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.
News
- (Mar 2025) Awarded a OVCR Fall Research Competition grant. Thank you OVCR for supporting our research.
- (Feb 2025) Our paper on Efficient curricula for MIM models accepted at CVPR 2025.
- (Oct 2024) Our paper on Accelerating the pretraining of vision transformers accepted at NeurIPS 2024.
- (Sep 2024) Serving as Area Chair at CVPR 2025.
- (Jul 2024) Three papers accepted at ECCV 2024 on Audio-guided video generation, Language-driven ZSL and Latent MIM.
- (Jun 2024) Serving as Area Chair at CVPR and NeurIPS 2024.
- (Mar 2024) We've received a research gift from Adobe. Thank you for supporting our work!
- (Feb 2024) Paper on the early-fusion audio-visual transformers accepted at CVPR 2024.
- (Jul 2023) Paper on the robustness of prompt-tuning accepted at ICCV 2023.
- (Jun 2023) Invited talk at the ML4MI Seminar Series @ University of Wisconsin-Madison.
- (Apr 2023) Paper on unified audio-visual modeling (OneAVM) accepted at ICML 2023.
Research Group
PhD Students
- Cheng-En Wu (w/ Yu Hen Hu)
- Yibing Wei
- Lin Zhang
MSc/Undergrad Students
- Jinhong (Jones) Lin
- Yijing Zhang
- Eleanna Panagiotou
External Student Collaborators
- Shentong Mo (CMU)
Teaching
- SP 2025 - CS/ECE 539: Intro to Artificial Neural Networks
- FA 2024 - ECE 204 Data Science & Engineering
- SP 2024 - CS/ECE 766: Computer Vision
- FA 2023 - CS/ECE 539: Intro to Artificial Neural Networks
- SP 2023 - CS/ECE/ME 532: Matrix Methods in Machine Learning
- FA 2022 - CS/ECE/ME 532: Matrix Methods in Machine Learning
Publications
From Prototypes to General Distributions: An Efficient Curriculum for Masked Image Modeling
Conf. on Computer Vision and Pattern Recognition (CVPR), Nashville, 2025.
@InProceedings{lin2025prototypes,
title={From Prototypes to General Distributions: An Efficient Curriculum for Masked Image Modeling},
author={Jinhong Lin and Cheng-En Wu and Huanran Li and Jifan Zhang and Yu Hen Hu and Pedro Morgado},
booktitle={IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR)},
year={2025}
}
Patch Ranking: Token Pruning as Ranking Prediction for Efficient CLIP Inference
Winter Conference on Applications of Computer Vision (WACV), Tucson, 2025.
@InProceedings{chengen2025pruning,
title={Patch Ranking: Token Pruning as Ranking Prediction for Efficient CLIP Inference},
author={Cheng-En Wu and Jinhong Lin and Yu-Hen Yu and Pedro Morgado},
booktitle={IEEE/CVF Winter Applications in Computer Vision (WACV)},
year={2025}
}
Accelerating Augmentation Invariance Pretraining
Neural Information Processing Systems (NeurIPS), Vancouver, 2024.
@InProceedings{lin2024fastcl,
title={Accelerating Augmentation Invariance Pretraining},
author={Jinhong Lin and Cheng-En Wu and Yibing Wei and Pedro Morgado},
booktitle={Advances in Neural Information Processing Systems (NeurIPS)},
year={2024}
}
Towards Latent Masked Image Modeling for Self-Supervised Visual Representation Learning
European Conference on Computer Vision (ECCV), Milan, 2024.
@InProceedings{wei2024lmim,
title={Towards Latent Masked Image Modeling for Self-Supervised Visual Representation Learning},
author={Yibing Wei and Abhinav Gupta and Pedro Morgado},
booktitle={European Conference on Computer Vision (ECCV)},
year={2024}
}
Audio-Synchronized Visual Animation
European Conference on Computer Vision (ECCV), Milan, 2024.
paper code website bibtex Oral presentation
@InProceedings{zhang2024asva,
title={Audio-Synchronized Visual Animation},
author={Lin Zhang, Shentong Mo, Yijing Zhang, Pedro Morgado},
booktitle={European Conference on Computer Vision (ECCV)},
year={2024}
}
Audio-visual Generalized Zero-shot Learning the Easy Way
European Conference on Computer Vision (ECCV), Milan, 2024.
