Description
Welcome to the 1st MSU-ND Computer Vision and Biometrics Workshop. This is a gathering of computer vision and biometrics researchers at Michigan State University and University of Notre Dame to discuss recent research findings and cultivate a community of collaboration among the faculty and students.
Program Outline
| Time | Program | Notes |
|---|---|---|
| Morning | ||
| 09:45 | Arrival/Check-In | |
| 10:00 | Introduction | |
| 10:30 | Uncertainty-aware Deep Face Recognition | Yichun Shi |
| 10:45 | Does Face Recognition Accuracy Get Better With Age? Deep Face Matchers Say No | Vitor Albiero |
| 11:00 | Deep Tree Learning for Zero-shot Face Anti-spoofing | Yaojie Liu |
| 11:15 | Provenance Analysis: Telling the Story of Composite Images | Daniel Moreira |
| 11:30 | Poster Session I | |
| 13:00 | Lunch Break | Catered |
| Afternoon | ||
| 14:00 | RaspiReader: An Open Source Fingerprint Reader | Joshua Engelsma |
| 14:15 | Deep Feature Extraction for Iris Recognition | Aidan Boyd |
| 14:30 | Fusing MFCC and LPC Features using 1D Triplet CNN for Speaker Recognition in Severely Degraded Audio Signals | Anurag Chowdhury |
| 14:45 | Bridging the Gap Between Computational Photography and Visual Recognition: The UG^2 Challenges | Sreya Banerjee |
| 15:00 | Poster Session II | |
| 16:30 | RankGAN: A Maximum Margin Ranking GAN for Generating Faces | Rahul Dey |
| 16:45 | Towards Exascale Connectomics with FLoRIN and Deep Learning | Jeff Kinnison |
| 17:00 | Unsupervised Temporal Segmentation of Actions in Video | Rosaura Vidal |
| 17:15 | Adversarially Fair Representation Learning | Bashir Sadeghi |
| Evening | ||
| 17:30 | Campus Walk/Tour | Weather Permitting |
| 18:30 | Dinner | |
| 20:00 | Departure |
Poster Session I
- Synthesizing Face Images from Graphs (Thomas Swearingen)
- Inverse Graphics for 3D Object Modeling and Reconstruction (Luan Tran/Feng Liu)
- Towards Interpretable Face Recognition (Xiaoming Liu)
- NSGA-Net: Neural Architecture Search using Multi-Objective Genetic Algorithm (Zhichao Lu)
- Fake Face Detection (Hao Dang)
- On the Intrinsic Dimensionality of Image Representation (Sixue Gong)
- WarpGAN: Automatic Caricature Generation (Debayan Deb)
- Face Phylogeny Tree: Deducing Relationships Between Near-Duplicate Face Images Using Legendre Polynomials and Radial Basis Functions (Sudipta Banerjee)
- On Learning Disentangled Representations for Gait Recognition (Ziyuan Zhang)
- Visual Psychophysics for Face Recognition (Walter Scheirer)
- Weakly Supervised Step-wise Domain Adaptation for LR Face Recognition (Pei Li)
- Domain-Specific Human-Inspired Binarized Statistical Image Features for Iris Recognition (Adam Czajka / Daniel Moreira)
- Predicting Gender From Iris Texture May be Harder Than it Seems (Andrey Kuehlkamp)
- Deep Feature Extraction for Iris Recognition (Aidan Boyd)
- Real-time Scene Text Detection and Recognition for Videos (Bingyu Shen)
- GTA: Ground Truth Automator (Patrick Tinsley)
- PrivacyNet: Obfuscating Soft-Biometric Attributes for Face Privacy (Vahid Mirjalili)
- Generating Hash Codes for Faces and Fingerprints (Achsah/Vedrana)
- Tools for Meme Analysis (William Theisen)
Poster Session II
- 3D Face Modeling From Diverse Raw Scan Data (Feng Liu)
- Verba Volant, Scripta Manent: AI Assisted Historical Document Analysis (Sam Grieggs/Bingyu Shen)
- Unsupervised Temporal Segmentation of Actions in Video (Rosaura Vidal)
- Bridging the Gap Between Computational Photography and Visual Recogntion: The UG^2 Dataset (Rosaura Vidal/Sreya Banerjee)
- On the Global Optima of Kernelized Adversarial Representation Learning (Bashir Sadeghi)
- Beyond Pixels: Image Provenance Analysis Leveraging Metadata (Daniel Moreira)
- M3D-RPN: Monocular 3D Region Proposal Network for Object Detection (Garrick Brazil)
- Noise Modeling, Synthesis, and Classification for Generic Object Anti-Spoofing (Joel Stehouwer)
- Learning-free iris segmentation revisited: A first step toward fast volumetric operation over video samples (Jeff Kinnison)
- Iris Presentation Attack Detection Based on Photometric Stereo Features (Zhaoyuan (Andy) Wang / Adam Czajka)
- Real-time Scene Text Detection and Recognition for Videos (Bingyu Shen)
- Synthesizing iris images using RaSGAN (Shivangi Yadav)
- Mitigating Information Leakage in Image Representations: A Maximum Entropy Approach (Proteek Roy)
- White-Box Evaluation of Fingerprint Matchers (Steven Grosz)
- Feature Transfer Learning for Face Recognition with Under-Represented Data (Xiaoming Liu)
- Depth Coefficients for Depth Completion (Saif Imran)
- OCT Imaging-based Iris Presentation Attack Detection (Renu Sharma)
- Fingerprint Presentation Attack Detection: Generalization and Efficiency (Tarang Chugh)