@inproceedings{9535aa681def4b4984ff4e20c9b0ab2a,
title = "Detecting semantic concepts from video using temporal gradients and audio classification",
abstract = "In this paper we describe new methods to detect semantic concepts from digital video based on audible and visual content. Temporal Gradient Correlogram captures temporal correlations of gradient edge directions from sampled shot frames. Power-related physical features are extracted from short audio samples in video shots. Video shots containing people, cityscape, landscape, speech or instrumental sound are detected with trained self-organized maps and kNN classification results of audio samples. Test runs and evaluations in TREC 2002 Video Track show consistent performance for Temporal Gradient Correlogram and state-of-the-art precision in audio-based instrumental sound detection.",
author = "Mika Rautiainen and Tapio Sepp{\"a}nen and Jani Penttil{\"a} and Johannes Peltola",
year = "2003",
doi = "10.1007/3-540-45113-7_26",
language = "English",
isbn = "978-3-540-40634-1",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "260--270",
booktitle = "Image and Video Retrieval",
address = "Germany",
note = "Image and Video Retrieval, CIVR 2003 , CIVR 2003 ; Conference date: 24-07-2003 Through 25-07-2003",
}