Pre-processing of Video Streams for Extracting Queryable Representation of...
AbstractAutomating video stream processing for inferring situations of interest has been an ongoing challenge. This problem is currently exacerbated by the volume of surveillance/monitoring videos...
View ArticleAPSEN: Pre-screening Tool for Sleep Apnea in a Home Environment
AbstractThis paper describes the APSEN system, a pre-screening tool for detecting sleep apnea in a home environment. The system was designed and evaluated in two parts; the apnea detection using SpO2...
View ArticleChallenges in Multi-modal Gesture Recognition
AbstractThis paper surveys the state of the art on multimodal gesture recognition and introduces the JMLR special topic on gesture recognition 2011–2015. We began right at the start of the...
View ArticleDetecting Instances of Shape Classes That Exhibit Variable Structure
AbstractThis paper proposes a method for detecting shapes of variable structure in images with clutter. The term “variable structure” means that some shape parts can be repeated an arbitrary number of...
View ArticleEvaluating Single Image Dehazing Methods Under Realistic Sunlight Haze
AbstractHaze can degrade the visibility and the image quality drastically, thus degrading the performance of computer vision tasks such as object detection. Single image dehazing is a challenging and...
View ArticleDomain Adaptive Transfer Learning on Visual Attention Aware Data Augmentation...
AbstractFine-Grained Visual Categorization (FGVC) is a challenging topic in computer vision. It is a problem characterized by large intra-class differences and subtle inter-class differences. In this...
View ArticleAdaptive Feature Norm for Unsupervised Subdomain Adaptation
AbstractIn many real-world problems, obtaining labeled data for a specific machine learning task is expensive. Unsupervised Domain Adaptation (UDA) aims at learning a good predictive model for the...
View ArticleCross Your Body: a Cognitive Assessment System for Children
AbstractWhile many action recognition techniques have great success on public benchmarks, such performance is not necessarily replicated in real-world scenarios, where the data comes from specific...
View ArticleSemi Automatic Hand Pose Annotation Using a Single Depth Camera
AbstractThis paper addresses the problem of 3D hand pose annotation using a single depth camera. While hand pose annotations are critically important for training deep neural networks, creating such...
View Article2D Fingertip Localization on Depth Videos Using Paired Video-to-Video...
AbstractWe propose a two-stage pipeline and formulate 2D hand keypoint localization as a problem of conditional video generation. The goal is to learn a mapping function from an input depth video in...
View Article