@InProceedings{mo24avzsl,
title={Audio-visual Generalized Zero-shot Learning the Easy Way},
author={Mo, Shentong and Morgado, Pedro},
booktitle={European Conference on Computer Vision (ECCV)},
year={2024}
}
Unveiling the Power of Audio-Visual Early Fusion Transformers with Dense Interactions through Masked Modeling
Conf. on Computer Vision and Pattern Recognition (CVPR), Seattle, 2024.
@InProceedings{mo2024_efav,
title={Unveiling the Power of Audio-Visual Early Fusion Transformers with Dense Interactions through Masked Modeling},
author={Shentong Mo, Pedro Morgado},
booktitle={IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR)},
year={2024}
}
A Unified Audio-Visual Learning Framework for Localization, Separation, and Recognition
International Conference on Machine Learning (ICML), Honolulu, 2023.
@InProceedings{mo2022_slavc,
title={A Unified Audio-Visual Learning Framework for Localization, Separation, and Recognition},
author={Shentong Mo, Pedro Morgado},
booktitle={Proceedings of the 40th International Conference on Machine Learning (ICML)},
year={2023}
}
Prompt Tuning Vision Language Models is Robust to Noisy Labels
International Conference on Computer Vision (ICCV), Paris, 2023.
@InProceedings{wu2023_robust_pt,
title={Why Is Prompt Tuning for Vision-Language Models Robust to Noisy Labels?},
author={Cheng-En Wu, Yu Tian, Haichao Yu, Heng Wang, Pedro Morgado, Yu Hen Hu, Linjie Yang},
booktitle={International Conference in Computer Vision (ICCV)},
year={2023}
}
A Closer Look at Weakly-Supervised Audio-Visual Source Localization
Neural Information Processing Systems (NeurIPS), New Orleans, 2022.
@InProceedings{mo2022_slavc,
title={A Closer Look at Weakly-Supervised Audio-Visual Source Localization},
author={Shentong Mo, Pedro Morgado},
booktitle={Advances in Neural Information Processing Systems (NeurIPS)},
year={2022}
}
Learning Visual Representation from Audible Interactions
Neural Information Processing Systems (NeurIPS), New Orleans, 2022.
@InProceedings{mittal2022_replai,
title={Learning Visual Representation from Audible Interactions},
author={Himangi Mittal, Pedro Morgado, Unnat Jain, Abhinav Gupta},
booktitle={Advances in Neural Information Processing Systems (NeurIPS)},
year={2022}
}
Benchmarking and Automating the Image Recognition Capability of an In Situ Plankton Imaging System
Frontiers in Marine Science, 2022.
@InProceedings{le2022_plankton_bench,
title={Benchmarking and Automating the Image Recognition Capability of an In Situ Plankton Imaging System},
author={Kevin T. Le, Zhouyuan Yuan, Areeb Syed, Devin Ratelle, Eric C. Orenstein, Melissa L. Carter, Sarah Strang, Kasia M. Kenitz, Pedro Morgado, Peter J. S. Franks, Nuno Vasconcelos and Jules S. Jaffe},
booktitle={Frontiers in Marine Science},
year={2022}
}
The Challenges of Continuous Self-Supervised Learning
European Conference on Computer Vision (ECCV), Tel Aviv, 2022.
paper code data video bibtex Oral presentation
@InProceedings{purushwalkam2022_continuous_ssl,
title={The Challenges of Continuous Self-Supervised Learning},
author={Senthil Purushwalkam, Pedro Morgado, Abhinav Gupta},
booktitle={European Conference on Computer Vision (ECCV)},
year={2022}
}
Localizing Visual Sounds the Easy Way
European Conference on Computer Vision (ECCV), Tel Aviv, 2022.
@InProceedings{mo2022_ezvsl,
title={Localizing Visual Sounds the Easy Way},
author={Shentong Mo, Pedro Morgado},
booktitle={European Conference on Computer Vision (ECCV)},
year={2022}
}
Learning to see and hear without human supervision
PhD Thesis, University of California San Diego, 2021.
