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.
Re-identification of people in surveillance footage must cope with drastic variations in color, background, viewing angle and a persons pose. Supervised techniques are often the most effective, but require extensive annotation which is infeasible for large camera networks. Unlike previous supervised learning approaches that require hundreds of annotated subjects, we learn a metric using a novel one-shot...
The 3D shapes of faces are well known to be discriminative. Yet despite this, they are rarely used for face recognition and always under controlled viewing conditions. We claim that this is a symptom of a serious but often overlooked problem with existing methods for single view 3D face reconstruction: when applied in the wild, their 3D estimates are either unstable and change for different photos...
In many real-world scenarios, labeled data for a specific machine learning task is costly to obtain. Semi-supervised training methods make use of abundantly available unlabeled data and a smaller number of labeled examples. We propose a new framework for semi-supervised training of deep neural networks inspired by learning in humans. Associations are made from embeddings of labeled samples to those...
Novelty detection, which aims to determine whether a given data belongs to any category of training data or not, is considered to be an important and challenging problem in areas of Pattern Recognition, Machine Learning, etc. Recently, kernel null space method (KNDA) was reported to have state-of-the-art performance in novelty detection. However, KNDA is hard to scale up because of its high computational...
We propose to jointly learn a Discriminative Bayesian dictionary along a linear classifier using coupled Beta-Bernoulli Processes. Our representation model uses separate base measures for the dictionary and the classifier, but associates them to the class-specific training data using the same Bernoulli distributions. The Bernoulli distributions control the frequency with which the factors (e.g. dictionary...
In order to improve booking tickets experience of the users of Railway Online Ticketing System and ensure the system normally running, Railway Online Ticketing System's users abnormality booking the tickets detection model based on the traditional K-Means and FP-Growth algorithm is proposed. Firstly, preliminary filter user features by the Random Forest Algorithm based on Spark MLlib to identify the...
We study the problem of answering questions about images in the harder setting, where the test questions and corresponding images contain novel objects, which were not queried about in the training data. Such setting is inevitable in real world–owing to the heavy tailed distribution of the visual categories, there would be some objects which would not be annotated in the train set. We show...
A major open problem on the road to artificial intelligence is the development of incrementally learning systems that learn about more and more concepts over time from a stream of data. In this work, we introduce a new training strategy, iCaRL, that allows learning in such a class-incremental way: only the training data for a small number of classes has to be present at the same time and new classes...
We propose a novel data-driven approach for automatically detecting and completing gaps in line drawings with a Convolutional Neural Network. In the case of existing inpainting approaches for natural images, masks indicating the missing regions are generally required as input. Here, we show that line drawings have enough structures that can be learned by the CNN to allow automatic detection and completion...
We present an approach that uses a multi-camera system to train fine-grained detectors for keypoints that are prone to occlusion, such as the joints of a hand. We call this procedure multiview bootstrapping: first, an initial keypoint detector is used to produce noisy labels in multiple views of the hand. The noisy detections are then triangulated in 3D using multiview geometry or marked as outliers...
Deep neural networks require a large amount of labeled training data during supervised learning. However, collecting and labeling so much data might be infeasible in many cases. In this paper, we introduce a deep transfer learning scheme, called selective joint fine-tuning, for improving the performance of deep learning tasks with insufficient training data. In this scheme, a target learning task...
We present a new Cascaded Shape Regression (CSR) architecture, namely Dynamic Attention-Controlled CSR (DAC-CSR), for robust facial landmark detection on unconstrained faces. Our DAC-CSR divides facial landmark detection into three cascaded sub-tasks: face bounding box refinement, general CSR and attention-controlled CSR. The first two stages refine initial face bounding boxes and output intermediate...
This paper proposes a hybrid negative correlation learning in which each individual neural network in an neural network ensemble would either learn a data point by negative correlation learning or learn to be different to the neural network ensemble. The implementation is through randomly splitting the training set into two subsets for each individual neural network in learning. On one subset of the...
AdaBoost is a popular ensemble method utilized in pattern recognition problems that are considered tough. Besides being a robust technique it does suffer from few limitations viz. size of training data and presence of noise in training data. In this context, we proposed a novel technique called Perspective Based Model (PBM) for ensemble creation in case of multispectral data analysis. In the present...
Area Sampling Frames are used for surveys including crop acreage and yield, forests, and natural resource inventories and are the foundation of the statistical program of the USDA National Agricultural Statistics Service (NASS) and many statistical survey programs around the world. An automated area frame stratification method was recently implemented into NASS operations, which is based on the objective...
The automatic generation of semantic maps from remotely sensed imagery by supervised classifiers has seen much effort in the last decades. The major focus has been on the improvement of the interplay between feature operators and classifiers, while experimental design and test data generation has been mostly neglected. This paper shows that sampling strategies applied to partition the available reference...
Palm vein recognition is developing biometric identification technology. It can be used in physical security and information security for selective control of access to a place or resource. A palm vein recognition has been gaining research interest from last few years because it use physiological intrinsic that uniqueness, stability, not easily spoofed and damaged and have live body identification...
Ship category recognition is one of the remote sensing applications that requires designing accurate image representation and classification models. Training these models is usually a data hungry process, that requires a lot of labeled data which are usually scarce and expensive. As unlabeled data are more abundant and relatively cheaper, transductive methods exploiting these data are highly preferred...
This paper addresses the band selection of a hyperspectral image. Considering a binary classification, we devise a method to choose the more discriminating bands for the separation of the two classes involved, by using a simple algorithm: single-layer neural network. After that, the most discriminative bands are selected, and the resulting reduced data set is used in a more powerful classifier, namely,...
Signature-based detectors for hyperspectral target detection rely on knowing the specific target signature in advance. However, target signatures are often difficult or impossible to obtain. Furthermore, common methods for obtaining target signatures, such as from laboratory measurements or manual selection from an image scene, usually do not capture the discriminative features of target class. In...
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.