{"id":129743,"date":"2022-08-01T09:52:42","date_gmt":"2022-08-01T13:52:42","guid":{"rendered":"https:\/\/www.ucf.edu\/news\/?p=129743"},"modified":"2022-08-03T16:21:58","modified_gmt":"2022-08-03T20:21:58","slug":"ucf-researchers-present-at-top-international-computer-vision-pattern-recognition-conference","status":"publish","type":"post","link":"https:\/\/www.ucf.edu\/news\/ucf-researchers-present-at-top-international-computer-vision-pattern-recognition-conference\/","title":{"rendered":"UCF Researchers Present at Top International Computer Vision, Pattern Recognition Conference"},"content":{"rendered":"

Researchers from UCF\u2019s Center for Research in Computer Vision (CRCV) had a strong showing at one of the top computer vision conferences in the world.<\/p>\n

The annual Computer Vision and Pattern Recognition Conference (CVPR), which was held recently in New Orleans, is ranked as the fourth top publication venue among all sciences.<\/p>\n

Mubarak Shah, UCF\u2019s CRCV director and a Board of Trustees Chair Professor, organized the event as one of the conference\u2019s general chairs.<\/p>\n

Shah, along with three other CRCV faculty members, Department of Computer Science assistant professors Chen Chen and Yogesh Rawat, Department of Electrical and Computer Engineering Professor Nazanin Rahnavard, and 32 doctoral students and alumni, traveled more than 600 miles to experience the conference in person.<\/p>\n

Matias Mendieta, one of Chen\u2019s doctoral students, along with doctoral student Taojiannan Yang and researchers from Tulane University and the University of North Carolina at Charlotte, were finalists for the conference\u2019s Best Paper Award.<\/p>\n

Their paper ranked 33rd<\/sup> out of 8,161 entries from across the globe.<\/p>\n

The paper, \u201cLocal Learning Matters: Rethinking Data Heterogeneity in Federated Learning,\u201d is focused on providing insight for improving efficacy of federated learning, which is using collaborative machine learning<\/a> while keeping new data local and private to a single device. The goal is to facilitate the development of strong machine learning models that can be trained without requiring access to private data.<\/p>\n

Mendieta says this has impactful applications in various fields, such as medicine, where data often cannot be shared with other entities.<\/p>\n

\u201cAttending the oral presentations and poster sessions was insightful and inspiring,\u201d Mendieta says. \u201cI was grateful for the opportunity to present our work as an oral presentation during the conference.\u201d<\/p>\n

Computer science doctoral student Akash Kumar attended and presented his poster at the conference. His work, \u201cEnd-to-End Semi-Supervised Learning for Video Action Detection,\u201d explores how researchers can approach a problem with fewer labels.<\/p>\n

\u201cVideo-action detection is a difficult task since it requires a lot of annotated, labeled data, which is extremely expensive,\u201d Kumar says. \u201cMy approach investigates how we can achieve the same performance level but with much less labeled data, especially, how we can utilize unlabeled data efficiently.\u201d<\/p>\n

In addition to experiencing high quality research and interacting with top researchers, students were able to speak with the numerous companies also in attendance. This was particularly important to Kumar, who plans to join industry after he graduates.<\/p>\n

\u201cI got to meet many professors who are experts in their respective research field, interacted with a lot of companies, and got to know what research industries are currently focused on and how they are tackling those problems in the real-world,\u201d Kumar says. \u201cIt was nice to talk with senior Ph.D. students who can guide you how to do research and make consistent progress, since they are in the same boat as us. They helped me look at my research problem from a different perspective.\u201d<\/p>\n