Domain-Specific Priors and Meta Learning for Few-Shot First-Person Action Recognition.

The lack of large-scale real datasets with annotations makes transfer learning a necessity for video activity understanding. We aim to develop an effective method for few-shot transfer learning for first-person action classification. We leverage independently trained local visual cues to learn representations that can be transferred from a source domain, which provides primitive action labels, to a different target domain - using only a handful of examples. Visual cues we employ include object-object interactions, hand grasps and motion within regions that are a function of hand locations. We employ a framework based on meta-learning to extract the distinctive and domain invariant components of the deployed visual cues. This enables transfer of action classification models across public datasets captured with diverse scene and action configurations. We present comparative results of our transfer learning methodology and report superior results over state-of-the-art action classification approaches for both inter-class and inter-dataset transfer.

Gastrointestinal duplication cysts: what a radiologist needs to know.

Gastrointestinal tract duplication cysts are rare congenital malformations which can be diagnosed as early as the prenatal period but are frequently found in infancy or incidentally in adulthood. They can be seen throughout the alimentary tract with the most common involving the distal ileum and second most common the esophagus. Many duplication cysts are asymptomatic and thus discovered as an incidental imaging finding, though they can also be symptomatic with an array of clinical presentations dependent largely on their location. The vast majority of duplication cysts are benign; however, there are rare instances of malignant transformation reported. The aim of this review is to show how multimodality imaging can help in the diagnosis of duplication cysts at various anatomical locations. Duplication cyst can become symptomatic and in rare cases undergo malignant transformation; therefore, they are typically managed with surgical excision, particularly if found prenatally or during infancy. Given the diversity of anatomic locations, multiple differential diagnoses, and the need for surgical intervention, it is valuable to comprehend the role of multimodality imaging role in diagnosing duplication cysts.

Post-traumatic intrathoracic splenosis and role of Tc-99m Sulfur colloid scintigraphy in confirmation.

Splenosis is acquired ectopic splenic tissue, usually a sequela of trauma. Its imaging appearance is can be deceiving, and at unusual locations may be mistaken for an alternate cause mass lesion. We present one such unusual case of splenosis in a 53 year-old man with history of heart failure involving the thoracic cavity identified as splenosis on nuclear medicine imaging and suspicion was raised given the remote history splenectomy after splenic rupture during trauma. We will discuss the imaging appearances of splenosis on CT, MRI and nuclear medicine studies, with emphasis on using nuclear medicine as a modality of choice to avoid biopsy. We will also go on to include a brief review of literature on this topic in this article. The key facts are role of detailed clinical history and requirement of high index of suspicion to avoid unnecessary intervention in the case of splenosis.

Renal transplant recipient seizure practical management.

Seizures are not uncommon in renal transplant patients. The common aetiologies are metabolic disturbance associated with renal failure, immunosuppression and associated complications and infections. Their management can be challenging because of altered pharmacokinetics of antiepileptic drugs (AEDs) and their removal by dialysis. A practical approach to the management of seizure in renal transplant patients is discussed. This review highlights the guidelines for use of various AEDs in renal transplants.

Roca disease: An osteochondrosis of the inferior pole of the scapula with review of the literature.

Osteochondrosis is a developmental condition affecting the endochondral ossification. It is commonly idiopathic however can be due to vascular anomalies, dietary conditions, hormonal irregularity, or overuse trauma. Osteochondrosis occurring in the inferior pole of the scapula is an extremely rare condition and is referred to as roca disease. A higher degree of suspicion is required especially in a young patient with atraumatic shoulder pain and additional unconventional MRI sequences focusing on the inferior pole of scapula can be taken to rule out such conditions. We report a case of Roca disease in a 16-year male who presented with right shoulder pain. This is the third case report of roca disease in the English literature according to our knowledge and the first case report to demonstrate extensive MRI imaging features with a normal radiograph. Imaging, particularly MRI, plays a pivotal role in the diagnosis of this extremely rare entity. Also, the inferior pole of the scapula is usually not included in routine shoulder MRI imaging thus close scrutiny with additional MRI sequences should be done to diagnose such a rare entity.

Solid pseudopapillary Tumor of the Pancreas: Radiological and surgical review.

Solid Pseudopapillary Neoplasms of the pancreas are rare pancreatic tumors with low-grade malignant potential, typically affecting young females. In this review, we discuss the surgical anatomy; the imaging characteristics, and image reporting essentials for proper surgical planning along with the atypical features which should caution the physician regarding the risk of malignancy. We also discuss the common surgical procedures and organ preservation surgeries along with a comprehensive review of the literature.

