This chapter provides a survey of the major research efforts that have exploited computer vision tools to extend the content production industry towards automated infrastructures allowing contents to be produced, stored, and accessed at low cost and in a personalized and dedicated way.
Chen, F., Delannay, D., De Vleeschouwer, C., & Parisot, P. (2010). Multi-sensored vision for autonomous production of personalized video summary. In Jinjun Wang, Jian Cheng Shuqiang Jiang (eds.) (ed.), Computer Vision for Multimedia Applications: Methods and Solutions (p. p. 102-120). IGI global. https://hdl.handle.net/2078.5/253630