Enhancing perception of the local environment with semantic information like the room type is an important ability for agents acting in their environment. Such high-level knowledge can reduce the effort needed for, e.g., object detection. This paper shows how to extract the room label from a small amount of room percepts taken from a certain view point (like the door frame when entering the roo...

This paper deals with state-of-the-art novel ideas in high level visualization, understanding and interpretation of 3D objects from 2D images. A new strategy using parallel pattern representation and matching is presented, which is aimed at learning, representing, visualizing, and interpreting 2D line drawings as 3D objects with only very few learning samples. The conventional linear combinatio...

The global telephone system is a complex transmission network, the features of which are defined to a very high level by ITU-T standards. It is therefore a prime candidate at which to target the application of software product line techniques, and feature modelling in particular, in order to handle the inherent commonality of protocols and variability in equipment functionality. This paper repo...

This paper advocates a new architecture for textual inference in which finding a good alignment is separated from evaluating entailment. Current approaches to semantic inference in question answering and textual entailment have approximated the entailment problem as that of computing the best alignment of the hypothesis to the text, using a locally decomposable matching score. We argue that the...

Humans' ability to detect and locate salient objects on images is remarkably fast and successful. Performing this process by using eye tracking equipment is expensive and cannot be easily applied, and computer modeling of this human behavior is still a problem to be solved. In our study, one of the largest public eye-tracking databases [1] which has fixation points of 15 observers on 1003 image...

We present a representation learning method that learns features at multiple different levels of scale. Working within the unsupervised framework of denoising autoencoders, we observe that when the input is heavily corrupted during training, the network tends to learn coarse-grained features, whereas when the input is only slightly corrupted, the network tends to learn fine-grained features. Th...

In Context-oriented Programming (COP), programs can be partitioned into behavioral variations expressed as sets of partial program definitions. Such layers can be activated and deactivated at runtime, depending on the execution context. In previous work, we identified the need for application-specific dependencies between layers, and suggested an efficient reflective interface for controlling s...

This paper proposes a new architecture for textual inference in which finding a good alignment is separated from evaluating entailment. Current approaches to semantic inference in question answering and textual entailment have approximated the entailment problem as that of computing the best alignment of the hypothesis to the text, using a locally decomposable matching score. While this formula...

Children affected by Autism Spectrum Disorders (ASD) exhibit behaviors that may vary drastically from child to child. The goal of achieving accurate computer simulations of behavioral responses to given stimuli for different ASD severities is a difficult one, but it could unlock interesting applications such as informing the algorithms of agents designed to interact with those individuals. This...

We describe three modifications to the structure tensor approach to low-level feature extraction. We first show that the structure tensor must be represented at a higher resolution than the original image. Second, we propose a non-linear filter for structure tensor computation that avoids undesirable blurring. Third, we introduce a method to simultaneously extract edge and junction information....