The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
User-generated content on online social media (OSM) has several data mining applications, such as extracting useful information during disaster events. Since popular / important content is often re-posted by multiple people on OSM, identifying duplicate content is an important first step in many data mining applications. In this work, we develop a methodology to identify near-duplicate images posted...
In image classification tasks, the image is rarely represented as only a collection of raw pixels. Myriad alternative representations, from Gaussian kernels to bags-of-words to layers of a convolutional neural network, have been proposed both to decrease the dimensionality of the task and, more importantly, to move into a space which better facilitates classification. This work explores several methods...
The disadvantages of BOW (Bag of words model) for image classification include the large amount of data in generating a codebook by clustering, redundant code words that may affect the classification results and so on. The process of BOW for the classification can be improved through the Laplace weights to improved fuzzy C means algorithm, and obtaining codebook with more ability to distinguish between...
We present a no-reference (NR) image quality assessment (IQA) algorithm that is inspired by the representation of visual scenes in the primary visual cortex of the human visual system. Specifically, we use the sparse coding model of the area V1 to construct an overcomplete dictionary for sparsely representing pristine (undistorted) natural images. First, we empirically demonstrate that the distribution...
We present an image classification method which consists of salient region (SR) detection, local feature extraction, and pairwise local observations based Naive Bayes classifier (NBPLO). Different from previous image classification algorithms, we propose a scale, translation, and rotation invariant image classification algorithm. Based on the discriminative pairwise local observations, we develop...
We propose a video graph based human action recognition framework. Given an input video sequence, we extract spatio-temporal local features and construct a video graph to incorporate appearance and motion constraints to reflect the spatio-temporal dependencies among features. them. In particular, we extend a popular dbscan density-based clustering algorithm to form an intuitive video graph. During...
Object recognition is especially challenging when the objects from different categories are visually similar to each other. This paper presents a novel method of group-based sparse coding dictionary learning (GSCDL) to exploit the visual correlation within a group of visually similar object categories for dictionary learning. First, a clustering algorithm is performed to partition the training data...
Labeling data to train visual concept classifiers requires significant human effort. Active learning addresses labeling overhead by selecting a meaningful subset of data, but often these approaches assume that the set of visual concepts is known in advance. Clustering approaches perform bottom-up discovery of concepts, and reduce labeling effort by moving from instance-based to group-based labeling...
We present a novel approach to the design of codebooks in patch-based, bag-of-feature visual scene recognition problems. The Sequential Input Space Carving (SISC) approach we present achieves compact codebooks in a fraction of the computation time needed by the k-means clustering method usually employed in this setting. We demonstrate the performance of the SISC using several recognition tasks including...
We propose a system designed to spot either words or patterns, based on a user made query. Employing a two stage approach, it takes advantage of the descriptive power of the Bag of Visual Words (BOVW) representation and the discriminative power of the proposed Longest Weighted Profile (LWP) algorithm. First, we try to identify the zones of images that share common characteristics with the query as...
In computer vision, semantically accurate segmentation of an object is considered to be a critical problem. The different looking fragments of the same object impose the main challenge of producing a good segmentation. This leads to consider the high-level semantics of an image as well as the low-level visual features which require computationally intensive operations. This demands to optimize the...
Objects in scenes interact with each other in complex ways. A key observation is that these interactions manifest themselves as predictable visual patterns in the image. Discovering and detecting these structured patterns is an important step towards deeper scene understanding. It goes beyond using either individual objects or the scene as a whole as the semantic unit. In this work, we promote "groups...
This paper proposes a hybrid algorithm based on improved LLE and adaptive k-means for visual codebook generation in tourism scene classification. Firstly, we construct the improved LLE algorithm to get lower dimensional and compressed image feature representations. Then we form the adaptive k-means clustering algorithm to generate the visual codebook. Finally, we use the visual codebook histogram...
Image recognition is one of the fundamental problems in multimedia analysis. Typically in the training database, there will be more than one image for each object, however most existing bag-of-features based approaches treat them independently and completely ignore the feature correspondence relationship among them. As a result, features corresponding to the same physical point may be clustered into...
In this paper, we investigate the parameters underpinning our previously presented system for detecting unusual events in surveillance applications [1]. The system identifies anomalous events using an unsupervised data-driven approach. During a training period, typical activities within a surveilled environment are modeled using multi-modal sensor readings. Significant deviations from the established...
The research of object localization is active in the field of visual object category. In this paper, we focus on object localization in a given special category dataset. We propose to exploit the context aware category discovery for object localization without any labeled examples. Firstly, the image is segmented based on a multiple segmentation algorithm. Secondly, these generated regions are clustered...
In this work we present an algorithm for extracting region level annotations from flickr images using a small set of manually labelled regions to guide the selection process. More specifically, we construct a set of flickr images that focuses on a certain concept and apply a novel graph based clustering algorithm on their regions. Then, we select the cluster or clusters that correspond to the examined...
In the 1980s and at the turn of last century, severe global waves of sovereign defaults occurred in less developed countries. To date, the forecasting and monitoring results of debt crises are still at a preliminary stage, while the issue is at present highly topical. This paper explores whether the application of the Self-organizing map (SOM), a neural network-based visualization tool, facilitates...
The method of extracting characteristic parameters of lip according to lip template was presented. A dynamic clustering algorithm to classify the lip-shape based on the criteria of the least square error sum was proposed, and dynamic state sequence that described the lip movement was obtained by the improved ant colony algorithm. The lip-reading dynamic pattern recognition was performed by DTW algorithm...
The bag of visual words model has seen immense success in addressing the problem of image classification. Algorithms using this model generate the codebook of visual words by vector quantizing the features (such as SIFT) of the images to be classified. However, a codebook so formed tends to get biased by the nature of the dataset. In this paper we propose an alternative method to create the codebook...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.