Masaru Sugano

Learn More
Audio information classification becomes a very important task for such purposes as automatic keyword spotting and other content-based audiovisual query system. In this paper, we describe a fast and accurate audio data classification method on MPEG coded data domain. Firstly silent segments are detected using a robust approach for different recording(More)
0. STRUCTURED ABSTRACT Story segmentation 1. Briefly, what approach or combination of approaches did you test in each of your submitted runs? z 1_kddi_ss_base1_5: " Baseline " method based on SVM, which discriminates shots that contain story boundaries. z 1_kddi_ss_c+k1_4: Baseline + section-specialized segmentation (SS-S). z 1_kddi_ss_all1_3: Baseline +(More)
Formerly, once the audio data is compressed, transcoding is used to scale the bit rate, where decoding and re-encoding are taken place. Therefore, data manipulation of coded data has been very complex and time consuming work. In this paper, we describe three algorithms for bit rate scaling on coded MPEG data domain. One is bandwidth limitation method(More)
This paper proposes shot genre classification from MPEG compressed movies, as one of the high-level indexing methods for audiovisual contents. Through statistical analysis of low-level and mid-level audiovisual features on compressed domain, the proposed method can achieve subjectively accurate shot classification within the movies into predefined genre(More)
0. STRUCTURED ABSTRACT Shot boundary detection 1. Briefly, what approach or combination of approaches did you test in each of your submitted runs? z bs-1: Compressed domain approach, which corresponds to the best options in TRECVID 2004 with newly introduced luminance adaptive threshold. z bs-2: Compressed domain approach with newly introduced luminance(More)