To address this problem, we propose Circulant Binary Embedding (CBE) which generates binary codes by projecting the data with a circulant matrix.
In addition, we propose an online clustering method based on binary k-means that is capable of clustering large photo stream on a single machine, and show applications to spam detection and trending photo discovery.
In this paper, we tackle this model storage issue by investigating information theoretical vector quantization methods for compressing the parameters of CNNs.
Deep convolutional neural networks (CNN) have shown their promise as a universal representation for recognition.
Multilabel image annotation is one of the most important challenges in computer vision with many real-world applications.
Recent advances in visual recognition indicate that to achieve good retrieval and classification accuracy on largescale datasets like ImageNet, extremely high-dimensional visual descriptors, e. g., Fisher Vectors, are needed.
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 (image annotation).
Such data typically arises in a large number of vision and text applications where counts or frequencies are used as features.