Deep learning techniques achieve state-of-the-art performance on many computer vision
related tasks, eg large-scale object recognition. In this paper we show that recognition …

In this work, we present the RNN Tree (RNN-T), an adaptive learning framework for skeleton
based human action recognition. Our method categorizes action classes and uses multiple …

Examples of techniques for adaptive object recognition for a target visual domain given a
generic machine learning model are provided. According to one or more embodiments of …

Examples of techniques for interactive generation of labeled data and training instances are
provided. According to one or more embodiments of the present invention, a computer …

Social relation analysis via images is a new research area that has attracted much interest
recently. As social media usage increases, a wide variety of information can be extracted …

Content-based image retrieval (CBIR) is to retrieve images from a database that are similar
to a query image. In CBIR, to compute the similarity between two images, feature vectors are …

Recent years have witnessed the increasing popularity of mobile devices (such as iphone)
due to the convenience that it brings to human lives. On one hand, rich user profiling and …

Examples of techniques for interactive generation of labeled data and training instances are
provided. According to one or more embodiments of the present invention, a computer …

Examples of techniques for adaptive model training are provided. According to one or more
embodiments of the present invention, a computer-implemented method for adaptive model …

High user interaction capability of mobile devices can help improve the accuracy of mobile
visual search systems. At query time, it is possible to capture multiple views of an object from …