Along with the explosive growth of multimedia data, automatic multimedia tagging has
attracted great interest of various research communities, such as computer vision …

Object class detection, also known as category-level object detection, has become one of
the most focused areas in computer vision in the new century. This article attempts to …

Convolutional networks trained on large supervised datasets produce visual features which
form the basis for the state-of-the-art in many computer-vision problems. Further …

We present an approach to utilize large amounts of web data for learning CNNs. Specifically
inspired by curriculum learning, we present a two-step approach for CNN training. First, we …

This paper investigates the problem of modeling Internet images and associated text or tags
for tasks such as image-to-image search, tag-to-image search, and image-to-tag search …

Due to the popularity of social media websites, extensive research efforts have been
dedicated to tag-based social image search. Both visual information and tags have been …

We consider a special type of multi-label learning where class assignments of training
examples are incomplete. As an example, an instance whose true class assignment is (c 1, c …

This paper proposes a paradigm of uncertainty injection for training deep learning model to
solve robust optimization problems. The majority of existing studies on deep learning focus …

Semantic indexing, or assigning semantic tags to video samples, is a key component for
content-based access to video documents and collections. The Semantic Indexing task has …

Learning sparse representation of high-dimensional data is a state-of-the-art method for
modeling data. Matrix factorization-based techniques, such as nonnegative matrix …