Sathyanarayanan N. Aakur

Highlights and News

Spring'23: Serving as Area Chair for NeurIPS 2023!
Spring'23: One paper on Scene Graph Generation accepted at CVPR 2023. Congrats to Sanjoy on his first CVPR paper and third overall. Preprint here
Spring'23: Received funding from USDA for multimodal time series classification for stress detection in precision agriculture!
Fall'22: Serving as Area Chair for CVPR 2023 !
Summer'22: Two papers accepted at ECCV 2022!
Spring'22: Received the prestigious NSF CAREER award to pursue research on multi-modal event understanding!
Spring'22: One paper on self-distillation for commonsense question answering accepted to ICPR 2022! Congrats to my student Priya on her first paper!
Spring'22: One paper on open world action recognition in egocentric videos accepted to Pattern Recognition Letters! Congrats to my student Sanjoy on his second paper!
Fall'21: One paper on using building an active vision system for action localization with embodied agents is accepted at WACV 2022! Congrats to my student Shubham on his first paper!
Fall'21: Book chapter with Ramy Mounir and Dr. Sudeep Sarkar on event understanding to appear in Elsevier Series on Computer Vision and Pattern Recognition!
Fall'21: One paper on using transformers for metagenome analysis accepted at the ICDM 2021 Workshops! Preprint coming soon!
Fall'21: Invited as Associate Editor for IEEE RA-L!
Summer'21: One paper on Leveraging Pseudo-Imaging for Multi-Modal Metagenome Analysis has been accepted at MICCAI 2021!
Spring'21: I will be an Area Chair for CVPR 2022 and ACM Multimedia 2021!
Spring'21: One paper on using Adversarial Co-Training for Sim2Real transfer in Metagenome analysis has been accepted at PAKDD 2021! Congrats Vineela and Vennela! Preprint coming soon!
Fall'20: Invited as reviewer for CVPR 2021, ICML 2021, CRV 2021, ICCV 2021.
Fall'20: One paper on Unsupervised Gaze Prediction in Egocentric Videos with Pattern Theory has been accepted at VISAPP 2021! Initial preprint can be found here.
Fall'20: One paper on Genome Sequence Classification for Animal Diagnostics with Deep Learning accepted at ICMLA 2020! Preprint can be found here!
Fall'20: One paper on Benchmarking Object Detection models on Resource Constrained Domains accepted at AIPR 2020! Congrats Sanjoy and Nikhil! Preprint coming soon!
Summer'20: Awarded NSF Medium Proposal for Self-Supervised Event Understanding in Streaming Videos! It is a collaborative effort with Dr. Sudeep Sarkar (USF) and Dr. Anuj Srivastava (FSU). More details to follow!

About Me

I am an Assistant Professor of Computer Science at Oklahoma State University.

I received my PhD from University of South Florida, where I worked with Dr. Sudeep Sarkar in the Computer Vision and Pattern Recognition Group and with Dr. Kenneth Malmberg. I received my Master's degree in Management Information Systems from the Muma College of Business at the University of South Florida and my undergraduate degree in Electronics and Communication Engineering from Velammal Engineering College, Anna University, India.

Research

In my research, I’m broadly interested in the intersection of computer vision, natural language processing and psychology: I aim to build intelligent agents that understand the visual world beyond recognition (labels) or captions (sentences) without the need for explicit human supervision through expensive annotations.

This entails developing approaches that do things such as:

self-supervised predictive learning for video event segmentation
commonsense reasoning to ground perception and prior knowledge
generative modeling for building knowledge from the ground-up

Much of my group's current work focuses on analyzing, modeling, and synthesizing complex video scenes and the semantic structure that can describe them. I also work on applying machine learning to other domains such as IoT security and running deep learning algorithms on constrained platforms like FPGA.

Group

I lead the Computer Vision and Understanding Lab. Here are the current and past members:

Students

Sanjoy Kundu, PhD student (Spring 2020 — Present)
Shubham Trehan, PhD student (Fall 2020 — Present)
Priyadharsini Ramamurthy, PhD student (Fall 2020 — Present)
Shengfang Ma, M.S. student (Fall 2021 — Present)
Yashwanth Peddaboina, M.S. student (Fall 2021 — Present)
Devyn Hubabrd, B.S. student (Spring 2022 — Present)
Uddhav Ramachandran, High School Intern, then B.S. C.S. (Fall 2020 — Present)

Past Students

Vineela Indla, M.S. student (Fall 2020 — Fall 2021). First Job: SDE, Amazon
Makenzie Terrell, B.S. student (Fall 2020 — Fall 2021)
Nikhil Gunti, MS student (Fall 2019 — Spring 2021). First Job: Data Scientst, Concat Systems

Funding

Our research is supported by the following:

OSU Core Facility Support Program with Pratul Agarwal
USDA NAHLN with Akhilesh Ramachandran and Arunkumar Bagavathi
National Science Foundation

Talks

Latent Space Modeling for Cloning Encrypted PUF-based Authentication. IFIP International Internet of Things (IoT) Conference, Fall 2019
The Role of Commonsense Reasoning in Visual Understanding. Oklahoma State University. Fall 2018
Going Deeper with Semantics: Exploiting Semantic Contextualization for Interpretation of Human Activity in Videos. Technical Seminar Series, Statistical Shape Analysis and Modeling Group, Florida State University. Fall 2018
Video Event Understanding with Pattern Theory. Robotics Technical Seminar Series, Department of Mechanical Engineering,University of South Florida. Spring 2018
Inherently Explainable Model for Video Activity Recognition. AAAI Workshop On Reasoningand Learning for Human-Machine Dialogues, 2018
Leveraging ConceptNet to Reduce Training Requirements for Video Descriptions, Seminar in AI, University of South Florida, Spring 2017
Towards a Knowledge-based Approach to Video Comprehension. Conference on Computer and Robot Vision (CRV), Spring 2017