Álan Lívio V. Guedes

NCL is the declarative programming language used to develop TV applications in IPTV systems and Terrestrial TV standardized by ITU and Brazilian TV Forum, respectively. Its main characteristics are: defining temporal synchronization among media assets and viewer interactions; layout reuse facilities; support multi-device presentation; support embed HTML code and scripts in the lightweight scripting language Lua; and an API for life-cycle controls (start, pause, resume, stop) and modifying applications on-the-fly called NCL editing command. This talk briefly introduces NCL, highlights its recent advances, and discuss the future of the language.

Many recent works have successfully applied some types of Convolutional Neural Networks (CNNs) to reduce the noticeable distortion resulting from the lossy JPEG compression technique. Most of them are built upon the processing made on the spatial domain. In this work, we propose a JPEG image decoder that is purely based on the frequency-to-frequency domain: it reads the quantized DCT coefficients received from a low-quality image bitstream and, using a deep learning-based model, predicts the missing coefficients in order to recompose the same image with enhanced quality. In experiments with two datasets, our best model was able to improve from images with quantized DCT coefficients corresponding to a Qualityz Factor (QF) of 10 to enhanced quality images with QF slightly higher than 20.

Face recognition systems are present in many modern solutions and thousands of applications in our daily lives. However, current solutions are not easily scalable, especially when it comes to the addition of new targeted people. We propose a cluster-matching-based approach for face recognition in video. In our approach, we use unsupervised learning to cluster the faces present in both the dataset and targeted videos selected for face recognition. Moreover, we design a cluster matching heuristic to associate clusters in both sets that is also capable of identifying when a face belongs to a non-registered person. Our method has achieved a recall of 99.435% and a precision of 99.131% in the task of video face recognition. Besides performing face recognition, it can also be used to determine the video segments where each person is present.

The recent availability of consumer-level head-mounted displays and omnidirectional cameras has been driving an explosion of 360 video content. Transforming the original recorded 360 video content in meaningful interactive multimedia presentations that support viewers in tasks such as learning, entertainment, and telepresence, however, is not trivial and requires new tools. Such tools must provide an easy-to-use authoring model for the integration of different media objects and active user interface elements.In this paper, based on real-world scenarios for interactive 360 videos, we gather a set of requirements and propose a declarative authoring model to support authors in the process of designing and creating 360-degree interactive video presentations. As a case study, we implement different applications showing the expressiveness and completeness of the model in the scope of the target scenarios.

Due to the extensive use of video-sharing platforms and services for their storage, the amount of such media on the internet has become massive. This volume of data makes it difficult to control the kind of content that may be present in such video files. One of the main concerns regarding the video content is if it has an inappropriate subject matter, such as nudity, violence, or other potentially disturbing content. More than telling if a video is either appropriate or inappropriate, it is also important to identify which parts of it contain such content, for preserving parts that would be discarded in a simple broad analysis. In this work, we present a multimodal~(using audio and image features) architecture based on Convolutional Neural Networks (CNNs) for detecting inappropriate scenes in video files. In the task of classifying video files, our model achieved 98.95\% and 98.94\% of F1-score for the appropriate and inappropriate classes, respectively. We also present a censoring tool that automatically censors inappropriate segments of a video file.

There are many ways to build a person identification system and those systems can be used for authentication and security. The latest phones for example, bring fingerprint readers to enhance the user experience. From our perspective on Neural Networkswe determine that Machine Learning is enough to guarantee someone’s identity without the need of any specific sensors other than a camera and a microphone. It is achievable with pictures of their face, sounds of their voice and Deep Learning. This work presents a study to build an application to allow biometric authentication using only multimedia and Deep Learning.