Abstract
Applying machine learning (ML), and especially deep learning, to understand visual content is becoming common practice in many application areas. However, little attention has been given to its use within the multimedia creative domain. It is true that ML is already popular for content creation, but the progress achieved so far addresses essentially textual content or the identification and selection of specific types of content. A wealth of possibilities are yet to be explored by bringing the use of ML into the multimedia creative process, allowing the knowledge inferred by the former to influence automatically how new multimedia content is created. The work presented in this article provides contributions in three distinct ways towards this goal: firstly, it proposes a methodology to re-train popular neural network models in identifying new thematic concepts in static visual content and attaching meaningful annotations to the detected regions of interest; secondly, it presents varied visual digital effects and corresponding tools that can be automatically called upon to apply such effects in a previously analyzed photo; thirdly, it defines a complete automated creative workflow, from the acquisition of a photograph and corresponding contextual data, through the ML region-based annotation, to the automatic application of digital effects and generation of a semantically aware multimedia story driven by the previously derived situational and visual contextual data. Additionally, it presents a variant of this automated workflow by offering to the user the possibility of manipulating the automatic annotations in an assisted manner. The final aim is to transform a static digital photo into a short video clip, taking into account the information acquired. The final result strongly contrasts with current standard approaches of creating random movements, by implementing an intelligent content- and context-aware video.

Abstract

Abstract

Abstract
The media sector is constantly evolving and, in the last few years, such evolution has been driven by a number of convergence paradigms, notably, that between broadband and broadcast technologies with the introduction of IT and IP technology. The present trend is to switch totally from a closed niche that uses highly specialized equipment to off-the-shelf IT-centric solutions, offering easy configuration and remote operation. The aim is to enable common computers to be turned into highly capable media devices and act as connected objects adopting an IoT-like paradigm. This vision, though, is not implemented easily, given that most media industry professionals do not yet feel comfortable operating in the IT technology space and also due to the stringent requirements that exist in this industry. The Joint Task Force on Networked Media is defining specifications that aim at overcoming such existing barriers. In this article we present a novel solution that follows the guidelines delivered by this group to set up a remotely operated media production facility, totally based on IP and IT technology, constituting a step forward the realization of the IoT concept in professional media environments. The focus is on two complementary components, namely, the GUI Agent and the MW Agent, which are not covered by the defined specifications but that are crucial to speed up the deployment of concrete solutions that can be easily operated by non-IT and non-IP experts in a transparent and ubiquitous way. © 2020 TRON Forum.

Abstract