Foreign body (toothpick) causing epiglottitis.

A 25-year-old otherwise healthy woman presented to the hospital with sore throat and dysphagia for 5 days. On her computed tomography images, thickening and edema of the right aryepiglottic fold was noted, associated with an impacted foreign body.

"Snap-n-Eat": Food Recognition and Nutrition Estimation on a Smartphone.

We present snap-n-eat, a mobile food recognition system. The system can recognize food and estimate the calorific and nutrition content of foods automatically without any user intervention. To identify food items, the user simply snaps a photo of the food plate. The system detects the salient region, crops its image, and subtracts the background accordingly. Hierarchical segmentation is performed to segment the image into regions. We then extract features at different locations and scales and classify these regions into different kinds of foods using a linear support vector machine classifier. In addition, the system determines the portion size which is then used to estimate the calorific and nutrition content of the food present on the plate. Previous approaches have mostly worked with either images captured in a lab setting, or they require additional user input (eg, user crop bounding boxes). Our system achieves automatic food detection and recognition in real-life settings containing cluttered backgrounds. When multiple food items appear in an image, our system can identify them and estimate their portion size simultaneously. We implemented this system as both an Android smartphone application and as a web service. In our experiments, we have achieved above 85% accuracy when detecting 15 different kinds of foods.

Interactive retinal vessel extraction by integrating vessel tracing and graph search.

Despite recent advances, automatic blood vessel extraction from low quality retina images remains difficult. We propose an interactive approach that enables a user to efficiently obtain near perfect vessel segmentation with a few mouse clicks. Given two seed points, the approach seeks an optimal path between them by minimizing a cost function. In contrast to the Live-Vessel approach, the graph in our approach is based on the curve fragments generated with vessel tracing instead of individual pixels. This enables our approach to overcome the shortcut problem in extracting tortuous vessels and the problem of vessel interference in extracting neighboring vessels in minimal-cost path techniques, resulting in less user interaction for extracting thin and tortuous vessels from low contrast images. It also makes the approach much faster.

Automatic blood vessel localization in small field of view eye images.

Localizing blood vessels in eye images is a crucial step in the automated and objective diagnosis of eye diseases. Most previous research has focused on extracting the centerlines of vessels in large field of view images. However, for diagnosing diseases of the optic disk region, like glaucoma, small field of view images have to be analyzed. One needs to identify not only the centerlines, but also vessel widths, which vary widely in these images. We present an automatic technique for localizing vessels in small field of view images using multi-scale matched filters. We also estimate local vessel properties - width and orientation - along the length of each vessel. Furthermore, we explicitly account for highlights on thick vessels - central reflexes - which are ignored in many previous works. Qualitative and quantitative results demonstrate the efficacy of our method - e.g. vessel centers are localized with RMS and median errors of 2.11 and 1 pixels, respectively in 700×700 images.

Utility of digital stereo images for optic disc evaluation.

PURPOSE: To assess the suitability of digital stereo images for optic disc evaluations in glaucoma. METHODS: Stereo color optic disc images in both digital and 35-mm slide film formats were acquired contemporaneously from 29 subjects with various cup-to-disc ratios (range, 0.26-0.76; median, 0.475). Using a grading scale designed to assess image quality, the ease of visualizing optic disc features important for glaucoma diagnosis, and the comparative diameters of the optic disc cup, experienced observers separately compared the primary digital stereo images to each subject's 35-mm slides, to scanned images of the same 35-mm slides, and to grayscale conversions of the digital images. Statistical analysis accounted for multiple gradings and comparisons and also assessed image formats under monoscopic viewing. RESULTS: Overall, the quality of primary digital color images was judged superior to that of 35-mm slides (P < 0.001), including improved stereo (P < 0.001), but the primary digital color images were mostly equivalent to the scanned digitized images of the same slides. Color seemingly added little to grayscale optic disc images, except that peripapillary atrophy was best seen in color (P < 0.0001); both the nerve fiber layer (P < 0.0001) and the paths of blood vessels on the optic disc (P < 0.0001) were best seen in grayscale. The preference for digital over film images was maintained under monoscopic viewing conditions. CONCLUSIONS: Digital stereo optic disc images are useful for evaluating the optic disc in glaucoma and allow the application of advanced image processing applications. Grayscale images, by providing luminance distinct from color, may be informative for assessing certain features.

Unsupervised learning of discriminative edge measures for vehicle matching between nonoverlapping cameras.

