The PASCAL Visual Object Classes Challenge

https://scholarlypublications.universiteitleiden.nl/access/item%3A2943283/view

Deep learning for visual understanding

This study aimed to review the literature describing and quantifying time lags in the health research translation process. Papers were included in the review if they quantified time lags in the development of health interventions. The study identified 23 papers. Few were comparable as different studies use different measures, of different things, at different time points. We concluded that the current state of knowledge of time lags is of limited use to those responsible for R&D and knowledge transfer who face difficulties in knowing what they should or can do to reduce time lags. This effectively ‘blindfolds’ investment decisions and risks wasting effort. The study concludes that understanding lags first requires agreeing models, definitions and measures, which can be applied in practice. A second task would be to develop a process by which to gather these data.

The Answer Is 17 Years, What Is the Question

Learning Deconvolution Network for Semantic Segmentation

We introduce hand movement, orientation, and grasp (HMOG), a set of behavioral features to continuously authenticate smartphone users. HMOG features unobtrusively capture subtle micro-movement and orientation dynamics resulting from how a user grasps, holds, and taps on the smartphone. We evaluated authentication and biometric key generation (BKG) performance of HMOG features on data collected from 100 subjects typing on a virtual keyboard. Data were collected under two conditions: 1) sitting and 2) walking. We achieved authentication equal error rates (EERs) as low as 7.16% (walking) and 10.05% (sitting) when we combined HMOG, tap, and keystroke features. We performed experiments to investigate why HMOG features perform well during walking. Our results suggest that this is due to the ability of HMOG features to capture distinctive body movements caused by walking, in addition to the hand-movement dynamics from taps. With BKG, we achieved the EERs of 15.1% using HMOG combined with taps. In comparison, BKG using tap, key hold, and swipe features had EERs between 25.7% and 34.2%. We also analyzed the energy consumption of HMOG feature extraction and computation. Our analysis shows that HMOG features extracted at a 16-Hz sensor sampling rate incurred a minor overhead of 7.9% without sacrificing authentication accuracy. Two points distinguish our work from current literature: 1) we present the results of a comprehensive evaluation of three types of features (HMOG, keystroke, and tap) and their combinations under the same experimental conditions and 2) we analyze the features from three perspectives (authentication, BKG, and energy consumption on smartphones).

/pdf/hmog-new-behavioral-biometric-features-for-continuous-wxqxi7t4mv.pdf

HMOG: New Behavioral Biometric Features for Continuous Authentication of Smartphone Users

In this paper, we proposed a novel graph based approach for image segmentation using color and texture features that are extracted from small image patches. This algorithm segments the image through two steps – it conservatively over segment the image and then merges the larger regions progressively. We also generate the visual content from the image by labeling it into different classes. We got 66.23% and 79.09% classification accuracy from our dataset and the Stanford background dataset respectively, and our segmentation approach consistently gives superior performance as compared to the over-segmentation method.

Generating Visual Content from Images via Segmentation.

High-level, or holistic, scene understanding involves reasoning about objects, regions, the 3D relationships between them, etc. Scene labeling underlies many of these problems in computer vision. Reasoning about scene images requires the decomposition into semantically meaningful regions over which a graphical model can be imposed. Typically, representational models, learned from data, are defined in terms of a unified energy function over the appearance and structure of the scene-under-investigation. In this chapter, we explore energy functions defined within the context of conditional random fields (CRF) and examine in detail, one learning and inference technique that can be used to reason about the scene. We specifically review methods involving semantic categorization (such as grass, sky, foreground, etc.) and geometric categorization (typically the vertical plane, the ground plane, and the sky plane). CRFs are an effective tool for partitioning images into their constituent semantic or geometric level regions and assigning the appropriate class labels to each region. We also present specific algorithms from the literature that have successfully used CRFs for labeling scene images.

Conditional Random Fields for Scene Labeling

American Sign Language (ASL) is the fourth most commonly used language in the United States and is the language most commonly used by Deaf people in the United States and the English-speaking regions of Canada. Unfortunately, until recently, ASL received little research. This is due, in part, to its delayed recognition as a language until William C. Stokoe's publication in 1960. Limited data has been a long-standing obstacle to ASL research and computational modeling. The lack of large-scale datasets has prohibited many modern machine-learning techniques, such as Neural Machine Translation, from being applied to ASL. In addition, the modality required to capture sign language (i.e. video) is complex in natural settings (as one must deal with background noise, motion blur, and the curse of dimensionality). Finally, when compared with spoken languages, such as English, there has been limited research conducted into the linguistics of ASL. 
We realize a simplified version of Liddell and Johnson's Movement-Hold (MH) Model using a Probabilistic Graphical Model (PGM). We trained our model on ASLing, a dataset collected from three fluent ASL signers. We evaluate our PGM against other models to determine its ability to model ASL. Finally, we interpret various aspects of the PGM and draw conclusions about ASL phonetics. The main contributions of this paper are

Modeling Global Body Configurations in American Sign Language

In this chapter, we discuss a novel biometric trait, called cognitive biometrics . It is defined as the process of identifying an individual through extracting and matching unique signatures based on the cognitive, affective, and conative state of that individual. Currently, there is an increasing need for novel biometric systems that engage multiple modalities because of the changing notion of privacy in today’s world. Also, cognitive biometrics will become essential as pervasive computing becomes more prevalent, where computing can happen anywhere and anytime. The use of cognitive traits for biometrics is relatively underexplored in the research community. We study whether the cognitive state of a person can be learned and used as a soft biometric trait and discuss our large-scale experimental setup, which yielded encouraging results.

A Large-Scale Study of Language Usage as a Cognitive Biometric Trait

Expression neutralization is the process of synthetically altering an image of a face so as to remove any facial expression from it without changing the face’s identity. Facial expression neutralization could have a variety of applications, particularly in the realms of facial recognition, in action unit analysis, or even improving the quality of identification pictures for various types of documents. Our proposed model, StoicNet, combines the robust encoding capacity of variational autoencoders, the generative power of generative adversarial networks, and the enhancing capabilities of super resolution networks with a learned encoding transformation to achieve compelling expression neutralization, while preserving the identity of the input face. Objective experiments demonstrate that StoicNet successfully generates realistic, identity-preserved faces with neutral expressions, regardless of the emotion or expression intensity of the input face.

/pdf/facial-expression-neutralization-with-stoicnet-2r8mrif7fe.pdf

Ifeoma Nwogu

Papers

Generating Visual Content from Images via Segmentation.

Conditional Random Fields for Scene Labeling

Modeling Global Body Configurations in American Sign Language

A Large-Scale Study of Language Usage as a Cognitive Biometric Trait

Facial Expression Neutralization With StoicNet