Matias Mendieta

I am a Ph.D. student in the Center for Research in Computer Vision at the University of Central Florida, advised by Dr. Chen Chen. My research interests are in the areas of machine learning, computer vision, and autonomous systems.

Email / Google Scholar / Github / LinkedIn / CV

Intern Experience

Machine Learning Intern
Apple
Cupertino, CA. May 2023 - Aug. 2023

Investigated generative AI methods for image and video inpainting.

Applied Scientist Intern
Amazon AWS
Santa Clara, CA. May 2022 - Nov. 2022

Conducted computer vision research in self-supervised learning for geospatial foundation models.

Software Engineer Intern
IBM
Durham, NC. May 2018 - Aug. 2018

Designed, integrated, and tested full proxy functionality for a SASP load balancer simulator.

Publications

	Towards Geospatial Foundation Models via Continual Pretraining Matias Mendieta, Boran Han, Xingjian Shi, Yi Zhu, Chen Chen. International Conference on Computer Vision (ICCV), 2023 paper / code
	PGFed: Personalize Each Client’s Global Objective for Federated Learning Jun Luo, Matias Mendieta, Chen Chen, Shandong Wu. International Conference on Computer Vision (ICCV), 2023 Oral Presentation paper / code
	FedPerfix: Towards Partial Model Personalization of Vision Transformers in Federated Learning Guangyu Sun, Matias Mendieta, Jun Luo, Shandong Wu, Chen Chen. International Conference on Computer Vision (ICCV), 2023 paper
	POSTER: A Pyramid Cross-Fusion Transformer Network for Facial Expression Recognition Ce Zheng, Matias Mendieta, Chen Chen. International Conference on Computer Vision (ICCV) AMFG Workshop, 2023. paper / code
	FeatER: An Efficient Network for Human Reconstruction via Feature Map-Based Transformer Ce Zheng, Matias Mendieta, TaoJinnan Yang, Guo-Jun Qi, Chen Chen. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023 paper / code
	Local Learning Matters: Rethinking Data Heterogeneity in Federated Learning Matias Mendieta, Taojiannan Yang, Pu Wang, Minwoo Lee, Zhengming Ding, Chen Chen. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022 Best Paper Finalist, 33 out of 8161 paper / code
	A Lightweight Graph Transformer Network for Human Mesh Reconstruction from 2D Human Pose Ce Zheng, Matias Mendieta, Pu Wang, Aidong Lu, Chen Chen. ACM Multimedia (ACM-MM), 2022. paper / code
	MutualNet: Adaptive ConvNet via Mutual Learning from Different Model Configurations Taojiannan Yang, Sijie Zhu, Matias Mendieta, Pu Wang, Ravikumar Balakrishnan, Minwoo Lee, Tao Han, Mubarak Shah, Chen Chen. IEEE Transaction on Pattern Analysis and Machine Intelligence (TPAMI), 2021 paper / code
	CARPe Posterum: A Convolutional Approach for Real-time Pedestrian Path Prediction Matias Mendieta, Hamed Tabkhi. Association for the Advancement of Artificial Intelligence (AAAI), 2021 paper / code
	3D Human Pose Estimation with Spatial and Temporal Transformers Ce Zheng, Sijie Zhu, Matias Mendieta, Taojiannan Yang, Chen Chen, Zhengming Ding. International Conference on Computer Vision (ICCV), 2021 paper / code
	Mez: An Adaptive Messaging System for Latency-Sensitive Multi-Camera Machine Vision at the IoT Edge Anjus George, Arun Ravindran, Matias Mendieta, Hamed Tabkhi. IEEE Access, 2021 paper
	REVAMP2T: Real-time Edge Video Analytics for Multi-camera Privacy-aware Pedestrian Tracking Christopher Neff, Matias Mendieta*, Shrey Mohan, Mohammadreza Baharani, Sam Rogers, Hamed Tabkhi. IEEE Internet of Things Journal (IoT-J)*, 2020 paper / code / demo
	A Novel Application/Infrastructure Co-design Approach for Real-time Edge Video Analytics Matias Mendieta, Christopher Neff, Daniel Lingerfelt, Christopher Beam, Anjus George, Sam Rogers, Arun Ravindran, Hamed Tabkhi. IEEE SoutheastCon, 2019 paper
	Measuring Compute-Reuse Opportunities for Video Processing Acceleration Andrew Willis, Hamed Tabkhi, Matias Mendieta, Christopher Neff. IEEE SoutheastCon, 2019 paper

Patents

Detection of Genuine Social Media Profiles
Al Chakra, Patricia Bui, Kaji Rashad, Matias Mendieta.
IBM. US10924499B2, 2018

A method, system and computer program product for performing the detection of genuine social media profiles.

Customizing Product Announcements Based on Product Usage
Al Chakra, Jerry Stevens, Matias Mendieta, Patricia Bui, Kaji Rashad.
IBM. US20200143385A1, 2018

A computer-implemented method that includes tracking usage history of a plurality of components of products

Feel free to steal this website's source code. Do not scrape the HTML from this page itself, as it includes analytics tags that you do not want on your own website — use the github code instead. Also, consider using Leonid Keselman's Jekyll fork of this page.