This paper proposes a novel unsupervised algorithm learning discriminative features in the context of matching road vehicles between two non-overlapping cameras. The matching problem is formulated as a same-different classification problem, which aims to compute the probability of vehicle images from two distinct cameras being from the same vehicle or different vehicle(s). We employ a novel measurement vector that consists of three independent edge-based measures and their associated robust measures computed from a pair of aligned vehicle edge maps. The weight of each measure is determined by an unsupervised learning algorithm that optimally separates the same-different classes in the combined measurement space. This is achieved with a weak classification algorithm that automatically collects representative samples from same-different classes, followed by a more discriminative classifier based on Fisher' s Linear Discriminants and Gibbs Sampling. The robustness of the match measures and the use of unsupervised discriminant analysis in the classification ensures that the proposed method performs consistently in the presence of missing/false features, temporally and spatially changing illumination conditions, and systematic misalignment caused by different camera configurations. Extensive experiments based on real data of over 200 vehicles at different times of day demonstrate promising results.

Robust object matching for persistent tracking with heterogeneous features.

This paper addresses the problem of matching vehicles across multiple sightings under variations in illumination and camera poses. Since multiple observations of a vehicle are separated in large temporal and/or spatial gaps, thus prohibiting the use of standard frame-to-frame data association, we employ features extracted over a sequence during one time interval as a vehicle fingerprint that is used to compute the likelihood that two or more sequence observations are from the same or different vehicles. Furthermore, since our domain is aerial video tracking, in order to deal with poor image quality and large resolution and quality variations, our approach employs robust alignment and match measures for different stages of vehicle matching. Most notably, we employ a heterogeneous collection of features such as lines, points, and regions in an integrated matching framework. Heterogeneous features are shown to be important. Line and point features provide accurate localization and are employed for robust alignment across disparate views. The challenges of change in pose, aspect, and appearances across two disparate observations are handled by combining a novel feature-based quasi-rigid alignment with flexible matching between two or more sequences. However, since lines and points are relatively sparse, they are not adequate to delineate the object and provide a comprehensive matching set that covers the complete object. Region features provide a high degree of coverage and are employed for continuous frames to provide a delineation of the vehicle region for subsequent generation of a match measure. Our approach reliably delineates objects by representing regions as robust blob features and matching multiple regions to multiple regions using Earth Mover's Distance (EMD). Extensive experimentation under a variety of real-world scenarios and over hundreds of thousands of Confirmatory Identification (CID) trails has demonstrated about 95 percent accuracy in vehicle reacquisition with both visible and Infrared (IR) imaging cameras.

Rapid object indexing using locality sensitive hashing and joint 3D-signature space estimation.

We propose a new method for rapid 3D object indexing that combines feature-based methods with coarse alignment-based matching techniques. Our approach achieves a sublinear complexity on the number of models, maintaining at the same time a high degree of performance for real 3D sensed data that is acquired in largely uncontrolled settings. The key component of our method is to first index surface descriptors computed at salient locations from the scene into the whole model database using the Locality Sensitive Hashing (LSH), a probabilistic approximate nearest neighbor method. Progressively complex geometric constraints are subsequently enforced to further prune the initial candidates and eliminate false correspondences due to inaccuracies in the surface descriptors and the errors of the LSH algorithm. The indexed models are selected based on the MAP rule using posterior probability of the models estimated in the joint 3D-signature space. Experiments with real 3D data employing a large database of vehicles, most of them very similar in shape, containing 1,000,000 features from more than 365 models demonstrate a high degree of performance in the presence of occlusion and obscuration, unmodeled vehicle interiors and part articulations, with an average processing time between 50 and 100 seconds per query.

Shapeme histogram projection and matching for partial object recognition.

Histograms of shape signature or prototypical shapes, called shapemes, have been used effectively in previous work for 2D/3D shape matching and recognition. We extend the idea of shapeme histogram to recognize partially observed query objects from a database of complete model objects. We propose representing each model object as a collection of shapeme histograms and match the query histogram to this representation in two steps: 1) compute a constrained projection of the query histogram onto the subspace spanned by all the shapeme histograms of the model and 2) compute a match measure between the query histogram and the projection. The first step is formulated as a constrained optimization problem that is solved by a sampling algorithm. The second step is formulated under a Bayesian framework, where an implicit feature selection process is conducted to improve the discrimination capability of shapeme histograms. Results of matching partially viewed range objects with a 243 model database demonstrate better performance than the original shapeme histogram matching algorithm and other approaches.