期刊
ACM COMPUTING SURVEYS
卷 46, 期 3, 页码 -出版社
ASSOC COMPUTING MACHINERY
DOI: 10.1145/2536798
关键词
Algorithms; Experimentation; Human Factors; Multimedia information retrieval; visual search; search re-ranking; survey
资金
- ARO [W911NF-12-1-0057]
- NSF [IIS 1052851]
- UTSA START-R Research Award
- National Science Foundation of China (NSFC) [61128007]
The explosive growth and widespread accessibility of community-contributed media content on the Internet have led to a surge of research activity inmultimedia search. Approaches that apply text search techniques for multimedia search have achieved limited success as they entirely ignore visual content as a ranking signal. Multimedia search reranking, which reorders visual documents based on multimodal cues to improve initial text-only searches, has received increasing attention in recent years. Such a problem is challenging because the initial search results often have a great deal of noise. Discovering knowledge or visual patterns from such a noisy ranked list to guide the reranking process is difficult. Numerous techniques have been developed for visual search re-ranking. The purpose of this paper is to categorize and evaluate these algorithms. We also discuss relevant issues such as data collection, evaluation metrics, and benchmarking. We conclude with several promising directions for future research.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据