The Experts below are selected from a list of 22875 Experts worldwide ranked by ideXlab platform

Benjamin Schrauwen - One of the best experts on this subject based on the ideXlab platform.

  • sign language recognition using convolutional neural networks
    European Conference on Computer Vision, 2014
    Co-Authors: Lionel Pigou, Sander Dieleman, Pieterjan Kindermans, Benjamin Schrauwen
    Abstract:

    There is an undeniable Communication problem between the Deaf community and the hearing majority. Innovations in automatic sign language recognition try to tear down this Communication Barrier. Our contribution considers a recognition system using the Microsoft Kinect, convolutional neural networks (CNNs) and GPU acceleration. Instead of constructing complex handcrafted features, CNNs are able to automate the process of feature construction. We are able to recognize 20 Italian gestures with high accuracy. The predictive model is able to generalize on users and surroundings not occurring during training with a cross-validation accuracy of 91.7%. Our model achieves a mean Jaccard Index of 0.789 in the ChaLearn 2014 Looking at People gesture spotting competition.

Ardpieter De Man - One of the best experts on this subject based on the ideXlab platform.

Tara Holcomb - One of the best experts on this subject based on the ideXlab platform.

  • Communication Barrier in family linked to increased risks for food insecurity among deaf people who use american sign language
    Public Health Nutrition, 2018
    Co-Authors: Poorna Kushalnagar, Christopher J Moreland, Abbi N Simons, Tara Holcomb
    Abstract:

    Objective Food security is defined as being able to access enough food that will help maintain an active, healthy lifestyle for those living in a household. While there are no studies on food security issues among deaf people, research shows that Communication Barriers early in life are linked to poor physical and mental health outcomes. Childhood Communication Barriers may also risk later food insecurity. Design/Setting/Subjects A single food security screener question found to have 82 % sensitivity in classifying families who are at risk for food insecurity was taken from the six-item US Household Food Security Survey Module. Questions related to food insecurity screener, depression diagnosis and retrospective Communication experience were translated to American Sign Language and then included in an online survey. Over 600 deaf adult signers (18–95 years old) were recruited across the USA. Results After adjusting for covariates, deaf adults who reported being able to understand little to none of what their caregiver said during their formative years were about five times more likely to often experience difficulty with making food last or finding money to buy more food, and were about three times more likely to sometimes experience this difficulty, compared with deaf adults who reported to being able to understand some to all of what their caregiver said. Conclusions Our results have highlighted a marked risk for food insecurity and related outcomes among deaf people. This should raise serious concern among individuals who have the potential to effect change in deaf children’s access to Communication.

Lionel Pigou - One of the best experts on this subject based on the ideXlab platform.

  • sign language recognition using convolutional neural networks
    European Conference on Computer Vision, 2014
    Co-Authors: Lionel Pigou, Sander Dieleman, Pieterjan Kindermans, Benjamin Schrauwen
    Abstract:

    There is an undeniable Communication problem between the Deaf community and the hearing majority. Innovations in automatic sign language recognition try to tear down this Communication Barrier. Our contribution considers a recognition system using the Microsoft Kinect, convolutional neural networks (CNNs) and GPU acceleration. Instead of constructing complex handcrafted features, CNNs are able to automate the process of feature construction. We are able to recognize 20 Italian gestures with high accuracy. The predictive model is able to generalize on users and surroundings not occurring during training with a cross-validation accuracy of 91.7%. Our model achieves a mean Jaccard Index of 0.789 in the ChaLearn 2014 Looking at People gesture spotting competition.

Vareska Van De Vrande - One of the best experts on this subject based on the ideXlab platform.