Skip to main content

Yogesh S Rawat

Assistant Professor

CRCV | Center for Research in Computer Vision
University of Central Florida
4328 Scorpius St. HEC 241
Orlando, FL 32816-2365

Phone: (407) 823-6495
Email: yogesh[at]crcv.ucf.edu

Research
Our lab studies computer vision, multimedia, and deep learning. We mainly explore the video domain with focus on activity recognition and robust video understanding. We also study the role of multiple modalities in computer vision and how different modalities can be utilized for robust video understanding. Another prime focus of the lab is to utilize large-scale unlabelled datasets with label efficient learning. Other interests include, video synthesis, bio-metrics, and robust video representation learning.
I am looking for a PostDoc for our group, please reach out if you are interested. I am always looking for PhD candidates, please reach out with your resume if you are interested in working with our group.
For recent list of research publications please visit Google Scholar page.

Recent Publications [ All Publications] [ Google Scholar]

Activity-Biometrics: Person Identification from Daily Activities
CVPR 2024
Shehreen Azad, and Yogesh Singh Rawat
[Paper] [Code]

EZ-CLIP: Efficient Zero-shot Video Action Recognition
Arxiv
Shahzad Ahmad, Sukalpa Chanda, Yogesh S Rawat
[Paper] [Code]

Semi-supervised Active Learning for Video Action Detection
AAAI 2024
Ayush Singh, Aayush J Rana, Akash Kumar, Shruti Vyas, Yogesh Singh Rawat
[Paper] [Code]

Revealing the unseen: Benchmarking video action recognition under occlusion
NeurIPS DB Track 2023
Shresth Grover, Vibhav Vineet, Yogesh S Rawat
[Paper] [Code]

On Occlusions in Video Action Detection: Benchmark Datasets And Training Recipes
NeurIPS DB Track 2023
Rajat Modi, Vibhav Vineet, Yogesh S Rawat
[Paper] [Code]

A Large-Scale Robustness Analysis of Video Action Recognition Models
CVPR2023
Madeline C Schiappa, Naman Biyani, Prudvi Kamtam, Shruti Vyas, Hamid Palangi, Vibhav Vineet, Yogesh S Rawat
[Paper] [Code]

Hybrid Active Learning via Deep Clustering for Video Action Detection
CVPR2023
Aayush Rana, Yogesh Rawat
[Paper] [Code]

Self-supervised learning for videos: A survey
ACM Computing Surveys 2023
Madeline Schiappa, Yogesh Rawat, Mubarak Shah
[Paper] [Code]

Are all Frames Equal? Active Sparse Labeling for Video Action Detection
NeurIPS 2022
Aayush Rana, Yogesh Rawat
[Paper] [Code]

Don’t Pour Cereal into Coffee: Differentiable Temporal Logic for Temporal Action Segmentation
NeurIPS 2022
Ziwei Xu, Yogesh Rawat, Yongkang Wong, Mohan Kankanhalli, Mubarak Shah
[Paper] [Code]

Robustness Analysis of Video-Language Models Against Visual and Language Perturbations
NeurIPS Dataset and Benchmarking 2022
Madeline Chantry, Shruti Vyas, Hamid Palangi, Yogesh Rawat, Vibhav Vineet
[Paper] [Code]

End-to-End Semi-Supervised Learning for Video Action Detection
CVPR 2022
Akash Kumar, Yogesh Rawat
[Paper] [Code]


Group Members

Akash Kumar

PhD student

Priyank Pathak

PhD student

Rajat Modi

PhD student

Shehreen Azad

PhD student

Raiyaan Abdullah

PhD student

Mayank Kumar

PhD student

Mohammad Alijanpour

PhD student

Shresth Grover

Intern

Former Members

  • Ayush Rana [PhD Student], Now: Qualcomm
  • Madeline Schiappa [PhD Student], Now:
  • Rahul Ambati [Master Student], Now: Amazon
  • Xianhang Li [Research Assistant], Now: Ph.D student at UC, Santa Cruz
  • Alex Matasa [Master Student], Now: Machine Learning Engineer II at Vadum Inc.
  • Arushi Rai [REU Student], Now: PhD student at University of Pittsburgh
  • Kara Schatz [REU Student], Now: PhD Student at North Carolina State University
  • Erik Quintanilla [REU Student], Now: Software Engineer at Amazon

Sponsors
Intelligence Advanced Research Projects Activity (IARPA)
Defense Advanced Research Projects Agency (DARPA)
National Science Foundation (NSF)
DRS