In this paper, we propose two video fingerprinting methods that are robust to both geometric and non-geometric modifications on content. Both of the proposed methods are based on ...
For multimedia interpretation, and in particular for the combined interpretation of information coming from different modalities, a semantically well-founded formalization is requ...
We consider the problem of clustering Web image search results. Generally, the image search results returned by an image search engine contain multiple topics. Organizing the resu...
Deng Cai, Xiaofei He, Zhiwei Li, Wei-Ying Ma, Ji-R...
We present an approach to video editing where movie sequences are treated as spatio-temporal volumes that can be sheered and warped under user control. This simple capability enab...
Describing shots through the occurrence of semantic concepts is the first step towards modeling the content of a video semantically. An important challenge is to automatically se...