Word2Image: towards visual interpreting of words
MM '08 Proceedings of the 16th ACM international conference on Multimedia
From text question-answering to multimedia QA on web-scale media resources
LS-MMRM '09 Proceedings of the First ACM workshop on Large-scale multimedia retrieval and mining
Visual tag dictionary: interpreting tags with visual words
WSMC '09 Proceedings of the 1st workshop on Web-scale multimedia corpus
Event driven summarization for web videos
WSM '09 Proceedings of the first SIGMM workshop on Social media
Video reference: question answering on YouTube
MM '09 Proceedings of the 17th ACM international conference on Multimedia
Scalable image retrieval based on feature forest
ACCV'09 Proceedings of the 9th Asian conference on Computer Vision - Volume Part III
Hi-index | 0.00 |
Community-based question answering systems have become very popular for providing answers to a wide variety of ”how-to” questions. However, most such systems present only textual answers. In many cases, users would prefer visual answers such as videos which are more intuitive and informative. The Video Reference system is proposed as a solution to the above problem. It automatically extracts videos from YouTube as a video reference responding to a textual question. The demo shows results on real questions sampled from Yahoo! Answering.