@phdthesis{morgado_phdthesis,
author = {Pedro Morgado},
title = {Learning to see and hear without human supervision},
school = {University of California San Diego},
year = 2021
}
Robust Audio-Visual Instance Discrimination
Conf. on Computer Vision and Pattern Recognition (CVPR), 2021.
paper video bibtex Oral presentation
@InProceedings{morgado2021_robust_xid,
title={Robust Audio-Visual Instance Discrimination},
author={Pedro Morgado, Ishan Misra, Nuno Vasconcelos},
booktitle={Computer Vision and Pattern Recognition (CVPR), IEEE/CVF Conf. on },
year={2021}
}
Audio-Visual Instance Discrimination with Cross-Modal Agreement
Conf. on Computer Vision and Pattern Recognition (CVPR), 2021.
paper code video blogpost bibtex Best paper candidate
@InProceedings{morgado2021avid,
title={Audio-Visual Instance Discrimination with Cross-Modal Agreement},
author={Pedro Morgado, Nuno Vasconcelos, Ishan Misra},
booktitle={Computer Vision and Pattern Recognition (CVPR), IEEE/CVF Conf. on },
year={2021}
}
Audio-Visual Instance Discrimination
ECCV Workshop - Multi-Modal Video Analysis, 2020.
Learning Representations from Audio-Visual Spatial Alignment
Neural Information Processing Systems (NeurIPS), 2020.
@inproceedings{morgadoNIPS20,
title={Learning Representations from Audio-Visual Spatial Alignment},
author={Pedro Morgado, Yi Li, Nuno Vasconcelos},
booktitle={Advances in Neural Information Processing Systems (NeurIPS)},
year={2020}
}
[Workshop] Learning Representations from Audio-Visual Spatial Alignment
CVPR Workshop - Sight and Sound, 2021.
Deep Hashing with Hash-Consistent Large Margin Proxy Embeddings
International Journal of Computer Vision (IJCV), 2020.
@article{MorgadoProxyHashing,
author = {Morgado, Pedro and Li, Yunsheng and Costa Pereira, Jose and Saberian, Mohammad and Vasconcelos, Nuno},
journal = {International Journal of Computer Vision},
title = {Deep Hashing with Hash-Consistent Large Margin Proxy Embeddings},
year = {2020},
doi = {10.1007/s11263-020-01362-7},
isbn = {1573-1405},
url = {https://doi.org/10.1007/s11263-020-01362-7}
}
Solving Long-tailed Recognition with Deep Realistic Taxonomic Classifier
European Conference on Computer Vision (ECCV), 2020.
paper suppl code website video bibtex
@inproceedings{Wu20DeepRTC,
title={Solving Long-tailed Recognition with Deep Realistic Taxonomic Classifier},
author={Tz-Ying Wu and Pedro Morgado and Pei Wang and Chih-Hui Ho and Nuno Vasconcelos},
booktitle={European Conference on Computer Vision (ECCV)},
year={2020}
}
NetTailor: Tuning the Architecture, Not Just the Weights
Conf. on Computer Vision and Pattern Recognition (CVPR), Long Beach, 2019.
@inproceedings{morgado2019nettailor,
title={NetTailor: Tuning the Architecture, Not Just the Weights},
author={Morgado, Pedro and Vasconcelos, Nuno},
booktitle={Computer Vision and Pattern Recognition (CVPR), IEEE/CVF Conf. on},
pages={3044--3054},
year={2019}
}
[Workshop] NetTailor: Tuning the Architecture, Not Just the Weights
Southern California Machine Learning Symposium (SCMLS), 2020.
assets/publications/2019-nettailor/scmls20_ref.txt
PIEs: Pose Invariant Embeddings
Conf. on Computer Vision and Pattern Recognition (CVPR), Long Beach, 2019.
paper suppl code data website bibtex
@InProceedings{Ho_2019_CVPR,
author = {Ho, Chih-Hui and Morgado, Pedro and Persekian, Amir and Vasconcelos, Nuno},
title = {PIEs: Pose Invariant Embeddings},
booktitle = {Computer Vision and Pattern Recognition (CVPR), IEEE/CVF Conf. on },
month = {June},
year = {2019}
}
Self-Supervised Generation of Spatial Audio for 360° Video
Neural Information Processing Systems (NeurIPS), Montreal, 2018.
