Learn More
We study large-scale image classification methods that can incorporate new classes and training images continuously over time at negligible cost. To this end, we consider two distance-based classifiers, the k-nearest neighbor (k-NN) and nearest class mean (NCM) classifiers, and introduce a new metric learning approach for the latter. We also introduce an(More)
1 Motivation Real-life data sets are evolving over time: • new images or items are added every second • new labels, tags and products are incorporated over time Need to index, retrieve, search and categorize these items Therefore, we are interested in methods for large scale visual classification where we can add new images and new classes at near-zero cost(More)
Several state-of-the-art Generic Visual Categorization (GVC) systems are built around a vocabulary of visual terms and characterize images with one histogram of visual word counts. We propose a novel and practical approach to GVC based on a universal vocabulary , which describes the content of all the considered classes of images, and class vocabularies(More)
In this paper, we automatically assess the aesthetic properties of images. In the past, this problem has been addressed by hand-crafting features which would correlate with best photographic practices (e.g. “Does this image respect the rule of thirds?”) or with photographic techniques (e.g. “Is this image a macro?”). We depart(More)
We propose a simple approach to semantic image segmentation. Our system scores low-level patches according to their class relevance, propagates these posterior probabilities to pixels and uses low-level segmentation to guide the semantic segmentation. The two main contributions of this paper are as follows. First, for the patch scoring, we describe each(More)
We propose a novel framework for visual saliency detection based on a simple principle: images sharing their global visual appearances are likely to share similar salience. Assuming that an annotated image database is available, we first retrieve the most similar images to the target image; secondly, we build a simple classifier and we use it to generate(More)
Digital watermarks have been proposed as a method for discouraging illicit copying and distribution of copyrighted material. This paper describes a method for the secure and robust copyright protection of digital images. We present an approach for embedding a digital watermark into an image using the fast Fourier transform. To this watermark is added a(More)
This paper deals with the analysis of the uncertainty of the fundamental matrix. The basic idea is to compute the fundamental matrix and its uncertainty at the same time. We give two diierent methods. The rst one is a statistical approach. As in all statistical methods the precision of the results depends on the number of analyzed samples. This means that(More)
This paper proposes a new approach for digital watermarking and secure copyright protection of videos, the principal aim being to discourage illicit copying and distribution of copyrighted material. The method presented here is based on the discrete Fourier transform (DFT) of three dimensional chunks of video scene, in contrast with previous works on video(More)
We consider the problem of semantic segmentation, i.e. assigning each pixel in an image to a set of pre-defined semantic object categories. State-of-the-art semantic segmentation algorithms typically consist of three components: a local appearance model, a local consistency model and a global consistency model. These three components are generally(More)