Video Google: A Text Retrieval Approach to Object Matching in Videos
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
CISP '08 Proceedings of the 2008 Congress on Image and Signal Processing, Vol. 5 - Volume 05
Toward Multi-modal Music Emotion Classification
PCM '08 Proceedings of the 9th Pacific Rim Conference on Multimedia: Advances in Multimedia Information Processing
Music information retrieval using social tags and audio
IEEE Transactions on Multimedia - Special section on communities and media computing
A user-centered design of a personal digital library for music exploration
Proceedings of the 10th annual joint conference on Digital libraries
Improving mood classification in music digital libraries by combining lyrics and audio
Proceedings of the 10th annual joint conference on Digital libraries
A new approach to cross-modal multimedia retrieval
Proceedings of the international conference on Multimedia
Visual expression for organizing and accessing music collections in MusicWiz
ECDL'10 Proceedings of the 14th European conference on Research and advanced technology for digital libraries
A correlation approach for automatic image annotation
ADMA'06 Proceedings of the Second international conference on Advanced Data Mining and Applications
A Survey of Audio-Based Music Classification and Annotation
IEEE Transactions on Multimedia
| Hi-index | 0.00 |
In CADAL, there preserve a lot of Chinese classical literatures, including graceful prose and verse. These works written in ancient Chinese comparatively are concise in vocabulary and sentence patterns. But they express rich feelings and convey a wealth of information. Although can be explained in modern Chinese, the aesthetic sense in those works disappears. So we aim to illustrate the feeling in these works using Chinese traditional music which is also another part of Chinese culture. This is an interesting and challenging work. In this paper, the correlation between the text and music is studied. A novel approach is proposed to model the latent semantic association underlying the two medium. Based on the correlation model we learned from training data, we can associate a literary work (mainly verse and prose in our digital library) with a few music pieces automatically. When a reader is appreciating a literary work, a piece of background music is playing meanwhile, the information and emotion implied by the work and music blend together. The reader may be immersed into the emotion and obtain aesthetic enjoyment intensively. We implement the proposed method and design experiments to evaluate the performance of it. The experimental result substantiates the feasibility of the proposed approach in this paper.