Measuring and Predicting Tag Importance for Image Retrieval.
IEEE Transactions on Pattern Analysis and Machine Intelligence(2017)
摘要
Textual data such as tags, sentence descriptions are combined with visual cues to reduce the semantic gap for image retrieval applications in today's Multimodal Image Retrieval (MIR) systems. However, all tags are treated as equally important in these systems, which may result in misalignment between visual and textual modalities during MIR training. This will further lead to degenerated retrieval...
更多查看译文
关键词
Visualization,Semantics,Image retrieval,Predictive models,Visual databases,Training,Learning systems
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络