VisualRank: Applying PageRank to Large-Scale Image Search
VisualRank: Applying PageRank to Large-Scale Image Search
复制标题
DOI：
10.1109/tpami.2008.121
复制
发表时间：
2008-11
影响因子：
23.6
通讯作者：
Yushi Jing;S. Baluja
中科院分区：
文献类型：
--
作者：
Yushi Jing;S. Baluja
由于理解和处理文本的相对轻松，商业图像搜索系统通常依赖于与文本搜索几乎没有区别的技术。最近，学术研究表明，采用基于图像的功能提供在此过程中使用的替代信号或其他信号的有效性。但是，尚不确定此类技术是否会推广到大量流行的Web查询以及搜索质量的潜在改进是否保证额外的计算成本。在这项工作中，我们将图像级问题投入到在推断的视觉相似性图上识别“权威”节点的任务，并建议VisualRank分析图像之间的视觉链接结构。被认为是“权威”的图像被选为那些很好地回答图像征服的图像。为了了解实际系统中这种方法的性能，我们根据为2,000个最受欢迎的产品查询检索图像的任务进行了一系列大规模实验。与最新的Google图像搜索结果相比，我们的实验结果在用户满意度和相关性方面显示出显着改善。保持适中的计算成本对于确保可以在实践中使用此过程至关重要。我们描述了使该系统在商业搜索引擎中进行大规模部署所需的技术。
Because of the relative ease in understanding and processing text, commercial image-search systems often rely on techniques that are largely indistinguishable from text search. Recently, academic studies have demonstrated the effectiveness of employing image-based features to provide either alternative or additional signals to use in this process. However, it remains uncertain whether such techniques will generalize to a large number of popular Web queries and whether the potential improvement to search quality warrants the additional computational cost. In this work, we cast the image-ranking problem into the task of identifying "authority" nodes on an inferred visual similarity graph and propose VisualRank to analyze the visual link structures among images. The images found to be "authorities" are chosen as those that answer the image-queries well. To understand the performance of such an approach in a real system, we conducted a series of large-scale experiments based on the task of retrieving images for 2,000 of the most popular products queries. Our experimental results show significant improvement, in terms of user satisfaction and relevancy, in comparison to the most recent Google image search results. Maintaining modest computational cost is vital to ensuring that this procedure can be used in practice; we describe the techniques required to make this system practical for large-scale deployment in commercial search engines.