Abstract: Most works on image retrieval from text queries have addressed the problem of retrieving semantically relevant images. However, the ability to assess the aesthetic quality of an image is an increasingly important differentiating factor for search engines. In this work, given a semantic query, we are interested in retrieving images which are semantically relevant and score highly in terms of aesthetics/visual quality. We use large-margin classifiers and rankers to learn statistical models capable of ordering images based on the aesthetic and semantic information. In particular, we compare two families of approaches: while the first one attempts to learn a single ranker which takes into account both semantic and aesthetic information, the second one learns separate semantic and aesthetic models. We carry out a quantitative and qualitative evaluation on a recently-published large-scale dataset and we show that the second family of techniques significantly outperforms the first one.

Abstract: This paper proposes a new version of Particle Filter, called Articulated Particle Filter – ArPF -, which has been specifically designed for an efficient sampling of hierarchical spaces, generated by articulated objects. Our approach decomposes the articulated motion into layers for efficiency purposes, making use of a careful modeling of the diffusion noise along with its propagation through the articulations. This produces an increase of accuracy and prevent for divergences. The algorithm is tested on hand tracking due to its complex hierarchical articulated nature. With this purpose, a new dataset generation tool for quantitative evaluation is also presented in this paper.

Abstract: This paper addresses the problem of video surveillance by mobile cameras. We present a method that allows online change detection in night-time outdoor surveillance. Because of the camera movement, background frames are not available and must be “localized” in former sequences and registered with the current frames. To this end, we propose a Frame Localization And Registration (FLAR) approach that solves the problem efficiently. Frames of former sequences define a database which is queried by current frames in turn. To quickly retrieve nearest neighbors, database is indexed through a visual dictionary method based on the SURF descriptor. Furthermore, the frame localization is benefited by a temporal filter that exploits the temporal coherence of videos. Next, the recently proposed ECC alignment scheme is used to spatially register the synchronized frames. Finally, change detection methods apply to aligned frames in order to mark suspicious areas. Experiments with real night sequences recorded by in-vehicle cameras demonstrate the performance of the proposed method and verify its efficiency and effectiveness against other methods.

Abstract: The pairwise classification approach tends to perform better than other well-known approaches when dealing with multiclass classification problems. In the pairwise approach, however, the nuisance votes of many irrelevant classifiers may result in a wrong prediction class. To overcome this problem, a novel method, Local Crossing Off (LCO), is presented and evaluated in this paper. The proposed LCO system takes advantage of nearest neighbor classification algorithm because of its simplicity and speed, as well as the strength of other two powerful binary classifiers to discriminate between two classes. This paper provides a set of experimental results on 20 datasets using two base learners: Neural Networks and Support Vector Machines. The results show that the proposed technique not only achieves better classification accuracy, but also is computationally more efficient for tackling classification problems which have a relatively large number of target classes.

Abstract: Unconstrained handwritten text recognition systems maximize the combination of two separate probability scores. The first one is the observation probability that indicates how well the returned word sequence matches the input image. The second score is the probability that reflects how likely a word sequence is according to a language model. Current state-of-the-art recognition systems use statistical language models in form of bigram word probabilities. This paper proposes to model the target language by means of a recurrent neural network with long-short term memory cells. Because the network is recurrent, the considered context is not limited to a fixed size especially as the memory cells are designed to deal with long-term dependencies. In a set of experiments conducted on the IAM off-line database we show the superiority of the proposed language model over statistical n-gram models.

Abstract: In this paper we present the importance of including the user in the loop in a handwritten word spotting framework. Several off-the-shelf query fusion and relevance feedback strategies have been tested in the handwritten word spotting context. The increase in terms of precision when the user is included in the loop is assessed using two datasets of historical handwritten documents and a baseline word spotting approach based on a bag-of-visual-words model.

Abstract: Mode detection in online handwritten documents refers to the process of distinguishing different types of contents, such as text, formulas, diagrams, or tables, one from another. In this paper a new approach to mode detection is proposed that uses bidirectional long-short term memory (BLSTM) neural networks. The BLSTM neural network is a novel type of recursive neural network that has been successfully applied in speech and handwriting recognition. In this paper we show that it has the potential to significantly outperform traditional methods for mode detection, which are usually based on stroke classification. As a further advantage over previous approaches, the proposed system is trainable and does not rely on user-defined heuristics. Moreover, it can be easily adapted to new or additional types of modes by just providing the system with new training data.