Pedro Morgado

I've completed my Ph.D. at the University of California San Diego under the supervision of Prof. Nuno Vasconcelos. The title of my dissertation was "Learning to see and hear without human supervision". After graduation, I will be doing a postdoc at CMU working with Prof. Abhinav Gupta and, in the Fall of 2022, I will join the ECE department at the University of Wisconsin Madison as an Assistant Professor. Before UC San Diego, I earned both B.Sc. and M.Sc. degrees from Instituto Superior Técnico, Universidade de Lisboa, Portugal in 2010 and 2012, respectively, where I worked with I worked with Prof. Margarida Silveira.

For up-to-date information about my work, please visit my new webpage.

I am interested in computer vision and machine learning. Specifically, my research focuses on developing learning and deployment frameworks that enable deep learning to operate with restricted labeled data and restricted computing power. As such, I maintain an active interest in areas such as zero-shot, low-shot learning and other transfer learning problems, self-supervised learning, multimodal supervision, and efficient training and deployment procedures.

	Learning to see and hear without human supervision Pedro Morgado University of California San Diego, 2021. Website Thesis
	Robust Audio-Visual Instance Discrimination Pedro Morgado, Ishan Misra and Nuno Vasconcelos IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), 2021. *(Oral presentation)* PDF ArXiv Video BibTeX
	Audio-Visual Instance Discrimination with Cross-Modal Agreement Pedro Morgado, Nuno Vasconcelos and Ishan Misra IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), 2021. *(Best paper award candidate)* Blogpost PDF ArXiv Code Video BibTeX
	Deep Hashing with Hash-Consistent Large Margin Proxy Embeddings Pedro Morgado, Yunsheng Li, Jose Costa Pereira, Mohammad Saberian, Nuno Vasconcelos International Journal of Computer Vision (IJCV), 2020. PDF Springer arXiv BibTeX
	Learning Representations from Audio-Visual Spatial Alignment Pedro Morgado, Yi Li and Nuno Vasconcelos Advances in Neural Information Processing Systems (NeurIPS), 2020. PDF arXiv BibTeX Code Video
	Solving Long-tailed Recognition with Deep Realistic Taxonomic Classifier Tz-Ying Wu, Pedro Morgado, Pei Wang, Chih-Hui Ho and Nuno Vasconcelos European Conference on Computer Vision (ECCV), Glasgow, UK, 2020. Website Arxiv Supp BibTeX Code
	NetTailor: Tuning the Architecture, Not Just the Weights Pedro Morgado and Nuno Vasconcelos IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, 2019. Website PDF BibTeX Code
	PIEs: Pose Invariant Embeddings Chih-Hui Ho, Pedro Morgado, Amir Persekian and Nuno Vasconcelos IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, 2019. Website PDF Supp BibTeX Dataset Code
	Self-Supervised Generation of Spatial Audio for 360° Video Pedro Morgado, Nuno Vasconcelos, Timothy Langlois and Oliver Wang Advances in Neural Information Processing Systems (NeurIPS), Montreal, Canada, 2018. Website PDF arXiv BibTeX Code
	Semantically Consistent Regularization for Zero-Shot Recognition Pedro Morgado and Nuno Vasconcelos IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), Honolulu, Hawai, 2017. Website PDF arXiv BibTeX Code
Minimal neighborhood redundancy maximal relevance: Application to the diagnosis of Alzheimer's disease Pedro Morgado and Margarida Silveira Neurocomputing Vol. 155, pp. 295-308, May, 2015
Predicting conversion from MCI to AD with FDG-PET brain images at different prodromal stages Carlos Cabral, Pedro Morgado, Durval Campos Costa and Margarida Silveira Computers in Biology and Medicine Vol. 58, pp. 101-109, March, 2015
Diagnosis of Alzheimer's disease using 3D Local Binary Patterns Pedro Morgado, Margarida Silveira and Jorge S Marques Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization Vol. 1, April, 2013
Texton-based diagnosis of Alzheimer's disease Pedro Morgado, Margarida Silveira and Durval C Costa IEEE International Workshop on Machine Learning for Signal Processing (MLSP) Southampton, United Kingdom, 2013
Efficient selection of non-redundant features for the diagnosis of Alzheimer's disease Pedro Morgado, Margarida Silveira and Jorge S Marques International Symposium on Biomedical Imaging (ISBI) San Francisco, CA, United States, 2013 (Oral presentation)
Extending Local Binary Patterns to 3D for the diagnosis of Alzheimer's disease Pedro Morgado, Margarida Silveira and Jorge S Marques International Symposium on Biomedical Imaging (ISBI) San Francisco, CA, United States, 2013
Automated Diagnosis of Alzheimer's Disease using PET Images: A study of alternative procedures for feature extraction and selection Pedro Morgado MSc Thesis, Instituto Superior Tecnico Lisboa, Portugal, 2012.

University of California, San Diego
Ph.D. Student in Electrical Engineering

2014-Now
La Jolla, CA, United States

Instituto Superior Técnico M.Sc. in Electrical and Computer Engineering	2012 Lisbon, Portugal
Dissertation: Automated diagnosis of Alzheimer's Diesease using PET images

Instituto Superior Técnico
B.Sc. in Electrical and Computer Engineering

2010
Lisbon, Portugal

	University of California, San Diego Graduate Student Resercher	San Diego, CA United States 2014-Now
	Facebook AI Research Intern Research Scientist	New York, NY United States Summer, 2019
	Adobe Research Intern Research Scientist	Seattle, WA United States Summer, 2017
	Institute for Systems and Robotics Graduate Reserch Assistent	Lisbon Portugal 2012-2014