13th May, 2023


Welcome to the 2nd MSU-ND Computer Vision and Biometrics Workshop. This is a gathering of computer vision and biometrics researchers at Michigan State University and the 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
9:30 Continental breakfast provided by Morton’s Fine Catering  
09:45 Arrival/Check-In  
10:00 Introduction  
10:30 The Gender Gap in Face Recognition is a Hairy Problem Aman Bhatta
10:45 Face Recognition, Image, Video, and Beyond Minchul Kim
11:00 Trusted AI and Forensic Iris Recognition Adam Czajka
11:15 Automatic Speaker Recognition in Affective Settings Morgan Sandler
11:30 Poster Session I  
13:00 Lunch Break Morton’s Fine Catering
14:00 Unsupervised Learning of Physiological Signals from Video Jeremy Speth
14:15 Representation Learning from Interventional Data Gautam Sreekumar
14:30 Measuring Human Perception to Improve Open Set Recognition Jin Huang
14:45 Evidential Deep Learning for Open Set Action Recognition Wentao Bao
15:00 Poster Session II  
16:30 Generalized and Robust Remote Photoplethysmography Nathan Vance
16:45 3D Perception: from Shape Reconstruction, 3D Detection to Recognition Feng Liu
17:00 Measuring Human Perception to Improve Handwritten Document Transcription Samuel Grieggs
17:15 Do learned representations respect causal relationships? Lan Wang
17:30 Campus walk/tour Weather Permitting
18:30 Dinner Brody Complex
20:00 Departure  

Poster Session I

  1. From Shadow Synthesis to Shadow Removal: Face Relighting Under Diverse Illumination Conditions (Andrew Hou)
  2. Proactive Image Manipulation Detection and Localization (Vishal Asnani)
  3. Deep Two-View Structure-From-Motion with RANSAC (Shengjie Zhu)
  4. TIGER: Time-varying Denoising Model for 3D Point Cloud Generation with Diffusion Process (Zhiyuan Ren)
  5. AutoFHE: Automated Adaption of CNNs for Efficient Evaluation over FHE (Wei Ao)
  6. Bridging the Spectrum: A Semantic-Guided GAN for Cross-Spectral Face Recognition (Parisa Farmanifard)
  7. Fusion of Face, Gait and Body for Long Range and High Altitude Human Recognition (Ryan Ashbaugh)
  8. Has the virtualization of the face changed facial perception? A study of the impact of augmented reality on facial perception (Louisa Conwill)
  9. Forensic Iris Recognition (Rasel Ahmed Bhuiyan)
  10. Human Activity Recognition in an Open World (Derek Prijatelj)
  11. HomOpt: A Homotopy-Based Hyperparameter Optimization Method (Sophia Abraham)
  12. Focus improves performance with deep learning-based models (Jacob Piland)
  13. Mitigating Task Interference in Multi-Task Learning via Explicit Task Routing with Non-Learnable Primitives (Vishnu Boddeti)

Poster Session II

  1. DEVIANT: Depth Equivariant Network for Monocular 3D Object Detection (Abhinav Kumar)
  2. GlobalGait: Global Spatiotemporal Representation Learning for GaitRecognition via Sequence Completion (Yiyang Su)
  3. Hierarchical Fine-Grained Image Forgery Detection and Localization (Xiao Guo)
  4. On Characterizing the Trade-off in Invariant Representation Learning (Sepehr Dehdashtian)
  5. Intelligent Frame Selection from Videos to Improve Face Recognition Accuracy (Pegah Varghaei)
  6. To Impute or Not: Addressing Missing Scores in Biometric Fusion (Melissa Dale)
  7. Deep Learning Approaches to Comparative Medical Radiography with Chest Radiographs (Redwan Sony)
  8. DeformIrisNet: An Identity-Preserving Model of Iris Texture Deformation (Siamul Karim Khan)
  9. Hierarchically Organized Computer Vision in Support of Multi-Faceted Search for Missing Persons (Arturo Miguel Russell Bernal)
  10. Scientific Integrity Verification through Image Forensics (Daniel Moreira)
  11. Teaching AI to Teach: Using Human Perception For Model Saliency-Based Training At Scale (Colton Crum)
  12. Revisiting Residual Networks for Adversarial Robustness (Vishnu Boddeti)
  13. RADIANT: Radar-Image Association Network for 3D Object Detection (Yunfei Long)