paper suppl code data website video bibtex
@inproceedings{morgadoNIPS18,
title={Self-Supervised Generation of Spatial Audio for 360° Video},
author={Pedro Morgado, Nuno Vasconcelos, Timothy Langlois and Oliver Wang},
booktitle={Advances in Neural Information Processing Systems (NeurIPS)},
year={2018}
}
Semantically Consistent Regularization for Zero-Shot Recognition
Conf. on Computer Vision and Pattern Recognition (CVPR), Honolulu, 2017.
@inproceedings{morgadoCVPR17,
title={Semantically Consistent Regularization for Zero-Shot Recognition},
author={Pedro Morgado and Nuno Vasconcelos},
booktitle={Computer Vision and Pattern Recognition (CVPR), IEEE/CVF Conf.~on},
year={2017},
organization={IEEE}
}
Minimal Neighborhood Redundancy Maximal Relevance: Application to the Diagnosis of Alzheimer's Disease
Neurocomputing, Vol. 155, pp. 295-308, May, 2015.
@article{morgado2015minimal,
title={Minimal neighborhood redundancy maximal relevance: Application to the diagnosis of Alzheimer׳ s disease},
author={Morgado, Pedro M and Silveira, Margarida and Alzheimer׳ s Disease Neuroimaging Initiative and others},
journal={Neurocomputing},
volume={155},
pages={295--308},
year={2015},
publisher={Elsevier}
}
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
@inproceedings{Morgado:ISBI2013,
title={Efficient selection of non-redundant features for the diagnosis of Alzheimer's disease},
author={Morgado, Pedro M and Silveira, Margarida and Marques, Jorge S},
booktitle={IEEE 10th International Symposium on Biomedical Imaging},
year={2013}
}
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
@article{cabral2015predicting,
title={Predicting conversion from MCI to AD with FDG-PET brain images at different prodromal stages},
author={Cabral, Carlos and Morgado, Pedro M and Costa, Durval Campos and Silveira, Margarida and Alzheimer׳ s Disease Neuroimaging Initiative and others},
journal={Computers in biology and medicine},
volume={58},
pages={101--109},
year={2015},
publisher={Elsevier}
}
Texton-based Diagnosis of Alzheimer's Disease
IEEE Int. Workshop on Machine Learning for Signal Processing (MLSP), Southampton, 2013.
@inproceedings{Morgado:MLSP13,
title={Texton-based diagnosis of Alzheimer's disease},
author={Pedro Morgado, Margarida Silveira and Durval Campos Costa},
booktitle={Machine Learning for Signal Processing (MLSP), 2013 IEEE International Workshop on},
year={2013},
organization={IEEE}
}
Diagnosis of Alzheimer's disease using 3D Local Binary Patterns
Computer Methods in Biomechanics and Biomedical Engineering: Imaging Visualization, Vol. 1, April, 2013
@article{morgado2013diagnosis,
title={Diagnosis of Alzheimer's disease using 3D local binary patterns},
author={Morgado, Pedro and Silveira, Margarida and Marques, Jorge S},
journal={Computer Methods in Biomechanics and Biomedical Engineering: Imaging Visualization},
volume={1},
number={1},
pages={2--12},
year={2013},
publisher={Taylor Francis}
}
Extending Local Binary Patterns to 3D for the Diagnosis of Alzheimer's Disease
International Symposium on Biomedical Imaging (ISBI), San Francisco, 2013.
@inproceedings{Morgado:ISBI2013b,
title={Extending Local Binary Patterns to 3D for the diagnosis of Alzheimer's disease},
author={Morgado, Pedro M and Silveira, Margarida and Marques, Jorge S},
booktitle={IEEE 10th International Symposium on Biomedical Imaging},
year={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.
@masterthesis{morgado_mscthesis,
author = {Pedro Morgado},
title = {Automated Diagnosis of Alzheimer's Disease using PET Images: A study of alternative procedures for feature extraction and selection},
school = {Instituto Superior Tecnico, Lisboa, Portugal},
year = 2012
}