Abstract

Graph-OLAP is an online analytical framework which allows us to obtain various projections of a graph, each of which helps us view the graph along multiple dimensions and multiple levels. Given a series of snapshots of a temporal heterogeneous graph, we aim to find interesting projections of the graph which have anomalous evolutionary behavior. Detecting anomalous projections in a series of such snapshots can be helpful for an analyst to understand the regions of interest from the temporal graph. Identifying such semantically related regions in the graph allows the analyst to derive insights from temporal graphs which enables her in making decisions. While most of the work on temporal outlier detection is performed on nodes, subgraphs and communities, we are the first to propose detection of evolutionary graph cuboid outliers. Further, we perform this detection in a query sensitive manner. Thus, an evolutionary graph cuboid outlier is a projection (or cuboid) of a snapshot of the temporal graph such that it contains an unexpected number of matches for the query with respect to other cuboids both in the same snapshot as well as in the other snapshots. Identifying such outliers is challenging because (1) the number of cuboids per snapshot could be large, and (2) number of snapshots could itself be large. We model the problem by predicting the outlier score for each cuboid in each snapshot. We propose to build subspace ensemble regression models to learn (a) the behavior of a cuboid across different snapshots, and (b) the behavior of all the cuboids in a given snapshot. Experimental results on both synthetic and real datasets show the effectiveness of the proposed algorithm in discovering evolutionary graph cuboid outliers.

Abstract

In this work we propose a novel representation learning model which computes semantic representations for tweets accurately. Our model systematically exploits the chronologically adjacent tweets ('context') from users' Twitter timelines for this task. Further, we make our model user-aware so that it can do well in modeling the target tweet by exploiting the rich knowledge about the user such as the way the user writes the post and also summarizing the topics on which the user writes. We empirically demonstrate that the proposed models outperform the state-of-the-art models in predicting the user profile attributes like spouse, education and job by 19.66%, 2.27% and 2.22% respectively.

Abstract

Current state of the art object recognition architectures achieve impressive performance but are typically specialized for a single depictive style (eg photos only, sketches only). In this paper, we present SwiDeN: our Convolutional Neural Network (CNN) architecture which recognizes objects regardless of how they are visually depicted (line drawing, realistic shaded drawing, photograph etc.). In SwiDeN, we utilize a noveldeep'depictive style-based switching mechanism which appropriately addresses the depiction-specific and depiction-invariant aspects of the problem. We compare SwiDeN with alternative architectures and prior work on a 50-category Photo-Art dataset containing objects depicted in multiple styles. Experimental results show that SwiDeN outperforms other approaches for the depiction-invariant object recognition problem.

Abstract

Freehand sketching is an inherently sequential process. Yet, most approaches for hand-drawn sketch recognition either ignore this sequential aspect or exploit it in an ad-hoc manner. In our work, we propose a recurrent neural network architecture for sketch object recognition which exploits the long-term sequential and structural regularities in stroke data in a scalable manner. Specifically, we introduce a Gated Recurrent Unit based framework which leverages deep sketch features and weighted per-timestep loss to achieve state-of-the-art results on a large database of freehand object sketches across a large number of object categories. The inherently online nature of our framework is especially suited for on-the-fly recognition of objects as they are being drawn. Thus, our framework can enable interesting applications such as camera-equipped robots playing the popular party game Pictionary with human players and generating sparsified yet recognizable sketches of objects.

Abstract

Traditional architectures for solving computer vision problems and the degree of success they enjoyed have been heavily reliant on hand-crafted features. However, of late, deep learning techniques have offered a compelling alternative -- that of automatically learning problem-specific features. With this new paradigm, every problem in computer vision is now being re-examined from a deep learning perspective. Therefore, it has become important to understand what kind of deep networks are suitable for a given problem. Although general surveys of this fast-moving paradigm (i.e. deep-networks) exist, a survey specific to computer vision is missing. We specifically consider one form of deep networks widely used in computer vision - convolutional neural networks (CNNs). We start with "AlexNet'' as our base CNN and then examine the broad variations proposed over time to suit different applications. We hope that our recipe-style survey will serve as a guide, particularly for novice practitioners intending to use deep-learning techniques for computer vision.

