Tutorial on Bridging Video and Language with Deep Learning

This is an invited tutorial given at ECCV and ACM Multimedia 2016 (http://www.eccv2016.org/invited-tutorials/ (opens in new tab)).  The tutorial includes several parts, including image and video captioning, video commenting, video and language alignment, summary of MSR Video to Language Grand Challenge held in ACM Multimedia 2016, performance metrics, datasets, and open issues.