Towards Compact Topical Descriptors | |
Ji, Rongrong ; Duan, Ling-Yu ; Chen, Jie ; Gao, Wen | |
2012 | |
英文摘要 | We introduce a Compact Topical Descriptor to learn a compact yet discriminative image signature from the reference image corpus. This descriptor is deployed over the well used bag-of-words image histogram, with two merits over the traditional topical features: First, we propose to directly control the topical sparsity to achieve the descriptor compactness. Second, we ensure the descriptor discriminability by minimizing the bag-of-words reconstruction errors during the topical histogram encoding. To this end, we have a generative viewpoint of the topical feature extraction, which is estimated as a sparse MAP estimation over the original bag-of-words. We learn such estimation by a bi-convex optimization, iterating between both hierarchical sparse coding from words to topical histograms and dictionary learning of the corresponding word-to-topic transform. Especially, supervised labels such as image ranking list can be also incorporated into our descriptor learning paradigm. We quantize our performance in both ImageNet10K and NUS-WIDE, with comparisons to bag-of-words, LDA, miniBoF, and Aggregated Local Descriptors. In practice, we also implement our descriptor for a low bit rate mobile visual search application, i.e. sending compact descriptors instead of the image to reduce the query delivery latency. Our descriptor has significantly outperformed the state-of-the-art compact descriptors by quantitative evaluations over 10 million reference images.; Computer Science, Artificial Intelligence; Computer Science, Interdisciplinary Applications; Engineering, Electrical & Electronic; EI; CPCI-S(ISTP); 5 |
语种 | 英语 |
DOI标识 | 10.1109/CVPR.2012.6248020 |
内容类型 | 其他 |
源URL | [http://ir.pku.edu.cn/handle/20.500.11897/406019] |
专题 | 信息科学技术学院 |
推荐引用方式 GB/T 7714 | Ji, Rongrong,Duan, Ling-Yu,Chen, Jie,et al. Towards Compact Topical Descriptors. 2012-01-01. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论