I am an Assistant Professor at the University of Wisconsin-Madison in the department of Electrical and Computer Engineering, and affiliated with the Computer Sciences department. My research interests are at the intersection of computer vision and machine learning. Specifically, I develop systems that continuously learn to perceive the world through multiple sensory modalities.
Previously, I was a postdoc researcher at Carnegie Mellon University, working with Abhinav Gupta. I completed my PhD at the University of California San Diego advised by Nuno Vasconcelos, and both BSc and MSc degrees at Instituto Superior Técnico, Universidade de Lisboa, where I worked with Margarida Silveira and Jorge S Marques.
I am looking for highly motivated PhD and MS students to join the lab. If you are interested, please contact me.
A Closer Look at Weakly-Supervised Audio-Visual Source Localization
Neural Information Processing Systems (NeurIPS), New Orleans, 2022.
Learning Visual Representation from Audible Interactions
Neural Information Processing Systems (NeurIPS), New Orleans, 2022.
Benchmarking and Automating the Image Recognition Capability of an In Situ Plankton Imaging System
Frontiers in Marine Science, 2022.
The Challenges of Continuous Self-Supervised Learning
European Conference on Computer Vision (ECCV), Tel Aviv, Israel, 2022.
paper code video bibtex Oral presentation
Localizing Visual Sounds the Easy Way
European Conference on Computer Vision (ECCV), Tel Aviv, Israel, 2022.
Learning to see and hear without human supervision
PhD Thesis, University of California San Diego, 2021.
Robust Audio-Visual Instance Discrimination
IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), 2021.
paper video bibtex Oral presentation
Audio-Visual Instance Discrimination with Cross-Modal Agreement
IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), 2021.
paper code video blogpost bibtex Best paper candidate
Audio-Visual Instance Discrimination
ECCV Workshop - Multi-Modal Video Analysis, 2020.
Deep Hashing with Hash-Consistent Large Margin Proxy Embeddings
International Journal of Computer Vision (IJCV), 2020.
NetTailor: Tuning the Architecture, Not Just the Weights
IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, 2019.
[Workshop] NetTailor: Tuning the Architecture, Not Just the Weights
Southern California Machine Learning Symposium (SCMLS), 2020.
Semantically Consistent Regularization for Zero-Shot Recognition
IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), Honolulu, Hawaii, 2017.
Minimal Neighborhood Redundancy Maximal Relevance: Application to the Diagnosis of Alzheimer's Disease
Neurocomputing, Vol. 155, pp. 295-308, May, 2015.
Efficient Selection of Non-redundant Features for the Diagnosis of Alzheimer's Disease
International Symposium on Biomedical Imaging (ISBI), San Francisco, CA, 2013.
paper bibtex Oral presentation
Predicting Conversion from MCI to AD with FDG-PET Brain Images at Different Prodromal Stages
Computers in Biology and Medicine, Vol. 58, pp. 101-109, March, 2015
Texton-based Diagnosis of Alzheimer's Disease
IEEE Int. Workshop on Machine Learning for Signal Processing (MLSP), Southampton, UK, 2013.
Diagnosis of Alzheimer's disease using 3D Local Binary Patterns
Computer Methods in Biomechanics and Biomedical Engineering: Imaging Visualization, Vol. 1, April, 2013
Extending Local Binary Patterns to 3D for the Diagnosis of Alzheimer's Disease
International Symposium on Biomedical Imaging (ISBI), San Francisco, CA, 2013.
Automated Diagnosis of Alzheimer's Disease using PET Images: A study of alternative procedures for feature extraction and selection
Master Thesis, Instituto Superior Tecnico, Lisboa, Portugal.