相关论文: Classification of Things in DBpedia using Deep Neu…

Recent empirical evidence has shown that in many real-world systems, successfully represented as networks, interactions are not limited to dyads, but often involve three or more agents at a time. These data are better described by…

We propose a methodology for estimating human behaviors in psychotherapy sessions using mutli-label and multi-task learning paradigms. We discuss the problem of behavioral coding in which data of human interactions is the annotated with…

Human observers engage in selective information uptake when classifying visual patterns. The same is true of deep neural networks, which currently constitute the best performing artificial vision systems. Our goal is to examine the…

Semantic types are a more powerful and detailed way of describing data than atomic types such as strings or integers. They establish connections between columns and concepts from the real world, providing more nuanced and fine-grained…

At its core, this thesis aims to enhance the practicality of deep learning by improving the label and training efficiency of deep learning models. To this end, we investigate data subset selection techniques, specifically active learning…

Training Deep neural networks (DNNs) on noisy labeled datasets is a challenging problem, because learning on mislabeled examples deteriorates the performance of the network. As the ground truth availability is limited with real-world noisy…

A new method of feature extraction in the social network for within-network classification is proposed in the paper. The method provides new features calculated by combination of both: network structure information and class labels assigned…

This paper presents the design of deep learning architectures which allow to classify the social relationship existing between two people who are walking in a side-by-side formation into four possible categories --colleagues, couple, family…

Graph-based analyses have gained a lot of relevance in the past years due to their high potential in describing complex systems by detailing the actors involved, their relations and their behaviours. Nevertheless, in scenarios where these…

Human parsing is a key topic in image processing with many applications, such as surveillance analysis, human-robot interaction, person search, and clothing category classification, among many others. Recently, due to the success of deep…

In music domain, feature learning has been conducted mainly in two ways: unsupervised learning based on sparse representations or supervised learning by semantic labels such as music genre. However, finding discriminative features in an…

We propose a method for formally certifying and quantifying individual fairness of deep neural networks (DNN). Individual fairness guarantees that any two individuals who are identical except for a legally protected attribute (e.g., gender…

Graph Neural Networks (GNNs) have achieved state-of-the-art results in node classification tasks. However, most improvements are in multi-class classification, with less focus on the cases where each node could have multiple labels. The…

The automatic characterization of pedestrians in surveillance footage is a tough challenge, particularly when the data is extremely diverse with cluttered backgrounds, and subjects are captured from varying distances, under multiple poses,…

We report our ongoing work about a new deep architecture working in tandem with a statistical test procedure for jointly training texts and their label descriptions for multi-label and multi-class classification tasks. A statistical…

The increasingly wide usage of location aware sensors has made it possible to collect large volume of trajectory data in diverse application domains. Machine learning allows to study the activities or behaviours of moving objects (e.g.,…

Numerous social, medical, engineering and biological challenges can be framed as graph-based learning tasks. Here, we propose a new feature based approach to network classification. We show how dynamics on a network can be useful to reveal…

Inferring latent attributes of people online is an important social computing task, but requires integrating the many heterogeneous sources of information available on the web. We propose learning individual representations of people using…

Modern graph or network datasets often contain rich structure that goes beyond simple pairwise connections between nodes. This calls for complex representations that can capture, for instance, edges of different types as well as so-called…

We propose a method for inferring human attributes (such as gender, hair style, clothes style, expression, action) from images of people under large variation of viewpoint, pose, appearance, articulation and occlusion. Convolutional Neural…