Temporal Cricket Stroke Localization from Untrimmed Highlight Videos
Arpan Gupta, Sakthi Balan M. · 2018
The problem of temporal Cricket stroke localization is important and is the first step towards creation of a domain-specific sports activity dataset. Having a pre-annotated dataset of Cricket activities would be beneficial for training deep neural networks and for recognition of Cricket activities from the telecast videos. Taking Cricket as our domain of interest, we collect 26 Highlight videos of a single T20 tournament and hand-label the Cricket stroke segments in them.