Naga Venkata Sai Raviteja Chappa
JBHT #447
227 N Harmon Ave
Fayetteville, AR 72701
As a Final Year Ph.D. Candidate in Computer Engineering at the University of Arkansas, I am actively engaged in cutting-edge research within the Computer Vision and Image Understanding Lab, under the mentorship of Prof. Khoa Luu. Prior to embarking on my doctoral journey, I earned an M.S. in Computer Engineering from Purdue University in May 2020 and a B.Tech in ECE from JNTU-K in April 2018.
My research expertise centers on the dynamic intersection of deep learning, machine learning, and their practical applications in the realm of computer vision. With a keen focus on advancing image and video understanding systems, my overarching goal is to cultivate a versatile skill set that seamlessly integrates academic prowess with industry relevance. I aspire to contribute meaningfully as both a proficient engineer and an influential scientist in the field.
News
Oct 28, 2024 | LiGAR paper has been accepted at WACV 2025! |
---|---|
Sep 24, 2024 | Ravi is awarded Cora E. Sanders Memorial Graduate Fellowship. |
Jul 20, 2024 | REACT paper has been accepted to Machine Vision and Applications Journal! |
May 22, 2024 | Hatt-Flow paper has been accepted to Sensors Journal! |
May 12, 2024 | Ravi crossed 50 citations!!! |
Feb 26, 2024 | A paper has been accepted at The Sixteenth Annual IEEE Green Technologies (GreenTech) Conference. |
Aug 15, 2023 | Ravi is awarded Reginald R. “Barney” & Jameson A. Baxter Graduate Fellowship. |
Jun 19, 2023 | SPARTAN paper is awarded 3rd place at CVSports workshop @CVPR 2023! |
Mar 31, 2023 | SPARTAN paper has been accepted at CVPRW 2023. Congrats! |
Aug 15, 2022 | Ravi is awarded Charles Morgan Endowed Chair Graduate Fellowship. |
Jan 16, 2021 | Ravi started his PhD journey @University of Arkansas under supervision of Dr. Khoa Luu! |
May 10, 2020 | Ravi received Master’s degree in Computer Engineering from Purdue University! |
Selected Publications
-
HAtt-Flow: Hierarchical Attention-Flow Mechanism for Group Activity Scene Graph Generation in VideosSensors Journal, 2024
-
REACT: Recognize Every Action Everywhere All At OnceMachine Vision and Applications Journal, 2024
-
SoGAR: Self-supervised Spatiotemporal Attention-based Social Group Activity RecognitionUnder review at IEEE Access Journal, 2023
-
FLAASH: Flow-Attention Adaptive Semantic Hierarchical Fusion for Multi-Modal Tobacco Content AnalysisUnder review at International Journal of Computer Vision, 2024
-
Assessing TikTok Videos Content of Tobacco Usage by Leveraging Deep Learning Methods2024 IEEE Green Technologies Conference (GreenTech), 2024
-
Public Health Advocacy Dataset: A Dataset of Tobacco Usage Videos from Social MediaUnder Review., 2024
-
LiGAR: LiDAR-Guided Hierarchical Transformer for Multi-Modal Group Activity RecognitionarXiv, 2024
-
SPARTAN: Self-Supervised Spatiotemporal Transformers Approach to Group Activity RecognitionIn Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2023
-
-
Otadapt: Optimal transport-based approach for unsupervised domain adaptationIn 2022 26th International Conference on Pattern Recognition (ICPR), 2022
-
Deployment of SE-SqueezeNext on NXP Bluebox 2.0 and NXP i.MX-RT1060 MCUIn 2020 IEEE Midwest Industry Conference (MIC), 2020