487 citations · 655 across the 12 of their papers we have counts for
6 papers · 1 filter
Tell me what you see: A zero-shot action recognition method based on natural language descriptions
Valter Estevam, Rayson Laroca, David Menotti +1
This paper presents a novel approach to Zero-Shot Action Recognition. Recent works have explored the detection and classification of objects to obtain semantic information from vid…
Dense Video Captioning Using Unsupervised Semantic Information
Valter Estevam, Rayson Laroca, Helio Pedrini +1
We introduce a method to learn unsupervised semantic visual information based on the premise that complex events can be decomposed into simpler events and that these simple events…
Weakly Supervised Attention-based Models Using Activation Maps for Citrus Mite and Insect Pest Classification
Edson Bollis, Helena Maia, Helio Pedrini +1
Citrus juices and fruits are commodities with great economic potential in the international market, but productivity losses caused by mites and other pests are still far from being…
On the Effect of Pruning on Adversarial Robustness
Artur Jordao, Helio Pedrini
Pruning is a well-known mechanism for reducing the computational cost of deep convolutional networks. However, studies have shown the potential of pruning as a form of regularizati…
AttributeNet: Attribute Enhanced Vehicle Re-Identification
Rodolfo Quispe, Cuiling Lan, Wenjun Zeng +1
Vehicle Re-Identification (V-ReID) is a critical task that associates the same vehicle across images from different camera viewpoints. Many works explore attribute clues to enhance…
Improving Makeup Face Verification by Exploring Part-Based Representations
Marcus de Assis Angeloni, Helio Pedrini
Recently, we have seen an increase in the global facial recognition market size. Despite significant advances in face recognition technology with the adoption of convolutional neur…