Title :
MMSS: multi-modal story-oriented video summarization
Author :
Pan, Jia-Yu ; Yang, Hyungjeong ; Faloutsos, Christos
Author_Institution :
Dept. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
Abstract :
We propose multi-modal story-oriented video summarization (MMSS) which, unlike previous works that use fine-tuned, domain-specific heuristics, provides a domain-independent, graph-based framework. MMSS uncovers correlation between information of different modalities which gives meaningful story-oriented news video summaries. MMSS can also be applied for video retrieval, giving performance that matches the best traditional retrieval techniques (OKAPI and LSI), with no fine-tuned heuristics such as tf/idf.
Keywords :
graph theory; image retrieval; video signal processing; MMSS; domain-independent graph-based framework; fine-tuned domain-specific heuristics; multi-modal story-oriented video summarization; video retrieval; Broadcasting; Computer science; Content based retrieval; Data mining; Information retrieval; Large scale integration; Libraries; Motion pictures; Multimedia communication; Robustness;
Conference_Titel :
Data Mining, 2004. ICDM '04. Fourth IEEE International Conference on
Print_ISBN :
0-7695-2142-8
DOI :
10.1109/ICDM.2004.10033
