… to justify the need for complex models and subsequent training. In this work, we introduce
a new baseline technique for image annotation that treats annotation as a retrieval problem. …

… a post-processing step; our model relies on LDA to infer meaningful topics that capture the
cooccurrence of visual features and words; (c) beyond image annotation, we show how the …

… the need for complex models and subsequent training. In this work, we introduce a new and
simple baseline technique for image annotation that treats annotation as a retrieval problem. …

… automatic image annotation problem and its application to multi-modal image retrieval. The
contribution of our work is three-fold. (1) We propose a probabilistic semantic model in which …

… We propose simple and effective models for the image annotation that make use of … an
image and word embedding vectors to represent their associated tags. Our first set of models is …

… semantic gap is through the automatic image annotation (AIA) which extracts … latest
development in image retrieval and provide a comprehensive survey on automatic image annotation. …

… annotation term to predict whether a test image is relevant. We assess the image annotation
… a separate classifier for each annotation term to predict its relevance for an image. For the …

… image features using clustering. Given a training set of images with annotations, we show
that probabilistic models … word given the blobs in an image. This may be used to automatically …

… model (SVM-DMBRM) combining a generative and a discriminative model for the image
annotation task… as the discriminative model and a Discrete Multiple Bernoulli Relevance Model (…

… Firstly, we present a new image annotation method based on manifold ranking algorithm, in
which visual and textual information are well integrated. Moreover, our graph-based method …