Free Shipping on orders over US$39.99 How to make these links

UCF Researchers Present at Top International Computer Vision, Pattern Recognition Conference


Researchers from UCF’s Center for Research in Computer Vision (CRCV) have a strong showing at one of the world’s leading computer vision conferences.

The annual Computer Vision and Pattern Recognition Conference (CVPR), held recently in New Orleans, was ranked as the fourth top publication venue in all of science.

Mubarak Shah, the director of the CRCV at UCF and a Board of Trustees Chair Professor, organized the event as one of the general chairs of the conference.

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. .

Matias Mendieta, one of Chen’s 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’s Best Paper Award.

Their paper ranked 33street from 8,161 entries from around the world.

The paper, “Local Learning Matters: Rethinking Data Heterogeneity in Federated Learning,” focuses on providing insight for improving the effectiveness of federated learning, which uses collaborative machine learning while keeping new data local and private to a device. The goal is to accelerate the development of robust machine learning models that can be trained without requiring access to private data.

Mendieta says it has impactful applications in various fields, such as medicine, where data often cannot be shared with other entities.

“Attending the oral presentations and poster sessions was meaningful and inspiring,” Mendieta said. “I am grateful for the opportunity to present our work as an oral presentation during the conference.”

Computer science doctoral student Akash Kumar attended and presented his poster at the conference. His work, “End-to-End Semi-Supervised Learning for Video Action Detection,” explores how researchers can approach a problem with fewer labels.

“Video action analysis is a difficult task because it requires a lot of annotated, labeled data, which is very expensive,” says Kumar. “My approach investigates how we can achieve the same level of performance but with less labeled data, specifically, how we can use unlabeled data effectively.”

In addition to experiencing high-quality research and interacting with leading researchers, students were able to communicate with many of the companies in attendance as well. This is especially important to Kumar, who plans to join the industry after he graduates.

“I met many professors who are experts in their respective fields of research, interacted with many companies, and learned which research industries are currently focused on and how they solve real problems that world,” Kumar said. . “It was nice to talk to the senior Ph.D. students who can guide you on how to do research and make constant progress, because they are in the same boat as us. They helped me look at my research problem from a different perspective. “

CRCV group photo of CVPR
Among the attendees, from bottom row (L to R): Sijie Zhu, Natnael Daba, Jyoti Kini, Rajat Modi, Akash Kumar, Matias Mendieta, Alec Kerrigan, Aisha Urooj, Swetha Sirnam, Parth Parag Kulkarni, Tushar Sangam, Adeel Yousaf, Aidean Sharghi, Mahdi M. Kalayeh, and Shervin Ardeshir. From top row (L to R): Jibanul Haque Jiban, James Beetham, Ishan Dave, Rohit Gupta, Moazam Soomro, Aakash Kumar, Mubarak Shah, Gonzalo Vaca, Khurram Soomro, Nasim Souly, Amir Mazaheri, Zacchaeus Scheffer, Arslan Basharat , Afshin Dehghan, Eyasu Semene Mequaanint, Leulseged Tesfaye Alemu, and Berkan Solmaz.

Along with Shah, who acted as a General Co-Chair for the research conference, assistant professors Chen and Rawat both organized a one-day interactive workshop.

Chen’s workshop, “Dynamic Neural Networks Meet Computer Vision,” brought together emerging research in the areas of dynamic deep neural network optimization, predictive control, dynamic neuro-symbolic reasoning and computer vision to discuss the open challenges and opportunities ahead.

Chen is also the lead organizer for the “First International Workshop on Federated Learning for Computer Vision (FedVision),” a workshop on federated learning and how it can help keep information private.

Rawat organized a workshop titled “Strength in Sequential Data.” Resilience is an important step towards developing reliable systems that can be deployed in the real world. This workshop encourages researchers to explore the robustness of models against real-world distributional shifts while operating on video and language-based sequential data.

He is also part of the organization of the “Tiny Actions Challenge,” a focused task in a series of challenges aimed at identifying small, or tiny, actions in low-resolution videos that are not clearly visible.

Over 5,500 people attended the conference in person with another 2,000 participating virtually. It has been on hiatus for three years due to the COVID-19 pandemic.

“We were not sure whether we should do it in person or not, but finally decided to go ahead with a personal conference,” Shah said. “It was a great success.”



Source link

We will be happy to hear your thoughts

Leave a reply

Info Bbea
Logo
Enable registration in settings - general
Compare items
  • Total (0)
Compare
0
Shopping cart