Abstract

Automated classification of glaucoma is of interest in early detection and treatment. Existing methods employ featureswhich are either image-based or derived from Optic Disc(OD) and Cup (OC) segmentation. While the latter suffers from segmentation inaccuracies, the image-based features tend to overf it in limited availability of training data. We propose a solution to overcome these issues and present a classification framework that fuses both type of features within a co-training based semi-supervised setting to over-come the paucity of labelled data. A novel set of features is proposed to represent the segmented OD-OC regions. Additionally, features based on Texture of projections and color Bag of Visual Words have been designed to be sensitive to the sector-wise deformations in OD. The proposed method was trained on 386 labelled and 717 unlabelled images. It outperformed existing methods with an accuracy and AUC of73.28%,0.79on a private test set of 696 unseen images and76.77%,0.78when cross-tested on DRISHTI-GS1 dataset

Abstract

A variety of imaging modalities have been used for developing diagnostic aids for glaucoma assessment. Structural imaging modalities such as colour fundus imaging and optical coherence tomography (OCT) have been investigated for automatically estimating key parameters for glaucoma assessment such as cup to disc diameter ratio and thickness of there tinal nerve fibre layer (RNFL). OCT-based angiography or OCTA is a new modality which provides structural and angiographic information about the retinal layers. We present a method for glaucoma detection using OCTA images. Specifically, the capillary density at various layers and thickness of RNFL are estimated and used to classify a given OCTA volume as glaucamatous or not. RNFL thickness is estimated using polynomial fitting to intensity profiles of OCT slices. The capillary density is estimated from the angio flow images using morphological processing to extract the optic nerve head(ONH) and vessel detection in a region of interest define daround the ONH. A system trained on these two features was evaluated on a dataset of 67 eyes (49 normal and 18 glaucomatous) and found to have a sensitivity of 94.44%and specificity of 91.67%. This demonstrates the potential of the new modality for glaucoma assessment.

Abstract

The variations in the intensity scale in Magnetic Resonance Images pose a problem for many tasks and Intensity Standardization (IS) aims to solve this problem. Existing methods generally use landmark values of the image histogram and match it to a standard scale. The landmarks are often chosen to be percentiles from different segmented tissues. We propose a method for IS in which tissue information (via segmentation) is needed during training but not during testing by using landmark propagation. A KL divergence-based technique is employed for identifying volumes from the training set, which are similar to a given non-standardized testing volume. The landmarks from the similar volumes are then propagated to the given test volume. Evaluation of the proposed method on 24 MRI volumes from 3 different scanners shows that the IS results are better than L4 and at par with a method which uses prior segmentation, to get percentile-based land-marks. The proposed method aids speeding up and expanding the scope of IS to volumes with no tissue information

Abstract

Cardiac motion analysis from B-mode ultrasound sequence is a key task in assessing the health of the heart. The paper proposes a new methodology for cardiac motion analysis based on the temporal behaviour of points of interest on the myocardium. We define a new signal called the Temporal Flow Graph(TFG) which depicts the movement of a point of interest over time. It is a graphical representation derived from a flow field and describes the temporal evolution of a point. We prove that TFG for an object undergoing periodic motion is also periodic. This principle can be utilized to derive both global and local information from a given sequence. We demonstrate this for detecting motion irregularities at the sequence, as well as regional levels on real and synthetic data. A coarse localisation of anatomical landmarks such as centres of left/right cavities and valve points is also demonstrated using TFGs.

Abstract

Color fundus photographs of 2252 eyes from1126 subjects were collected from 2 centers: Aravind Eye Hospital,Madurai and Coimbatore, India. The images of 1926 eyes (963 subjects) were used to train an automated image analysis-based system,which was developed to provide a decision on a given fundus image.A total of 163 subjects were clinically examined by 2 ophthalmologists independently and their diagnostic decisions were recorded. The consensus decision was defined to be the clinical reference (gold standard). Fundus images of eyes with disagreement in diagnosis were excluded from the study. The fundus images of the remaining 314eyes (157 subjects) were presented to 4 graders and their diagnostic decisions on the same were collected. The performance of the system was evaluated on the 314 images, using the reference standard. The sensitivity and specificity of the system and 4 independent graders were determined against the clinical reference standard