Classic query optimization techniques, including predicate pushdown, are of limited use for
machine learning inference queries, because the user-defined functions (UDFs) which …

In this paper, we propose a deep convolutional neural network (DCNN) architecture that
addresses the problem of video/image concept annotation by exploiting concept relations at …

Hashing-based fast nearest neighbor search technique has attracted great attention in both
research and industry areas recently. Many existing hashing approaches encode data with …

In many applications, the data may be high dimensional, represented by multiple features,
and associated with more than one labels. Embedding learning is an effective strategy for …

A household robot usually works in a complex working environment, where it will
continuously see new objects and encounter new concepts in its lifetime. Therefore, being …

In a world where taking photos has become a daily behavior to most people, it is deemed
that a photo sharing service has the strong potential to recommend desirable sightseeing …

Videos are dominant on the Internet. Current systems to process large-scale videos are
suboptimal due to the following reasons:(1) machine learning modules such as feature …

Tagged Web images provide an abundance of labeled training examples for visual concept
learning. However, the performance of automatic training data selection is susceptible to …

Modern newsroom tools offer advanced functionality for automatic and semi-automatic
content collection from the web and social media sources to accompany news stories …

Artificial intelligence has become the topic of the current and next decade. Numerous AI-
related applications in computer vision, natural language processing and audio are …