A central problem in automatic sound recognition is the mapping between low-level audio features and the meaningful content of an auditory scene. We propose a dynamic network model to perform this mapping. In acoustics, much research is devoted to low-level perceptual abilities such as audio feature extraction and grouping, which are translated into successful signal processing techniques. Howe...

This paper proposes a multi-level feature learning framework for human action recognition using body-worn inertial sensors. The framework consists of three phases, respectively designed to analyze signal-based (low-level), components (mid-level) and semantic (high-level) information. Low-level features, extracted from raw signals, capture the time and frequency domain property while mid-level r...

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 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...

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....

When listening to foreign radio or TV programs we are able to pick up some information from the way people are interacting with each others and easily identify the most dominant speaker or the person who is interviewed. Our work relies on the existence of clues about speaker roles in acoustic and prosodic low-level features extracted from audio files and from speaker segmentations. In this pape...