Compressed Domain Image Classification Using a Dynamic-Rate Neural Network

Semantic-Based Image Retrial in the VQ Compressed Domain using Image Annotation Statistical Models

Image Classification in the Compressed Domain

For content-based image classification and retrieval applications, the adoption of compressed domain features is due more to the improvement of processing efficiencies than the enhancement of content characterization accuracies. To address the second issue in addition to the first, we propose to modify the compressed domain features such that their content characterization capabilities can be i...

Sample-oriented Domain Adaptation for Image Classification

Image processing is a method to perform some operations on an image, in order to get an enhanced image or to extract some useful information from it. The conventional image processing algorithms cannot perform well in scenarios where the training images (source domain) that are used to learn the model have a different distribution with test images (target domain). Also, many real world applicat...

Image Classification using Convolutional Neural Network

Convolutional Neural Networks (CNNs) have been established as a powerful class of models for image recognition problems. Inspired by a blog post [1], we tried to predict the probability of an image getting a high number of likes on Instagram. We modified a pre-trained AlexNet ImageNet CNN model using Caffe on a new dataset of Instagram images with hashtag ‘me’ to predict the likability of photo...

Compressed-Sampling-Based Image Saliency Detection in the Wavelet Domain

When watching natural scenes, an overwhelming amount of information is delivered to the Human Visual System (HVS). The optic nerve is estimated to receive around 108 bits of information a second. This large amount of information can’t be processed right away through our neural system. Visual attention mechanism enables HVS to spend neural resources efficiently, only on the selected parts of the...