. Most studies break down the problem of ZSSBIR…
ASR data augmentation in low-resource settings using cross-lingual multi-speaker TTS and cross-lingual voice conversion
Edresson Casanova, Christopher Shulby, Alexander Korolev +4
We explore cross-lingual multi-speaker speech synthesis and cross-lingual voice conversion applied to data augmentation for automatic speech recognition (ASR) systems in low/medium…