20,609 Result(s)
within
Chapter
**e **an
Algorithm Analysis and Problem Complexity
Artificial Intelligence
Pattern Recognition
-
Chapter and Conference Paper
Improved Training for 3D Point Cloud Classification
The point cloud is a 3D geometric data of irregular format. As a result, they are needed to be transformed into 3D voxels or a collection of images before being fed into models. This unnecessarily increases th...
-
Chapter and Conference Paper
An Autoencoding Method for Detecting Counterfeit Coins
We use coins in our daily life to pay for bus, metro tickets, vending machines, etc. However, the market for antique and historical coins is another place, where the quality of coins and their genuinity play a...
-
Chapter and Conference Paper
Zero-Error Digitisation and Contextualisation of Pi** and Instrumentation Diagrams Using Node Classification and Sub-graph Search
Thousands of huge printed sheets depicting engineering drawings keep record of complex industrial structures from Oil & Gas facilities. Currently, there is a trend of digitising these drawings, having as final...
-
Chapter and Conference Paper
Human Description in the Wild: Description of the Scene with Ensembles of AI Models
Describing an image scene in Natural Language is a very complex procedure for a machine. Many researchers have used Natural Language Processing approaches. In this paper Machine Learning and Computer Vision mo...
-
Chapter and Conference Paper
Learning Distances Between Graph Nodes and Edges
Several applications can be developed when graphs represent objects composed of local parts and their relations. For instance, chemical compounds are characterised by nodes that represent chemical elements and...
-
Chapter and Conference Paper
Realization of Autoencoders by Kernel Methods
An autoencoder is a neural network to realize an identity map** with hidden layers of a relatively small number of nodes. However, the role of the hidden layers is not clear because they are automatically de...
-
Chapter and Conference Paper
A Novel Graph Kernel Based on the Wasserstein Distance and Spectral Signatures
Spectral signatures have been used with great success in computer vision to characterise the local and global topology of 3D meshes. In this paper, we propose to use two widely used spectral signatures, the He...
-
Chapter and Conference Paper
Annotation-Free Keyword Spotting in Historical Vietnamese Manuscripts Using Graph Matching
Finding key terms in scanned historical manuscripts is invaluable for accessing our written cultural heritage. While keyword spotting (KWS) approaches based on machine learning achieve the best spotting resul...
-
Chapter and Conference Paper
Graph Regression Based on Graph Autoencoders
We offer in this paper a trial of encoding graph data as means of efficient prediction in a parallel setup. The first step converts graph data into feature vectors through a Graph Autoencoder (G-AE). Then, der...
-
Chapter and Conference Paper
Classifying Me Softly: A Novel Graph Neural Network Based on Features Soft-Alignment
Graph neural networks are increasingly becoming the framework of choice for graph-based machine learning. In this paper we propose a new graph neural network architecture based on the soft-alignment of the gra...
-
Chapter and Conference Paper
A Capsule Network for Hierarchical Multi-label Image Classification
Image classification is one of the most important areas in computer vision. Hierarchical multi-label classification applies when a multi-class image classification problem is arranged into smaller ones based u...
-
Chapter and Conference Paper
Retargeted Regression Methods for Multi-label Learning
In Multi-Label Classification, utilizing label relationship is a key to improve classification accuracy. Label Space Dimension Reduction or Classifier Chains utilizes the relationship explicitly however those ...
-
Chapter and Conference Paper
Graph Reduction Neural Networks for Structural Pattern Recognition
In industry, business, and science large amounts of data are produced and collected. In some of these data applications, the underlying entities are inherently complex, making graphs the representation formali...
-
Chapter and Conference Paper
One-Against-All Halfplane Dichotomies
Given M vectors in N-dimensional attribute space, it is much easier to find M hyperplanes that separate each of the vectors from all the others than to solve M arbitrary linear dichotomies with approximately e...
-
Chapter and Conference Paper
Efficient Leave-One-Out Evaluation of Kernelized Implicit Map**s
End-to-end learning is discussed in the framework of linear combinations of reproducing kernels associated with training samples. This paper shows that the leave-one-out (LOO) technique can be executed very ef...
-
Chapter and Conference Paper
Spatio-Temporal United Memory for Video Anomaly Detection
Video anomaly detection aims to identify the anomalous that do not conform to normal behavior. The abnormal events tend to relate to appearance and motion, in which there are considerable difference in each ot...
-
Chapter and Conference Paper
Data Augmentation on Graphs for Table Type Classification
Tables are widely used in documents because of their compact and structured representation of information. In particular, in scientific papers, tables can sum up novel discoveries and summarize experimental r...
-
Chapter and Conference Paper
On the Importance of Temporal Features in Domain Adaptation Methods for Action Recognition
One of the most common vision problems is Video based Action Recognition. Many public datasets, public contests, and so on, boosted the development of new methods to face the challenges posed by this problem. ...
-
Chapter and Conference Paper
Tarragona Graph Database for Machine Learning Based on Graphs
Attributed graphs are commonly used to represent structured objects ranging from images or chemical compounds to social networks, among others. In the last years, graphs have become a powerful tool in machine ...
-
Chapter and Conference Paper
Refining AttnGAN Using Attention on Attention Network
AttnGAN finds the semantic relation between text and image using an attention network. However, some of the words in the text description remain unattended. We propose a solution called Refined AttnGAN, which ...
