MAMaria Teresa Andrade

Maria Teresa Andrade

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Maria Teresa Andrade has a total of 100 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Review of: "Exploding AI-Generated Deepfakes and Misinformation: A Threat to Global Concern in the 21st Century"

    by Maria Teresa Andrade

    Generally, the level of writing is very good, and the addressed topic is very relevant and interesting. But, in my opinion, the article has limited added value because it does not provide meaningful insights into research being conducted and results...

  • Open Access

    Data2MV - A user behaviour dataset for multi-view scenarios

    by Tiago Soares da Costa, Maria Teresa Andrade, Paula Viana, Nuno Castro Silva


  • Open Access

    Deep Learning Approach for Seamless Navigation in Multi-View Streaming Applications

    by Tiago S. Costa, Paula Viana, Maria T. Andrade

    Quality of Experience (QoE) in multi-view streaming systems is known to be severely affected by the latency associated with view-switching procedures. Anticipating the navigation intentions of the viewer on the multi-view scene could provide the means to greatly reduce such latency. The research work presented in this article builds on this premise, by proposing a new predictive view-selection mechanism. A VGG16-inspired Convolutional Neural Network (CNN) is used to identify the viewer’s focus of attention and determine which views would be most suited to be presented in the brief term, i.e., the near term viewing intentions. This way, those views can be locally buffered before they are actually needed. To this aim, two datasets were used to evaluate the prediction performance and impact on latency, in particular when compared to the solution implemented in the previous version of our multi-view streaming system. Results obtained with this work translate into a generalized improvement of the perceived QoE. A significant reduction of latency during view-switching procedures was effectively achieved. Moreover, results also demonstrated that the prediction of the user’s visual interest was achieved with a high level of accuracy. An experimental platform was also established, on which future predictive models can be integrated and compared with previously implemented models.

  • Open Access

    A Dataset for User Visual Behaviour with Multi-View Video Content

    by Tiago Soares da Costa, Maria Teresa Andrade, Paula Viana, Nuno Castro Silva

    Immersive video applications impose unpractical bandwidth requirements for best-effort networks. With Multi-View (MV) streaming, these can be minimized by resorting to view prediction techniques. SmoothMV is a multi-view system that uses a non-intrusive head tracking mechanism to detect the viewer's interest and select appropriate views. By coupling Neural Networks (NNs) to anticipate the viewer's interest, a reduction of view-switching latency is likely to be obtained. The objective of this paper is twofold: 1) Present a solution for acquisition of gaze data from users when viewing MV content; 2) Describe a dataset, collected with a large-scale testbed, capable of being used to train NNs to predict the user's viewing interest. Tracking data from head movements was obtained from 45 participants using an Intel Realsense F200 camera, with 7 video playlists, each being viewed a minimum of 17 times. This dataset is publicly available to the research community and constitutes an important contribution to reducing the current scarcity of such data. Tools to obtain saliency/heat maps and generate complementary plots are also provided as an open-source software package.


  • Open Access

    Photo2Video: Semantic-Aware Deep Learning-Based Video Generation from Still Content

    by Paula Viana, Maria Teresa Andrade, Pedro Carvalho, Luis Vilaça, Inês N. Teixeira, Tiago Costa, Pieter Jonker

    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.


  • Inferring Contextual Data from Real-World Photography

    by Tiago S. Costa, Maria Teresa Andrade, Paula Viana


  • Context-Based Cultural Visits

    by Mariana Assis, Maria Teresa Andrade, Paula Viana


  • Adaptation execution cost definition for a multimedia adaptation decision engine using a neural network

    by Rui Fernandes, M. T. Andrade

    Multimedia content adaptation decision is necessary whenever a multimedia transmission system has multiple adaptations available to adjust the content representation requirements to the present available system resources. The implementation of an adaptation decision module, based on a Markov Decision Process, requires to weight the adaptations, to establish the adaptation plan to deliver the best possible Quality of Experience (QoE) to the user. We present a method, using a feedforward neural network, to determine these costs using two approaches: user and service provider perspectives.

  • Open Access

    Predictive multi‐view content buffering applied to interactive streaming system

    by T.S. Costa, M.T. Andrade, P. Viana

    This Letter discusses the benefits of introducing Machine Learning techniques in multi‐view streaming applications. Widespread use of machine learning techniques has contributed to significant gains in numerous scientific and industry fields. Nonetheless, these have not yet been specifically applied to adaptive interactive multimedia streaming systems where, typically, the encoding bit rate is adapted based on resources availability, targeting the efficient use of network resources whilst offering the best possible user quality of experience (QoE). Intrinsic user data could be coupled with such existing quality adaptation mechanisms to derive better results, driven also by the preferences of the user. Head‐tracking data, captured from camera feeds available at the user side, is an example of such data to which Recurrent Attention Models could be applied to accurately predict the focus of attention of users within videos frames. Information obtained from such models could be used to assist a preemptive buffering approach of specific viewing angles, contributing to the joint goal of maximising QoE. Based on these assumptions, a research line is presented, focusing on obtaining better QoE in an already existing multi‐view streaming system