다중혈관 관상동맥 환자에서 y-문합을 이용하여 양쪽 내흉동맥만을 사용한 우회술의 조기 성적

The Pascal Visual Object Classes (VOC) challenge is a benchmark in visual object category recognition and detection, providing the vision and machine learning communities with a standard dataset of images and annotation, and standard evaluation procedures. Organised annually from 2005 to present, the challenge and its associated dataset has become accepted as the benchmark for object detection.

This paper describes the dataset and evaluation procedure. We review the state-of-the-art in evaluated methods for both classification and detection, analyse whether the methods are statistically different, what they are learning from the images (e.g. the object or its context), and what the methods find easy or confuse. The paper concludes with lessons learnt in the three year history of the challenge, and proposes directions for future improvement and extension.

/pdf/the-pascal-visual-object-classes-voc-challenge-ugvl0p2h51.pdf

The Pascal Visual Object Classes (VOC) Challenge

I have developed "tennis elbow" from lugging this book around the past four weeks, but it is worth the pain, the effort, and the aspirin. It is also worth the (relatively speaking) bargain price. Including appendixes, this book contains 894 pages of text. The entire panorama of the neural sciences is surveyed and examined, and it is comprehensive in its scope, from genomes to social behaviors. The editors explicitly state that the book is designed as "an introductory text for students of biology, behavior, and medicine," but it is hard to imagine any audience, interested in any fragment of neuroscience at any level of sophistication, that would not enjoy this book. The editors have done a masterful job of weaving together the biologic, the behavioral, and the clinical sciences into a single tapestry in which everyone from the molecular biologist to the practicing psychiatrist can find and appreciate his or

Principles of Neural Science

We seek to build a large collection of images with ground truth labels to be used for object detection and recognition research. Such data is useful for supervised learning and quantitative evaluation. To achieve this, we developed a web-based tool that allows easy image annotation and instant sharing of such annotations. Using this annotation tool, we have collected a large dataset that spans many object categories, often containing multiple instances over a wide variety of images. We quantify the contents of the dataset and compare against existing state of the art datasets used for object recognition and detection. Also, we show how to extend the dataset to automatically enhance object labels with WordNet, discover object parts, recover a depth ordering of objects in a scene, and increase the number of labels using minimal user supervision and images from the web.

/pdf/labelme-a-database-and-web-based-tool-for-image-annotation-11uu9zjhjj.pdf

LabelMe: A Database and Web-Based Tool for Image Annotation

Human linguistic annotation is crucial for many natural language processing tasks but can be expensive and time-consuming. We explore the use of Amazon's Mechanical Turk system, a significantly cheaper and faster method for collecting annotations from a broad base of paid non-expert contributors over the Web. We investigate five tasks: affect recognition, word similarity, recognizing textual entailment, event temporal ordering, and word sense disambiguation. For all five, we show high agreement between Mechanical Turk non-expert annotations and existing gold standard labels provided by expert labelers. For the task of affect recognition, we also show that using non-expert labels for training machine learning algorithms can be as effective as using gold standard annotations from experts. We propose a technique for bias correction that significantly improves annotation quality on two tasks. We conclude that many large labeling tasks can be effectively designed and carried out in this method at a fraction of the usual expense.

/pdf/cheap-and-fast-but-is-it-good-evaluating-non-expert-4kvurc68of.pdf

Cheap and Fast -- But is it Good? Evaluating Non-Expert Annotations for Natural Language Tasks

Finding slope units for a given watershed is an important task before analyzing landslide susceptibility. Usually, slope unit generation requires integration of several digital elevation model (DEM)-based outputs obtained from GIS and related hydrological software. Therefore, it is time consuming due to involved steps and compilation of various software outputs. In this paper a DEM-based, scale and resolution invariant, fully automatic method is proposed for creating slope units to be used in landslide susceptibility mapping.

Deliniation of Slope Units based on Scale and Resolution Invariant 3D Curvature Extraction

This invention is related to a method that enables the object based segmentation of especially air/satellite images that are displayed in high resolution. The aim of the invention is to determine automatically the borders of objects by using statistical, spatial and structural relationships/characteristics and also by using high resolution air/satellite image data. Another aim of the invention is to develop a method that can operate by being minimally affected by limiting aspects such as ambient light, weather conditions or resolution and that can provide the determination of an object as a whole instead of sensing it in pixels.

An object based segmentation method

In this paper we present a physically-based 3D facial skin model based on biomechanical properties of human facial anatomy. The skin model is mainly formed of two DNURBS surfaces as a two layered membrane structure. The model represents the soft tissue layer which covers the skull and is attached to the skull via muscle insertion points. The model is fitted on digitally scanned 3D facial surfaces and controlled via DNURBS control points, which are spatially close to muscle insertion points. The face (skin model) is modified by displacing control points to mimic muscle contraction in order to simulate facial expressions. The system is solved and the simulations are displayed on a graphics workstation, where near real-time performance is achieved as opposed to many other existing physically- based methods.

A physically-based facial skin model to simulate facial expressions on digitally scanned 3D models

This paper addresses semi-automatic annotation of faces in personal videos. Different from previous offline annotation systems, this paper studies online annotation of faces. During an annotation session, few annotations are requested from the user only for some part of the video online. These annotations are used to train a system that will perform annotation automatically for the rest of the video. The automatic annotation results are presented to the user during the same session and the user is allowed to correct any automatic annotation mistakes. Thus, only fast and accurate face recognition methods are considered. Instead of batch learning, which has been used in the existing annotation systems, this paper proposes sequential learning methods to be used as face classifiers. Different classification methods are tested with various feature extraction methods using the same database so that a fair comparison is made among them. The results are evaluated in terms of recognition accuracies and execution time requirements.

Online annotation of faces in personal videos by sequential learning

The simultaneous operation of localization capability which serves to navigation of an autonomous robot and map building mechanism which provides an environmental model is called SLAM (Simultaneous Localization and Map Building). While various sensors are used for this algorithm, vision-based algorithms are relatively new and have attracted more attention in recent years. In this work, while a Visual SLAM algorithm utilizing Extended Kalman Filter is introduced, the two main branches, mono and stereo SLAM algorithms, are also compared.

Ilkay Ulusoy

Papers

Deliniation of Slope Units based on Scale and Resolution Invariant 3D Curvature Extraction

An object based segmentation method

A physically-based facial skin model to simulate facial expressions on digitally scanned 3D models

Online annotation of faces in personal videos by sequential learning

Vision-based Simultaneous Localization and Map Building: Stereo and mono SLAM