Search results for "Moda"

Neural Multimodal Belief Tracker with Adaptive Attention for Dialogue Systems

2019

Multimodal dialogue systems are attracting increasing attention with a more natural and informative way for human-computer interaction. As one of its core components, the belief tracker estimates the user's goal at each step of the dialogue and provides a direct way to validate the ability of dialogue understanding. However, existing studies on belief trackers are largely limited to textual modality, which cannot be easily extended to capture the rich semantics in multimodal systems such as those with product images. For example, in fashion domain, the visual appearance of clothes play a crucial role in understanding the user's intention. In this case, the existing belief trackers may fail …

Using Internet videos to learn about controversies: Evaluation and integration of multiple and multimodal documents by primary school students

2020

Abstract In many Internet videos authors appear in front of the camera to present their particular view on a topic. Given the high consumption rate of Internet videos by teenagers, we explored the pros and cons of using these videos to learn about complex topics, compared to learning from textual web pages. Specifically, we studied how 207 primary school students (grades 4–6) evaluated and integrated multiple and multimodal web pages (text or video) while learning about the pros and cons of bottled water. Results showed no major role of modality in students' source memory, as measured by citations in their responses to an integration question and their memory for sources. Nevertheless, moda…

MFCC-based Recurrent Neural Network for automatic clinical depression recognition and assessment from speech

2022

Abstract Clinical depression or Major Depressive Disorder (MDD) is a common and serious medical illness. In this paper, a deep Recurrent Neural Network-based framework is presented to detect depression and to predict its severity level from speech. Low-level and high-level audio features are extracted from audio recordings to predict the 24 scores of the Patient Health Questionnaire and the binary class of depression diagnosis. To overcome the problem of the small size of Speech Depression Recognition (SDR) datasets, expanding training labels and transferred features are considered. The proposed approach outperforms the state-of-art approaches on the DAIC-WOZ database with an overall accura…

Gestures in Human-Computer Interaction – Just Another Modality?

2010

The traditional framework in human-computer studies is based on a simple input-output model of interaction. In many cases, however, splitting interaction into input and output is not necessarily appropriate. Gestures work as a good example of a modality which is difficult or inappropriate to be conceptualised within the traditional input-output paradigm. In the search for a more appropriate interaction paradigm, gestures, as modality, have potential in working as a meta-modality, in terms of which all other modalities could be analysed. This paper proposes the use of gestures and gestural metaphors in a central role in interaction design, and presents a case study as an illustration of the …

Benchmarking Saliency Detection Methods on Multimodal Image Data

2018

Saliency detecmage processing. Most of the work is adapted to the specific application and available dataset. The present work is about a comparative analysis of saliency detection for multimodal images dataset. There were many researches on the detection of saliency on several types of images, such as multispectral, natural, 3D and so on. This work presents a first focused study on saliency detection on multimodal images. Our database was extracted from acquisitions on cultural heritage wall paintings that contain four modalities UV, IR, Visible and fluorescence. In this paper, the analysis has been performed for many methods on saliency detection. We evaluate the performance of each metho…

An Embedded Solution for Multispectral Palmprint Recognition

2018

Palmprint based identification has attracted much attention in the past decades. In some real-life applications, portable personal authentication systems with high accuracy and speed efficiency are required. This paper presents an embedded palmprint recognition solution based on the multispectral image modality. We first develop an effective recognition algorithm by using partial least squares regression, then a FPGA prototype is implemented and optimized through high-level synthesis technique. The evaluation experiments demonstrate that the proposed system can achieve a higher recognition rate at a lower running cost comparing to the reference implementations.

LynxNet: Wild Animal Monitoring Using Sensor Networks

2010

Monitoring wild animals, especially those that are becoming endangered (for example, lynxes and wolves) is important for biology researchers. Solutions for the monitoring already exist; however, they all have drawbacks, such as limited range or lifetime, sensing modality, reporting delays, unreliability of operation. In this work we describe our experiences in designing an improved animal monitoring sensor system and low-level software for sensor node control and communication. The target animals for this particular research are wild lynxes or canines, however it can be extended to other animal species. The LynxNet system is based on tracking collars, built around TMote Mini sensor nodes, s…

Modalità “orientata sul partecipante” in siciliano contemporaneo: un’analisi dei dati dell’Atlante linguistico della Sicilia (ALS)

Acousto-Optic Interaction for Accurate Two-Mode Optical Fibers Characterization

2016

Accurate characterization of two-mode fibers by acousto-optic interaction is reported. Difference of modal index, group delay, and dispersion between the guided modes is obtained. Properties of the vector modes comprising the LP11 mode are investigated.

Avoiding tunnel collisions between fibular collateral ligament and ACL posterolateral bundle reconstruction

2010

PURPOSE: The purpose of this study was to evaluate the risk of tunnel collisions of the fibular collateral ligament (FCL) and posterolateral bundle anterior cruciate ligament (PLB-ACL) tunnels during a combined FCL and double-dundle (DB) ACL reconstruction. METHODS: Thirty-six 4th-generation synthetic femurs (Sawbones, Pacific Research Laboratories, Vashon, WA) were utilized, and two different femur sizes were used. A FCL tunnel and a PLB-ACL tunnel were reamed on each femur. The tunnels of synthetic specimens that did not have a collision were filled with an epoxy resin augmented with BaSO(4) and radiographic evaluation, and Multidetector CT exams of the specimens were performed. RESULTS: …