Takahiro Okabe

Latest

Hierarchical Gaussian Descriptors with Application to Person Re-Identification
Auto-Radiometric Calibration in Photometric Stereo
Hierarchical Gaussian Descriptor for Person Re-identification
Reflectance and Fluorescence Spectral Recovery via Actively Lit RGB Images
Separating Reflective and Fluorescent Components Using High Frequency Illumination in the Spectral Domain
From Intensity Profile to Surface Normal: Photometric Stereo for Unknown Light Sources and Isotropic Reflectances
Gaze Estimation From Eye Appearance: A Head Pose-Free Method via Eye Image Synthesis
Adaptive Linear Regressionfor Appearance-Based Gaze Estimation
Fast Spectral Reflectance Recovery Using DLP Projector
Learning gaze biases with head motion for head pose-free gaze estimation
Person Re-identification via Discriminative Accumulation of Local Features
Reflectance and Fluorescent Spectra Recovery Based on Fluorescent Chromaticity Invariance under Varying Illumination
Converting Near Infrared Facial Images to Visible Light Images using Skin Pigment Model
Efficient Modeling of Objects BRDF with Planned Sampling
Head direction estimation from low resolution images with scene adaptation
Separating Reflective and Fluorescent Components Using High Frequency Illumination in the Spectral Domain
Spectral Imaging Using Basis Lights
Uncalibrated Photometric Stereo for Unknown Isotropic Reflectances
Bispectral photometric stereo based on fluorescence
Camera spectral sensitivity estimation from a single image under unknown illumination by using fluorescence
Head pose-free appearance-based gaze sensing via eye image synthesis
Illumination normalization of face images with cast shadows
Incorporating visual field characteristics into a saliency map
Toward Efficient Acquisition of BRDFs with Fewer Samples
A Head Pose-free Approach for Appearance-based Gaze Estimation
Aesthetic quality classification of photographs based on color harmony
Appearance-based head pose estimation with scene-specific adaptation
Attention Prediction in Egocentric Video Using Motion and Visual Saliency
Fast unsupervised ego-action learning for first-person sports videos
Inferring human gaze from appearance via adaptive linear regression
Photometric stereo with auto-radiometric calibration
Surface Reconstruction in Photometric Stereo with Calibration Error
Can Saliency Map Models Predict Human Egocentric Visual Attention?
Detecting Forgery From Static-Scene Video Based on Inconsistency in Noise Level Functions
Fast Spectral Reflectance Recovery Using DLP Projector
Image Enhancement of Low-light Scenes with Near-infrared Flash Images
Recognizing Multiple Objects Based on Co-occurence of Categories
Video Temporal Super-Resolution Based on Self-similarity
Attached shadow coding: Estimating surface normals from shadows under unknown reflectance and lighting conditions
Detecting Video Forgeries Based on Noise Characteristics
Image Enhancement of Low-Light Scenes with Near-Infrared Flash Images
Recognizing Multiple Objects via Regression Incorporating the Co-occurrence of Categories
Sensation-based photo cropping
Using individuality to track individuals: Clustering individual trajectories in crowds using local appearance and frequency trait
Discovering Primitive Action Categories by Leveraging Relevant Visual Context
Appearance Sampling of Real Objects for Variable Illumination
Shape Reconstruction Based on Similarity in Radiance Changes under Varying Illumination
Effects of Image Segmentation for Approximating Object Appearance Under Near Lighting
Face Recognition Under Varying Illumination Based on MAP Estimation Incorporating Correlation Between Surface Points
Gaze Estimation from Low Resolution Images
Robust Content-Dependent Photometric Projector Compensation
Radiometric Compensation in a Projector-Camera System Based Properties of Human Vision System
Using Extended Light Sources for Modeling Object Appearance under Varying Illumination
Reflectance Estimation from Motion under Complex Illumination
Spherical Harmonics vs. Haar Wavelets: Basis for Recovering Illumination from Cast Shadows
Support Vector Machines for Object Recognition under Varying Illumination Conditions
Appearance Sampling for Obtaining A Set of Basis Images for Variable Illumination
Object Recognition Based on Photometric Alignment Using RANSAC