With the exponential surge in diverse multi-modal data, traditional uni-modal retrieval
methods struggle to meet the needs of users seeking access to data across various …

One of the most challenging machine learning problems is a particular case of data
classification in which classes are hierarchically structured and objects can be assigned to …

Image-text retrieval of natural scenes has been a popular research topic. Since image and
text are heterogeneous cross-modal data, one of the key challenges is how to learn …

Learning semantic correspondence between image and text is significant as it bridges the
semantic gap between vision and language. The key challenge is to accurately find and …

Image-text retrieval task is a challenging task. It aims to measure the visual-semantic
correspondence between an image and a text caption. This is tough mainly because the …

Image and sentence matching has drawn much attention recently, but due to the lack of
sufficient pairwise data for training, most previous methods still cannot well associate those …

Abstract a using an embedding vector of an instance from modality b. Such an adaptation is
designed to filter and enhance important information across internal features, allowing for …

Learning an effective similarity measure between image representations is key to the
success of recent advances in visual search tasks (eg verification or zero-shot learning) …

Cross-modal image-text retrieval has been a long-standing challenge in the multimedia
community. Existing methods explore various complicated embedding spaces to assess the …

This paper proposes a framework for training language-invariant cross-modal retrieval
models. We also introduce a novel character-based word-embedding approach, allowing …