TagBook: A Semantic Video Representation Without Supervision for Event Detection
TagBook: A Semantic Video Representation Without Supervision for Event Detection
复制标题
TagBook：无监督事件检测的语义视频表示
DOI：
10.1109/tmm.2016.2559947
复制
发表时间：
2016-07-01
影响因子：
7.3
通讯作者：
Snoek, Cees G. M.
中科院分区：
文献类型：
--
作者：
Mazloom, Masoud;Li, Xirong;Snoek, Cees G. M.
我们考虑的问题，在视频中的事件检测的情况下，只有几个，甚至零，可用于训练的例子。对于这种具有挑战性的设置，文献中的主流解决方案依赖于从数千个预先训练的概念检测器获得的语义视频表示。不同于现有的工作，我们提出了一个新的语义视频表示，是基于免费提供的社会标记的视频，而不需要训练任何中间的概念检测器。我们介绍了一个简单的算法，传播标签从视频的最近的邻居，类似的精神，用于图像检索，但重新设计它的视频事件检测，包括视频源集细化和不同的视频标签分配。我们称我们的方法为TagBook，并在TRECVID 2013年和2014年多媒体事件检测数据集和哥伦比亚消费者视频数据集上研究其构造、重复性和检测性能。尽管其简单的性质，提出的TagBook视频表示是非常有效的少例和零例事件检测，甚至优于最近的国家的最先进的替代品建立在监督表示。
We consider the problem of event detection in video for scenarios where only a few, or even zero, examples are available for training. For this challenging setting, the prevailing solutions in the literature rely on a semantic video representation obtained from thousands of pretrained concept detectors. Different from existing work, we propose a new semantic video representation that is based on freely available social tagged videos only, without the need for training any intermediate concept detectors. We introduce a simple algorithm that propagates tags from a video's nearest neighbors, similar in spirit to the ones used for image retrieval, but redesign it for video event detection by including video source set refinement and varying the video tag assignment. We call our approach TagBook and study its construction, descriptiveness, and detection performance on the TRECVID 2013 and 2014 multimedia event detection datasets and the Columbia Consumer Video dataset. Despite its simple nature, the proposed TagBook video representation is remarkably effective for few-example and zero-example event detection, even outperforming very recent state-of-the-art alternatives building on supervised representations.