IEEE JSTSP Article

One challenging aspect in face anti-spoofing (or presentation attack detection, PAD) refers to the difficulty of collecting enough and representative attack samples for an application-specific environment. In view of this, we tackle the problem of training a robust PAD model with limited data in an application-specific domain.

With the rapid progress in recent years, techniques that generate and manipulate multimedia content can now provide a very advanced level of realism. The boundary between real and synthetic media has become very thin. On the one hand, this opens the door to a series of exciting applications in different fields such as creative arts, advertising, film production, and video games. On the other hand, it poses enormous security threats. Software packages freely available on the web allow any individual, without special skills, to create very realistic fake images and videos. 

This paper presents a novel approach for accurate barcodes detection in real and challenging environments using compact deep neural networks. Our approach is based on Convolutional Neural Network ( CNN ) and neural network compression, which can detect the four vertexes coordinates of a barcode accurately and quickly. Our approach consists of four stages: ( i ) feature extraction by a base network, ( ii ) region proposal network ( RPN ) training, ( iii ) barcode classification and coordinates regression, and ( iv ) weights pruning and recoding.

Visual food recognition on mobile devices has attracted increasing attention in recent years due to its roles in individual diet monitoring and social health management and analysis. Existing visual food recognition approaches usually use large server-based networks to achieve high accuracy. 

We consider the problem of reliable information propagation in the brain using biologically realistic models of spiking neurons. Biological neurons use action potentials, or spikes, to encode information. Information can be encoded by the rate of asynchronous spikes or by the (precise) timing of synchronous spikes. Reliable propagation of synchronous spikes is well understood in neuroscience and is relatively easy to implement by biologically-realistic models of neurons. 

Solving visual question answering (VQA) task requires recognizing many diverse visual concepts as the answer. These visual concepts contain rich structural semantic meanings, e.g., some concepts in VQA are highly related (e.g., red & blue), some of them are less relevant (e.g., red & standing).

Deep learning methods haverevolutionized speech recognition, image recognition, and natural language processing since 2010. Each of these tasks involves a single modality in their input signals. However, many applications in the artificial intelligence field involve multiple modalities.

Speech analysis could provide an indicator of Alzheimer's disease and help develop clinical tools for automatically detecting and monitoring disease progression. While previous studies have employed acoustic (speech) features for characterisation of Alzheimer's dementia, these studies focused on a few common prosodic features, often in combination with lexical and syntactic features which require transcription.

Clinical literature provides convincing evidence that language deficits in Alzheimer's disease (AD) allow for distinguishing patients with dementia from healthy subjects. Currently, computational approaches have widely investigated lexicosemantic aspects of discourse production, while pragmatic aspects like cohesion and coherence, are still mostly unexplored.

Obstructive sleep apnea (OSA) is a sleep disorder in which pharyngeal collapse during sleep causes complete (apnea) or partial (hypopnea) airway obstruction. OSA is common and can have severe implications, but often remains undiagnosed. The most widely used objective measure of OSA severity is the number of obstructive events per hour of sleep, known as the apnea-hypopnea index (AHI).