Learning to Identify TV News Monologues by Style and Context
Learning to Identify TV News Monologues by Style and Context
复制标题
学习根据风格和背景识别电视新闻独白
DOI：
--
复制
发表时间：
2003
期刊：
影响因子：
--
通讯作者：
Alexander Hauptmann
中科院分区：
文献类型：
--
作者：
Cees G. M. Snoek;Alexander Hauptmann
我们主要研究从与广播视频文档相关联的多媒体数据中学习语义的问题。在本文中，我们提出了基于样式和上下文检测器，结合统计分类器集成从多模源中学习语义概念。作为案例研究，我们给出了检测新闻主题独白概念的方法。在2003年文本检索会议基准视频轨道的26份提交材料中，这一方法的平均精确度表现最佳。针对单个检测器的贡献、集合大小和排序机制进行了实验。研究发现，探测器的组合对NAL结果是决定性的，尽管一些探测器在隔离时可能看起来毫无用处。此外，通过使用概率排序，结合大型分类器集成，结果可以得到进一步改进。
We focus on the problem of learning semantics from multimedia data associated with broadcast video documents. In this paper we propose to learn semantic concepts from multimodal sources based on style and context detectors, in combination with statistical classier ensembles. As a case study we present our method for detecting the concept of news subject monologues. This approach had the best average precision performance amongst 26 submissions in the 2003 video track of the Text Retrieval Conference benchmark. Experiments were conducted with respect to individual detector contribution, ensemble size, and ranking mechanism. It was found that the combination of detectors is decisive for the nal result, although some detectors might appear useless in isolation. Moreover, by using a probabilistic ranking, in combination with a large classier ensemble, results can be improved even further.