2 citations · 3 across the 4 of their papers we have counts for
7 papers
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…
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…
Scene Designer: a Unified Model for Scene Search and Synthesis from Sketch
Leo Sampaio Ferraz Ribeiro, Tu Bui, John Collomosse +1
Scene Designer is a novel method for searching and generating images using free-hand sketches of scene compositions; i.e. drawings that describe both the appearance and relative po…
Sketchformer: Transformer-based Representation for Sketched Structure
Leo Sampaio Ferraz Ribeiro, Tu Bui, John Collomosse +1
Sketchformer is a novel transformer-based representation for encoding free-hand sketches input in a vector form, i.e. as a sequence of strokes. Sketchformer effectively addresses m…
Generalization of feature embeddings transferred from different video anomaly detection domains
Fernando Pereira dos Santos, Leonardo Sampaio Ferraz Ribeiro, Moacir Antonelli Ponti
Detecting anomalous activity in video surveillance often involves using only normal activity data in order to learn an accurate detector. Due to lack of annotated data for some spe…
Unsupervised representation learning using convolutional and stacked auto-encoders: a domain and cross-domain feature space analysis
Gabriel B. Cavallari, Leonardo Sampaio Ferraz Ribeiro, Moacir Antonelli Ponti
A feature learning task involves training models that are capable of inferring good representations (transformations of the original space) from input data alone. When working with…