@InProceedings{fu-EtAl:2017:EMNLP2017,
  author    = {Fu, Cheng-Yang  and  Lee, Joon  and  Bansal, Mohit  and  Berg, Alexander},
  title     = {Video Highlight Prediction Using Audience Chat Reactions},
  booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing},
  month     = {September},
  year      = {2017},
  address   = {Copenhagen, Denmark},
  publisher = {Association for Computational Linguistics},
  pages     = {972--978},
  abstract  = {Sports channel video portals offer an exciting domain for research on
	multimodal, multilingual analysis. We present methods addressing the problem of
	automatic video highlight prediction based on joint visual features and textual
	analysis of the real-world audience discourse with complex slang, in both
	English and traditional Chinese. We present a novel dataset based on League of
	Legends championships recorded from North American and Taiwanese Twitch.tv
	channels (will be released for further research), and demonstrate strong
	results on these using multimodal, character-level CNN-RNN model architectures.},
  url       = {https://www.aclweb.org/anthology/D17-1102}
}