Search Results for author:
Found 25 papers, 15 papers with code
CAPIVARA: Cost-Efficient Approach for Improving Multilingual CLIP Performance on Low-Resource Languages
This work introduces CAPIVARA, a cost-efficient framework designed to enhance the performance of multilingual CLIP models in low-resource languages.
SelfGraphVQA: A Self-Supervised Graph Neural Network for Scene-based Question Answering
Scene graphs (SGs) have emerged as a useful tool for multimodal image analysis, showing impressive performance in tasks such as Visual Question Answering (VQA).
Self-supervised Learning of Contextualized Local Visual Embeddings
We present Contextualized Local Visual Embeddings (CLoVE), a self-supervised convolutional-based method that learns representations suited for dense prediction tasks.
P-NOC: adversarial training of CAM generating networks for robust weakly supervised semantic segmentation priors
Weakly Supervised Semantic Segmentation (WSSS) techniques explore individual regularization strategies to refine Class Activation Maps (CAMs).
MIA-3DCNN: COVID-19 Detection Based on a 3D CNN
Convolutional neural networks have been widely used to detect pneumonia caused by COVID-19 in lung images.
When Layers Play the Lottery, all Tickets Win at Initialization
In this work, we investigate LTH and pruning at initialization from the lens of layer pruning.
Single Image Super-Resolution Based on Capsule Neural Networks
Our network achieved good results with fewer convolutional-based layers, showing that capsules might be a concept worth applying in the image super-resolution problem.
Global Semantic Descriptors for Zero-Shot Action Recognition
This work introduces a new ZSAR method based on the relationships of actions-objects and actions-descriptive sentences.
Tell me what you see: A zero-shot action recognition method based on natural language descriptions
To the best of our knowledge, this is the first work to represent both videos and labels with descriptive sentences.
Dense Video Captioning Using Unsupervised Semantic Information
We introduce a method to learn unsupervised semantic visual information based on the premise that complex events (e. g., minutes) can be decomposed into simpler events (e. g., a few seconds), and that these simple events are shared across several complex events.
Weakly Supervised Attention-based Models Using Activation Maps for Citrus Mite and Insect Pest Classification
Despite the integrated pest mechanical aspect, only a few works on automatic classification have handled images with orange mite characteristics, which means tiny and noisy regions of interest.
On the Effect of Pruning on Adversarial Robustness
However, studies have shown the potential of pruning as a form of regularization, which reduces overfitting and improves generalization.
AttributeNet: Attribute Enhanced Vehicle Re-Identification
Vehicle Re-Identification (V-ReID) is a critical task that associates the same vehicle across images from different camera viewpoints.
Ranked #1 on
Vehicle Re-Identification
on VeRi-Wild Large
Improving Makeup Face Verification by Exploring Part-Based Representations
Recently, we have seen an increase in the global facial recognition market size.
Adaptive Multiplane Image Generation from a Single Internet Picture
We present a new lightweight CNN for depth estimation, which is learned by knowledge distillation from a larger network.
Top-DB-Net: Top DropBlock for Activation Enhancement in Person Re-Identification
Person Re-Identification is a challenging task that aims to retrieve all instances of a query image across a system of non-overlapping cameras.
Ranked #1 on
Person Re-Identification
on CUHK03 detected
Parallax Motion Effect Generation Through Instance Segmentation And Depth Estimation
Stereo vision is a growing topic in computer vision due to the innumerable opportunities and applications this technology offers for the development of modern solutions, such as virtual and augmented reality applications.
Lite Training Strategies for Portuguese-English and English-Portuguese Translation
Despite the widespread adoption of deep learning for machine translation, it is still expensive to develop high-quality translation models.
Weakly Supervised Learning Guided by Activation Mapping Applied to a Novel Citrus Pest Benchmark
Pests and diseases are relevant factors for production losses in agriculture and, therefore, promote a huge investment in the prevention and detection of its causative agents.
Multi-Stream Networks and Ground-Truth Generation for Crowd Counting
Crowd scene analysis has received a lot of attention recently due to the wide variety of applications, for instance, forensic science, urban planning, surveillance and security.
Image Super-Resolution Improved by Edge Information
As well as in other knowledge domains, deep learning techniques have revolutionized the development of image super-resolution approaches.
Zero-Shot Action Recognition in Videos: A Survey
Zero-Shot Action Recognition has attracted attention in the last years and many approaches have been proposed for recognition of objects, events and actions in images and videos.
Action Recognition In Still Images
Action Recognition In Videos
+2
Improved Person Re-Identification Based on Saliency and Semantic Parsing with Deep Neural Network Models
Given a video or an image of a person acquired from a camera, person re-identification is the process of retrieving all instances of the same person from videos or images taken from a different camera with non-overlapping view.
Ranked #25 on
Person Re-Identification
on DukeMTMC-reID
Deep Representations for Iris, Face, and Fingerprint Spoofing Detection
We assume a very limited knowledge about biometric spoofing at the sensor to derive outstanding spoofing detection systems for iris, face, and fingerprint modalities based on two deep learning approaches.
