Most studies on affective analysis of text focus on the sentiment or emotion expressed by a whole sentence or document. In this paper, we propose a novel approach to predict the affective states of a described event through the predictions of the corresponding subject, action and object involved in the described event. Rather than using a sentiment label or discrete emotion categories, the affe...

Several recent publications have proposed methods for mapping images into continuous semantic embedding spaces. In some cases the embedding space is trained jointly with the image transformation. In other cases the semantic embedding space is established by an independent natural language processing task, and then the image transformation into that space is learned in a second stage. Proponents...

numerical analyses have shown that successful flow simulations and the accuracy of solution noticeably depend on the number of nodes used in computational meshing. a suitable meshing should have the capability of adapting with main flow parameters. because the number of total nodes that can be used in numerical simulation is limited, making such grid for complex flows is almost difficult, if it...

Multi-class classification becomes challenging at test time when the number of classes is very large and testing against every possible class can become computationally infeasible. This problem can be alleviated by imposing (or learning) a structure over the set of classes. We propose an algorithm for learning a treestructure of classifiers which, by optimizing the overall tree loss, provides s...

Learning to hash has become a crucial technique for big data analytics. Among existing methods, supervised learning approaches play an important role as they can produce compact codes and enable semantic search. However, the size of an instancepairwise similarity matrix used in most supervised hashing methods is quadratic to the size of labeled training data, which is very expensive in terms of...

Several steganography tools are freely available over the Internet, ranging from straight forward least significant embedding to complex transform domain encrypted algorithms within digital images. Given the number of tools available, the digital forensics investigator must not only determine that an image contains embedded hidden information but the method used during the embedding process, al...

In this paper, we introduce an incremental dimensionality reduction approach for labeled data. The algorithm incrementally samples in latent space and chooses a solution that minimizes the nearest neighbor classification error taking into account label information. We introduce and compare two optimization approaches to generate supervised embeddings, i.e., an incremental solution construction ...

This paper introduces a novel deep learning framework including a lexicon-based approach for sentencelevel prediction of sentiment label distribution. We propose to first apply semantic rules and then use a Deep Convolutional Neural Network (DeepCNN) for character-level embeddings in order to increase information for word-level embedding. After that, a Bidirectional Long Short-Term Memory netwo...

In this work we introduce a method for visualization of fuzzy label information obtained from prototype based fuzzy labeled selforganizing map (FLSOM) for fuzzy classification. FLSOM returns vectors of fuzyy class labels for the prototypes containing class simlarity information. This information is used for apropriate visualization by an adequate, similarity preserving color space embedding rea...