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.

We report the detection of a massive neutral gas outflow in the z = 2.09 gravitationally lensed dusty star-forming galaxy HATLAS J085358.9+015537 (G09v1.40), seen in absorption with the OH+(11-10) transition using spatially resolved (0"5 × 0"4) Atacama Large Millimeter/submillimeter Array (ALMA) observations. The blueshifted OH+ line is observed simultaneously with the CO(9-8) emission line and underlying dust continuum. These data are complemented by high-angular-resolution (0"17 × 0"13) ALMA observations of CH+(1-0) and underlying dust continuum, and Keck 2.2 μm imaging tracing the stellar emission. The neutral outflow, dust, dense molecular gas, and stars all show spatial offsets from each other. The total atomic gas mass of the observed outflow is 6.7 × 109M⊙, >25% as massive as the gas mass of the galaxy. We find that a conical outflow geometry best describes the OH+ kinematics and morphology and derive deprojected outflow properties as functions of possible inclination (0°.38-64°). The neutral gas mass outflow rate is between 83 and 25,400 M⊙ yr-1, exceeding the star formation rate (788 ± 300M⊙ yr-1) if the inclination is >3°.6 (mass-loading factor = 0.3-4.7). Kinetic energy and momentum fluxes span (4.4-290) × 109 L⊙ and (0.1-3.7) × 1037 dyne, respectively (energy-loading factor = 0.013-16), indicating that the feedback mechanisms required to drive the outflow depend on the inclination assumed. We derive a gas depletion time between 29 and 1 Myr, but find that the neutral outflow is likely to remain bound to the galaxy unless the inclination is small and may be reaccreted if additional feedback processes do not occur.