The Workshop

Multimedia content and video consumption are expected to take a central role in the post-pandemic world. Thus, providing new advanced interfaces and services that exploit them and lessen their weaker aspects becomes of paramount importance. Video consumption suffers for instance from the well-known problem of linear-sequential viewing, poor content retrieval, lack of structure and lack of highlighting of relevant features. Online video services and the research community are working to provide tools that enhance the user experience with video consumption. This issue affects in particular the use of videos for learning and training purposes. The provision of augmentation services such as visual feedback, knowledge graphs, and visual summaries of video fragments, just to give some examples, have been shown to limit the problems mentioned above. However, automating the development of such services is still a challenge, recently addressed by exploiting deep learning models that use multimodal input data, but further research is needed to exploit the results in effective  services. Personalized visual annotation of videos and adaptive interfaces for data visualization and mobile interaction are further examples of video augmentation that can address the needs of users with different needs, abilities and usage contexts.