The emergence of low-cost, high-quality personal wearable cameras combined with the unlimited storage capacity of video-sharing websites have evoked a growing interest in First-Person Videos. Such videos are usually composed of long-running unedited streams captured by a device attached to the user body, which makes them tedious and visually unpleasant to watch. To provide quick access to the video information, efforts have been applied to the development of techniques such as Hyperlapse and Semantic Hyperlapse, which aims to create visually pleasant shorter videos and emphasize semantic portions of the video respectively. We propose a parameter-free Sparse Coding based methodology to adaptively fast-forward First-Person Videos, that emphasize the semantic portions applying a multi-importance approach. Experimental evaluations show that the proposed method creates visually pleasant accelerated outputs to watch, emphasize the relevant segments while keeping the video context.

Prof. Erickson Rangel do Nascimento – Advisor (DCC – UFMG)
Prof. Mario Fernando Montenegro Campos – Co-advisor (DCC – UFMG)
Prof. André Vital Saúde (DCC – UFLA)
Prof. Cláudio Rosito Jung (INF – UFRGS)
Prof. Ricardo da Silva Torres (IC – UNICAMP)
Prof. Silvio Jamil Ferzoli Guimarães (DCC – PUC/MG)