Apprentissage de représentations pour l’analyse robuste de scènes audiovisuelles

Humans invariably perceive the world multimodally. From a piece of cloth to a car, from a conversation to a concert, each object and event around us is discovered through perceptual senses of vision, sound, touch, smell and taste. Among our...

A brief history of Steganography

If cryptography is the art of secrecy, then steganography may be considered as the art of hiding data secretly.To take a metaphor, steganography would be to make a file in your computer invisible where cryptography would be to lock this...

Flexible and Scalable Models For Clustering and Few-Shot Learning

The advancement of data acquisition technologies through Internet, digital media, social networks, video surveillance and growing business industries have produced massive amounts of high dimensional data. The manipulation of these huge volumes of data is crucial to learn resourceful models,...

Facial Expression Recognition in Videos

Studying facial expression recognition is a challenging task and has drawn increasing attention from computer vision researchers due to its variety of applications in interacting human with computers, medical and psychological assistance and marketing. In fact, facial expression is one...

Pavement Distress Detection with Conventional Self-Driving Car Sensors

Pavement distresses substantially impact the driving comfort, the vehicle operating costs and the road safety. The main causes of pavement distresses are: poor construction, fatigue due to heavy traffic, and natural factors such as water action and extreme temperature fluctuations....

Histology image analysis – background and challenges

Histology image analysis – background and challenges  Cytology imagery provides interesting characteristics that ease the visual analysis like isolated/clustered cells and the absence of complicated structures such as glands. Moreover, this type of image often results from the least invasive...

Visualizing Large Medical Image Datasets using the 3D Scale-Invariant Feature Transform (SIFT)

Consider human-in-the-loop systems that rely on a human expert to make decisions based on data, e.g., clinicians such as radiologists or pathologists interpreting images visually to identify the subtle signs of disease to plan the best possible treatment. According to...

Automatic Eye Localization for Hospitalized Infants and Children Using Convolutional Neural Networks

Consciousness–that is, the patient’s wakefulness and awareness of his or her surroundings– is an important indicator of health and neurological state. Altered consciousness, ranging from confusion and lethargy to loss of consciousness or even coma, may indicate many problems, including...

Application au contrôle non destructif ultrasonore d’un algorithme de déconvolution utilisant des réseaux de neurones convolutifs

Le contrôle non destructif (CND) vise à inspecter une pièce ou une structure en respectant son intégrité. Une multitude de moyens ont été développés dans ce but : du simple contrôle visuel à des techniques plus sophistiquée utilisant les rayons...

Variational Autoencoders with Gaussian Mixture Prior for Recommender Systems

In an era when more content is available electronically every day, it has become harder for consumers to find interesting media such as books, movies, TV shows, songs and textual information. The shear volume of information is overwhelming and provides...