学习多类型对象和任务的深度表示
Learning deep representation of multityped objects and tasks
摘要:
我们引入了一个深度的多任务架构,以集成多类型的多模态对象表示。这种多类型的阐述比多模态表征更抽象,但更机器友好,因此建模更精确。例如,图像可以由多个视觉视图来描述,这些视觉视图可以是词袋(计数)或颜色/纹理直方图(实值)的形式。同时,图像可能有几个社交标签,这些标签最好使用稀疏二进制向量来描述。我们的深度模型将多个类型特定的特征作为输入,缩小跨模态语义差距,学习跨类型相关性,并产生高级同质表示。同时,该模型支持异构类型的任务。我们展示了两个应用程序的模型的能力:社会图像检索和多概念预测。深层架构产生更紧凑的表示,自然地集成多视图和多模态,利用更好的辅助信息,最重要的是,与基线相比具有竞争力。
英文摘要:
We introduce a deep multitask architecture to integrate multityped representations of multimodal objects. This multitype exposition is less abstract than the multimodal characterization, but more machine-friendly, and thus is more precise to model. For example, an image can be described by multiple visual views, which can be in the forms of bag-of-words (counts) or color/texture histograms (real-valued). At the same time, the image may have several social tags, which are best described using a sparse binary vector. Our deep model takes as input multiple type-specific features, narrows the cross-modality semantic gaps, learns cross-type correlation, and produces a high-level homogeneous representation. At the same time, the model supports heterogeneously typed tasks. We demonstrate the capacity of the model on two applications: social image retrieval and multiple concept prediction. The deep architecture produces more compact representation, naturally integrates multiviews and multimodalities, exploits better side information, and most importantly, performs competitively against baselines.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。