JOE ROBINSON'S HOMEPAGE
  • Home
  • Publications
  • Services
  • Projects
  • FIW
  • Blog
  • News
  • My Blogs

Projects

Picture

FIW Database
​

FIW is the largest and most comprehensive image DB for kinship recognition to date! Check out webpage for benchmarks, data, data challenges, and more.
​Visit project page.
Picture

BFW and Fair Face Recognition

Bias in FR is a contemporary concern, justifiably. To have solutions we must establish ground-work such aa a baseline to characterize and rate systems per demographic. Visit GitHub for more info, source code, data downloads, and more.
Picture

Profiler: Face Synthesizer

Face frontalization system with one-to-many inputs (more faces = better results). For this, we proposed a Dual-Attention GAN For Large-Pose Face Frontalization! Published in 2020 AAAI!
Check out on Github!

PhD Dissertation: Defense PresentatioN

Title                                    
Title: Automatic Face Understanding: Recognizing Families in Photos
Date / Time                                    
Nov 24, 2020 at 2:00 PM

Committee Members       
Prof. Yun Fu (Advisor), Prof. Octavia Camps, Prof. Sarah Ostadabbas

Laplace Landmark Localization (Fig. 1)

Abstract

Landmark localization in images and videos is a classic problem solved in various ways. Nowadays, with deep networks prevailing throughout machine learning, there are revamped interests in pushing facial landmark detectors to handle more challenging data. Most efforts use network objectives based on L1 or L2 norms, which have several disadvantages. First of all, the generated heat-maps trans- late to the locations of landmarks (i.e. confidence maps) from which predicted landmark locations (i.e. the means) get penalized without accounting for the spread: a high- scatter corresponds to low confidence and vice-versa. For this, we introduce a LaplaceKL objective that penalizes for low confidence. Another issue is a dependency on labeled data, which are expensive to obtain and susceptible to error. To address both issues, we propose an adversarial training framework that leverages unlabeled data to improve model performance. Our method claims state-of-the-art on all of the 300W benchmarks and ranks second-to-best on the An- notated Facial Landmarks in the Wild (AFLW) dataset. Furthermore, our model is robust with a reduced size: 1/8 the number of channels (i.e. 0.0398 MB) is comparable to the state-of-the-art in real-time on CPU. Thus, this work is of high practical value to real-life application. 
Picture
Fig. 1: The proposed semi-supervised framework for landmarks localization. The labeled and unlabeled branched are marked with blue and red arrows, respectfully. Given an input image, G produces K heat-maps, one for each landmark. Labels are used to generate real heat-maps as ω(sl). G produces fake samples from the unlabeled data. Source images are concatenated on heat-maps and passed to D. 
Other Projects
Families In the Wild (FIW) Image Dataset
Picture
1st large-scale image database for kinship recognition [project page]
Call For Papers! An ACM MM 2017 Data Challenge Workshop [challenge page]
NE CV Workshop 2016 @ BU [extended abstract, ppt]
ACM MM 2016 @ University of Amsterdam, [paper, poster]
Person Re-ID
Complex Event Detection in Videos
Picture
Picture
COMING SOON
[paper] [workbook] [ppt] [poster]
Robotics
A Tunnel Inspecting Robot
Picture
                         Poster, presentation, report, video demos (V1, V2)​
Optical Science
Simulation of OCT in Lung Tissues
Picture
[poster] [paper]
Melanoma Detection via 3-Photon Florence 
Picture
[poster] [paper]
Powered by Create your own unique website with customizable templates.
  • Home
  • Publications
  • Services
  • Projects
  • FIW
  • Blog
  • News
  • My Blogs