List

 

This paper introduces a new video understanding dataset which can be utilised for the related problems of event recognition, localisation and description in video. Our dataset consists of dense, well structured event annotations in untrimmed video of tennis matches. We also include highly detailed commentary style descriptions, which are heavily dependent on both the occurrence as well as the sequence of particular events. We use general deep learning techniques to acquire some initial baseline results on our dataset, without the need for explicit domain-specific assumptions.

Paper

Dataset Available Soon

  Posts

1 2
January 28th, 2014

You think water moves fast? You should see ice

January 9th, 2017

Video Description (With Deep Neural Networks)

November 30th, 2015

Hello world!

January 28th, 2014

The hidden benefits of gossip, ostracism

January 28th, 2014

Rust Belt gentrification and how it hurts the poor

January 28th, 2014

An old mathematical puzzle soon to be unraveled?

January 28th, 2014

Making stem cells grow human hair

January 28th, 2014

Study analyzes content of nightmares and bad dreams

January 28th, 2014

Just another blog post

January 28th, 2014

Astronomy podcast for kids