Efficient Clothing Retrieval with Semantic-Preserving Visual Phrases
Efficient Clothing Retrieval with Semantic-Preserving Visual Phrases
复制标题
DOI：
10.1007/978-3-642-37444-9_33
复制
发表时间：
2012-11
期刊：
影响因子：
--
通讯作者：
Jianlong Fu;Jinqiao Wang;Zechao Li;Min Xu;Hanqing Lu
中科院分区：
文献类型：
--
作者：
Jianlong Fu;Jinqiao Wang;Zechao Li;Min Xu;Hanqing Lu
在本文中，我们解决了基于语义保持视觉短语（SPVP）的大规模跨场景服装检索问题。由于人体部位是服装检测和分割的重要线索，我们首先检测人体部位作为语义上下文，并通过稀疏背景重建来细化人体部位区域。然后，在视觉词袋（BOW）框架下将语义部分编码到词汇树中，并通过SPVP利用视觉词在不同人体部位之间的语境约束。并将SPVP集成到倒排索引结构中，加快了检索速度。在服装数据集上的实验和比较表明，与BOW模型相比，SPVP显著增强了局部特征的判别能力，但内存使用或运行时消耗略有增加。因此，这种方法优于最先进的方法和两个服装搜索引擎。
In this paper, we address the problem of large scale cross-scenario clothing retrieval with semantic-preserving visual phrases (SPVP). Since the human parts are important cues for clothing detection and segmentation, we firstly detect human parts as the semantic context, and refine the regions of human parts with sparse background reconstruction. Then, the semantic parts are encoded into the vocabulary tree under the bag-of-visual-word (BOW) framework, and the contextual constraint of visual words among different human parts is exploited through the SPVP. Moreover, the SPVP is integrated into the inverted index structure for accelerating the retrieval process. Experiments and comparisons on our clothing dataset indicate that the SPVP significantly enhances the discriminative power of local features with a slight increase of memory usage or runtime consumption compared to the BOW model. Therefore, the approach is superior to both the state-of-the-art approach and two clothing search engines.