Compactly representing visual information plays a fundamental role in optimizing the
ultimate utility of myriad visual data-centered applications. Numerous approaches have …

We propose an empirical study to see whether learning with convolutional neural networks
(CNNs) on entropy coded data is possible. First, we define spatial and semantic closeness …

Images on the Internet are usually in the form of compressed bitstream to save storage. To
fulfill content-based image retrieval (CBIR), image features are also required to be stored in …

Region-based image retrieval has been proven to be effective in finding relevant images. In
this paper, we propose a cuboid image segmentation method which results in rectangle …

Images in JPEG compressed domain have a widespread use and computationally efficient
retrieval of those images is of prime concern. In this paper, a content-based image retrieval …

Within the emerging area of goal-oriented communications, this paper introduces a novel
end-to-end transmission scheme dedicated to learning over a noisy channel, under the …

The vast majority of images are stored in compressed JPEG format. When performing
content-based image retrieval, faster feature extraction is possible when calculating them …

Fast content access and content based retrieval of images are among the common web and
signal processing applications; on the other hand, JPEG is the dominant format for image …

A secure identification scheme for JPEG images is proposed in this paper. The aim is to
robustly identify JPEG images which are generated from the same original image under …

Learning on entropy coded data has many benefits. First, it avoids decoding, but also it
allows one to process compact data. However, this type of learning has been overlooked …