INRIA LEAR-TEXMEX: Video Copy Detection Task

In this paper we present the results of our experiments in the Trecvid'10 copy detection task and introduce the components of our system. In particular, we describe the recent approximate nearest neighbor search method we used to index the hundreds millions of audio descriptors. Our system obtained excellent accuracy and localization results, achieving the best performance on a few transformations, and this with a single kind of image descriptor. Moreover, the analysis evidences that our system can be significantly improved.

[1]  C. Schmid,et al.  On the burstiness of visual elements , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Antonio Torralba,et al.  Spectral Hashing , 2008, NIPS.

[3]  Marko Heikkilä,et al.  Description of interest regions with local binary patterns , 2009, Pattern Recognit..

[4]  Cordelia Schmid,et al.  Product Quantization for Nearest Neighbor Search , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Cordelia Schmid,et al.  INRIA-LEAR'S Video Copy Detection System , 2008, TRECVID.

[6]  Cordelia Schmid,et al.  An Image-Based Approach to Video Copy Detection With Spatio-Temporal Post-Filtering , 2010, IEEE Transactions on Multimedia.

[7]  Paul Over,et al.  Evaluation campaigns and TRECVid , 2006, MIR '06.

[8]  Cordelia Schmid,et al.  Improving Bag-of-Features for Large Scale Image Search , 2010, International Journal of Computer Vision.

[9]  Andrew Zisserman,et al.  Video Google: a text retrieval approach to object matching in videos , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[10]  Cordelia Schmid,et al.  Scale & Affine Invariant Interest Point Detectors , 2004, International Journal of Computer Vision.