论文信息 - Eurecom and ECNU at TRECVID 2010 : The Semantic Indexing Task

Eurecom and ECNU at TRECVID 2010 : The Semantic Indexing Task

in the TRECVID context for spatially-independent concepts like “Nighttime”. We then experiment with a multi-modal analysis, combining the visual features with the textual metadata that have been provided with the 2010 video database. As last run, we try a new system based on Hamming Embedding and Weighted Visual words. The runs are composed as follows: 1. EURECOM Fusebase This run fuses a pool of visual features, namely the Sift descriptor, the Color Moments global descriptor, the Wavelet Feature and the Edge Histogram. On top of this, a face detector and a re-ranking method based on the video knowledge are applied, according to the 4 th run that EURECOM presented in the 2009 Edition.

[1] Bernard. Merialdo,et al. Eurecom at TRECVID 2009 High-Level Feature Extraction , 2009, TRECVID.

[2] Bernard Merialdo,et al. Weighting informativeness of bag-of-visual-words by kernel optimization for video concept detection , 2010, VLS-MCMR '10.

[3] Chih-Jen Lin,et al. LIBSVM: A library for support vector machines , 2011, TIST.

[4] Hervé Glotin,et al. IRIM at TRECVID2009: High Level Feature Extraction , 2009 .

[5] Cordelia Schmid,et al. Hamming Embedding and Weak Geometric Consistency for Large Scale Image Search , 2008, ECCV.

[6] Antonio Torralba,et al. Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope , 2001, International Journal of Computer Vision.

[7] G LoweDavid,et al. Distinctive Image Features from Scale-Invariant Keypoints , 2004 .