A practical spatial re-ranking method for instance search from videos
A practical spatial re-ranking method for instance search from videos
复制标题
DOI：
10.1109/icip.2014.7025608
复制
发表时间：
2014-10
期刊：
影响因子：
--
通讯作者：
Xiaoping Zhou;Cai-Zhi Zhu;Qiang Zhu;S. Satoh;Yu-tang Guo
中科院分区：
文献类型：
--
作者：
Xiaoping Zhou;Cai-Zhi Zhu;Qiang Zhu;S. Satoh;Yu-tang Guo
空间重排序在图像检索中已被证明是成功的。然而，迄今为止，还没有关于空间重新排序的工作被系统地报道，例如从视频中搜索：由于视频由多个帧组成，并且逐帧的空间验证太过禁止，到目前为止，我们缺乏一种有效的空间重新排序方法，该方法被设计用于视频实例搜索的目的。其有效性也尚不清楚。本文提出了一种实用的视频实例搜索的空间重排序方法。我们做了两个贡献，以加快算法：一个是选择最有代表性的图像/帧的空间验证，基于可用的Bag-of-Words表示;另一个是有效地建立试探性的匹配特征对，作为RANSAC算法的输入，通过将特征量化为相同的视觉词作为匹配，从而避免了昂贵的最近邻搜索。这两个修改导致一个数量级的加速而不影响性能。另一个贡献是一个ROI起源的RANSAC方法，它提高了重新排名的性能显着。在TrecVid实例搜索2013数据集上进行了实验，所提出的方法以更快的速度实现了新的最先进的性能。
Spatial re-ranking has proved to be successful in image retrieval. Yet no work on spatial re-ranking has been systematically reported for instance search from videos so far: As videos are composed of multiple frames, and frame-by-frame spatial verification is too prohibitive, till now we lack an efficient spatial re-ranking method designed for the purpose of video instance search. The effectiveness is unclear as well. This paper proposes a practical spatial re-ranking method for video instance search. We make two contributions to speed up the algorithm: One is to select the most representative image/frame for spatial verification, based on the available Bag-of-Words representation; the other is to efficiently build tentative matching feature pairs, which serve as the input of the RANSAC algorithm, by regarding features quantized to the same visual word as matches, thus avoid the costly nearest-neighbor search. These two modifications lead one order of magnitude speedup without compromising the performance. Another contribution is a ROI-originated RANSAC method, which improves the re-ranking performance significantly. Experiments were carried out on the TrecVid Instance Search 2013 dataset, and the new state-of-the-art performance was achieved by the proposed method, at a much faster speed.