Temporal recurrence hashing algorithm for mining commercials from multimedia streams
Temporal recurrence hashing algorithm for mining commercials from multimedia streams
复制标题
DOI：
10.1109/icassp.2011.5946948
复制
发表时间：
2011-05
期刊：
影响因子：
--
通讯作者：
Xiaomeng Wu;S. Satoh
中科院分区：
文献类型：
--
作者：
Xiaomeng Wu;S. Satoh
本文提出了一种完全无监督的超快速电视广告挖掘的双阶段算法。过程中涉及的两个阶段包括：1）寻找重复出现的短片段，以及2）将这些短片段组装成长且完整的商业序列组。第一阶段通过帧散列实现。与依赖于暴力配对的相关研究不同，我们提出了一种第二阶段的哈希算法的循环段组装，这是本文的核心思想。实验使用了包含10小时和1个月流的大规模存档。该算法在不到50分钟的时间内从1个月的流中挖掘商业广告，比相关研究快10倍，序列级准确率为98.05%，帧级准确率为97.39%。我们证明了算法在音频和视频流上的性能一致性，并从理论和实验的角度研究了计算成本。
We propose a dual-stage algorithm for fully-unsupervised and super-fast TV commercial mining in this paper. The two stages involved in process include: 1) searching for recurring short segments, and 2) assembling these short segments into sets of long and complete commercial sequences. The first stage is achieved by frame hashing. Different from the related studies that depend on brute-force pairwise matching, we propose applying a second-stage hashing algorithm for the recurring segment assemblage, which is the key idea in this paper. A large-scale archive containing a 10-hour and a 1-month stream was used for the experimentation. The algorithm mined commercials from the 1-month stream in less than 50 minutes, which was ten times faster than that of related studies, with a 98.05% sequence-level and 97.39% frame-level accuracy. We demonstrate the performance consistency of the algorithm on both audio and video streams, and investigate the computational cost from both the theoretical and experimental viewpoints.