Search Results for author:
Found 32 papers, 24 papers with code
A template-independent approach for information extraction in real estate documents
We propose an extraction pipeline that employs question-answering models to get insight from unstructured data, allowing fast and efficient information retrieval from different sources.
In-season and dynamic crop mapping using 3D convolution neural networks and sentinel-2 time series
In this paper we present a Deep Neural Network-based approach capable of generating (i) a crop map of the current season at a specific point in time (“In season mapping” conventionally at the end of the current year), along with (ii) all intermediate maps during the season able to describe in near real-time the evolution of crop presence (“Dynamic-mapping” at the temporal granularity of satellite imagery revisiting, e. g., 5 days for Sentinel-2 data).
An Adversarial Generative Network Designed for High-Resolution Monocular Depth Estimation from 2D HiRISE Images of Mars
In this paper, we combine these last two concepts into a single end-to-end model and introduce a new generative adversarial network solution that estimates the DTM at 4× resolution from a single monocular image, called SRDiNet (super-resolution depth image network).
Ranked #1 on
Depth Estimation
on Mars DTM Estimation
Generative Adversarial Network
Monocular Depth Estimation
+2
Two New Datasets for Italian-Language Abstractive Text Summarization
Text summarization aims to produce a short summary containing relevant parts from a given text.
Ranked #1 on
Abstractive Text Summarization
on MLSum-it
Food Recommendations for Reducing Water Footprint
Therefore, in this work, we present a personalized food recommendation scheme, mapping the ingredients to the most resource-friendly dishes on the planet and in particular, selecting recipes that contain ingredients that consume as little water as possible for their production.
Is One Teacher Model Enough to Transfer Knowledge to a Student Model?
Nowadays, the transfer learning technique can be successfully applied in the deep learning field through techniques that fine-tune the CNN’s starting point so it may learn over a huge dataset such as ImageNet and continue to learn on a fixed dataset to achieve better performance.
Learning to Navigate in the Gaussian Mixture Surface
We aim to reduce variances considering many centers per class, using the information from the hidden layers of a deep model, and decreasing the high response from the unnecessary areas of images detected along the baselines.
EnGraf-Net: Multiple Granularity Branch Network with Fine-Coarse Graft Grained for Classification Task
Fine-Grained classification models can expressly focus on the relevant details useful to distinguish highly similar classes typically when the intra-class variance is high and the inter-class variance is low given a dataset.
Ranked #1 on
Fine-Grained Image Classification
on FGVC-Aircraft
Sentinel 2 Time Series Analysis with 3D Feature Pyramid Network and Time Domain Class Activation Intervals for Crop Mapping
In this paper, we provide an innovative contribution in the research domain dedicated to crop mapping by exploiting the of Sentinel-2 satellite images time series, with the specific aim to extract information on “where and when” crops are grown.
Combining Optimization Methods Using an Adaptive Meta Optimizer
In our article, we propose the use of the combination of two very different optimizers that, when used simultaneously, can exceed the performance of the single optimizers in very different problems.
Visual Word Embedding for Text Classification
The question we answer with this paper is: ‘can we convert a text document into an image to take advantage of image neural models to classify text documents?’ To answer this question we present a novel text classification method that converts a document into an encoded image, using word embedding.
Improving the Efficient Neural Architecture Search via Rewarding Modifications
Neural Architecture Search (NAS) has achieved remarkable results in deep learning applications in the past few years.
Image and Text fusion for UPMC Food-101 \\using BERT and CNNs
The modern digital world is becoming more and more multimodal.
Ranked #1 on
Document Text Classification
on Food-101
Mixing ADAM and SGD: a Combined Optimization Method
Optimization methods (optimizers) get special attention for the efficient training of neural networks in the field of deep learning.
Ranked #1 on
Stochastic Optimization
on CIFAR-100
$σ^2$R Loss: a Weighted Loss by Multiplicative Factors using Sigmoidal Functions
In neural networks, the loss function represents the core of the learning process that leads the optimizer to an approximation of the optimal convergence error.
Learn Class Hierarchy using Convolutional Neural Networks
A large amount of research on Convolutional Neural Networks has focused on flat Classification in the multi-class domain.
Can a powerful neural network be a teacher for a weaker neural network?
Is it possible to improve the performance of a weak neural network using the knowledge acquired by a more powerful neural network?
Cross-modal Speaker Verification and Recognition: A Multilingual Perspective
Recent years have seen a surge in finding association between faces and voices within a cross-modal biometric application along with speaker recognition.
Dynamic Decision Boundary for One-class Classifiers applied to non-uniformly Sampled Data
A typical issue in Pattern Recognition is the non-uniformly sampled data, which modifies the general performance and capability of machine learning algorithms to make accurate predictions.
OCmst: One-class Novelty Detection using Convolutional Neural Network and Minimum Spanning Trees
We present a novel model called One Class Minimum Spanning Tree (OCmst) for novelty detection problem that uses a Convolutional Neural Network (CNN) as deep feature extractor and graph-based model based on Minimum Spanning Tree (MST).
Are These Birds Similar: Learning Branched Networks for Fine-grained Representations
In recent years, natural language descriptions are used to obtain information on discriminative parts of the object.
Ranked #1 on
Multi-Modal Document Classification
on CUB-200-2011
Deep Latent Space Learning for Cross-modal Mapping of Audio and Visual Signals
We quantitatively and qualitatively evaluate the proposed approach on VoxCeleb, a benchmarks audio-visual dataset on a multitude of tasks including cross-modal verification, cross-modal matching, and cross-modal retrieval.
A Classification Methodology based on Subspace Graphs Learning
The objective is to select the best structures created during the training phase using an ensemble of spanning trees.
Picture What you Read
Visualization refers to our ability to create an image in our head based on the text we read or the words we hear.
Do Cross Modal Systems Leverage Semantic Relationships?
Our proposed measure evaluates the semantic similarity between the image and text representations in the latent embedding space.
Binary Classification using Pairs of Minimum Spanning Trees or N-ary Trees
One-class classifiers are trained with target class only samples.
Aiding Intra-Text Representations with Visual Context for Multimodal Named Entity Recognition
With massive explosion of social media such as Twitter and Instagram, people daily share billions of multimedia posts, containing images and text.
Learning Inward Scaled Hypersphere Embedding: Exploring Projections in Higher Dimensions
Majority of the current dimensionality reduction or retrieval techniques rely on embedding the learned feature representations onto a computable metric space.
Image and Encoded Text Fusion for Multi-Modal Classification
To learn feature representations of resulting images, standard Convolutional Neural Networks (CNNs) are employed for the classification task.
Seeing Colors: Learning Semantic Text Encoding for Classification
The question we answer with this work is: can we convert a text document into an image to exploit best image classification models to classify documents?
Git Loss for Deep Face Recognition
Conventionally, CNNs have been trained with softmax as supervision signal to penalize the classification loss.
Ranked #8 on
Face Verification
on YouTube Faces DB
Revisiting Cross Modal Retrieval
We show that text encodings can capture semantic relationships between multiple modalities.
