Abstract

Abstract
Sign Language Recognition (SLR) has become one of the most important research areas in the field of human computer interaction. SLR systems are meant to automatically translate sign language into text or speech, in order to reduce the communicational gap between deaf and hearing people. The aim of this paper is to exploit multimodal learning techniques for an accurate SLR, making use of data provided by Kinect and Leap Motion. In this regard, single-modality approaches as well as different multimodal methods, mainly based on convolutional neural networks, are proposed. Our main contribution is a novel multimodal end-to-end neural network that explicitly models private feature representations that are specific to each modality and shared feature representations that are similar between modalities. By imposing such regularization in the learning process, the underlying idea is to increase the discriminative ability of the learned features and, hence, improve the generalization capability of the model. Experimental results demonstrate that multimodal learning yields an overall improvement in the sign recognition performance. In particular, the novel neural network architecture outperforms the current state-of-the-art methods for the SLR task. © 2018, Springer Science+Business Media, LLC, part of Springer Nature.

Abstract

Abstract
Despite the high performance of current presentation attack detection (PAD) methods, the robustness to unseen attacks is still an under addressed challenge. This work approaches the problem by enforcing the learning of the bona fide presentations while making the model less dependent on the presentation attack instrument species (PAIS). The proposed model comprises an encoder, mapping from input features to latent representations, and two classifiers operating on these underlying representations: (i) the task-classifier, for predicting the class labels (as bona fide or attack); and (ii) the species-classifier, for predicting the PAIS. In the learning stage, the encoder is trained to help the task-classifier while trying to fool the species-classifier. Plus, an additional training objective enforcing the similarity of the latent distributions of different species is added leading to a 'PAI-species'-independent model. The experimental results demonstrated that the proposed regularisation strategies equipped the neural network with increased PAD robustness. The adversarial model obtained better loss and accuracy as well as improved error rates in the detection of attack and bona fide presentations. © 2019 Gesellschaft fuer Informatik.

Abstract
The importance of recycling is well known, either for environmental or economic reasons, it is impossible to escape it and the industry demands efficiency. Manual labour and traditional industrial sorting techniques are not capable of keeping up with the objectives demanded by the international community. Solutions based in computer vision techniques have the potential automate part of the waste handling tasks. In this paper, we propose a hierarchical deep learning approach for waste detection and classification in food trays. The proposed two-step approach retains the advantages of recent object detectors (as Faster R-CNN) and allows the classification task to be supported in higher resolution bounding boxes. Additionally, we also collect, annotate and make available to the scientific community a new dataset, named Labeled Waste in the Wild, for research and benchmark purposes. In the experimental comparison with standard deep learning approaches, the proposed hierarchical model shows better detection and classification performance. © 2019 IEEE.