ComMon SensE: Cross-Modal Search Engine
STATUS: TEST PHASE This demo may be unstable…
The CMSE is our initiative to develop a framework for cross-modal multimedia search.
The CMSE is first a feature extraction library. Based on the OpenCV framework, it is able to process images
of any type and extract many features related to
Color
Texture
Edges
Faces
…
The CMSE also accounts for the textual modality and indexes it as the classical bags-of-words.
The CMSE is then an indexing engine built around our defined indexing and retrieval strategies (see references below).
Some references (see also our list of publications)
Bruno, É., Moënne-Loccoz, N., & Marchand-Maillet, S. (2008). Design of multimodal dissimilarity spaces for retrieval of multimedia documents. IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(9), 1520-1533.
Kludas, J., Bruno, E., & Marchand-Maillet, S. (2008). Can Feature Information Interaction help for Information Fusion in Multimedia Problems?. To appear in Multimedia Tools and Applications Journal special issue on “Metadata Mining for Image Understanding”.
Bruno, E., Kludas, J., & Marchand-Maillet, S. (2007). Combining Multimodal Preferences for Multimedia Information Retrieval. In Proc. of International Workshop on Multimedia Information Retrieval, Augsburg, Germany.