Video mining: pattern discovery versus pattern recognition

We examine the significance of video mining as pattern discovery in multimedia content. We examine the underlying issue of pattern discovery versus pattern recognition, since most past work has not drawn such a sharp distinction. We argue that while the term "pattern discovery" implies a purely unsupervised approach, in practice a mixture of unsupervised and supervised techniques will have to be used. We compare conventional data mining with video mining and observe that a key difference is in the multilayered semantics of multimedia content. We then identify significant challenges posed by video mining.

[1]  Azriel Rosenfeld,et al.  Video Mining , 2010, The Springer International Series in Video Computing.

[2]  Regunathan Radhakrishnan,et al.  Video Summarization Using Mpeg-7 Motion Activity and Audio Descriptors , 2003 .

[3]  Shih-Fu Chang,et al.  Structure analysis of soccer video with hidden Markov models , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[4]  Ziyou Xiong,et al.  Generation of sports highlights using a combination of supervised & unsupervised learning in audio domain , 2003, Fourth International Conference on Information, Communications and Signal Processing, 2003 and the Fourth Pacific Rim Conference on Multimedia. Proceedings of the 2003 Joint.

[5]  Regunathan Radhakrishnan,et al.  Video mining using combinations of unsupervised and supervised learning techniques , 2003, IS&T/SPIE Electronic Imaging.

[6]  Shih-Fu Chang,et al.  Unsupervised Mining of Statistical Temporal Structures in Video , 2003 .