Praveen Tirupattur
Recently, I defended my thesis dissertation and will be graduating with a Ph.D. in computer science, from the
Center for Research in
Computer Vision, UCF, under the guidance of Prof. Mubarak Shah.
My research interests span various domains within computer vision and machine learning.
During my doctoral studies, I have focused extensively on tackling diverse challenges in video comprehension using supervised,
weakly supervised, self-supervised, and zero-shot learning. This includes tasks such as action detection, temporal action localization,
and complex activity recognition. I have also worked on anomaly detection, gait recognition, person-Reid, and video understanding using large language models. Experienced in working with deep learning frameworks such as PyTorch, Keras, and Tensorflow.
Email /
CV /
Scholar /
Twitter /
LinkedIn /
Github
|
|
Updates
  August 2024: Graduate with Ph.D in Computer Science, from UCF
  June 2024: Successfully defended my Ph.D dissertation
  December 2023: Paper accepted to AAAI 2024
  May 2023: Started summer internship at Amazon
  October 2022: Patent granted for real-time spatio-temporal activity detection from untrimmed videos
  May 2022: Started summer internship at Pinterest
  March 2021: Paper accepted to CVPR 2021 as an Oral
  January 2021: Our Gabriella paper has been awarded the best scientific paper award at ICPR 2020
  June 2020: Placed first at ActEV SDL Challenge (ActivityNet workshop at CVPR 2020)
  October 2019: Placed second at the TRECVID leaderboard
  August 2018: Paper accepted to ACM MM 2018
|
|
Video action detection: Analysing limitations and challenges
Rajat Modi,
Aayush Jung Rana,
Akash Kumar,
Praveen Tirupattur,
Shruti Vyas,
Yogesh S Rawat,
Mubarak Shah
CVPR, 2022
arxiv /
code /
bibtex
Our work delves into attributes measuring dataset quality for video action detection, probing existing datasets' limitations and proposing the Multi Actor Multi Action (MAMA) dataset, addressing real-world application needs. We conduct a biasness study examining the temporal aspect's significance, questioning assumptions on temporal ordering's importance, revealing biases despite meticulous modeling.
|
|
Modeling Multi-Label Action Dependencies for Temporal Action Localization
Praveen Tirupattur,
Kevin Duarte,
Yogesh S Rawat,
Mubarak Shah
CVPR, 2021 (Oral presentation; in top 2.5%)
arxiv /
code /
bibtex /
slides
/
video
We propose an attention-based architecture to capture action relationships in the context of
temporal action localization within untrimmed videos. Our approach discerns between relationships
among actions unfolding simultaneously and those occurring at different time steps, labeling them as
distinct action dependencies. To enhance action localization performance, we introduce a novel
Multi-Label Action Dependency (MLAD) layer, leveraging attention mechanisms to model these intricate
dependencies.
|
|
TinyAction Challenge: Recognizing Real-world Low-resolution Activities in Videos
Praveen Tirupattur,
Aayush Jung Rana,
Tushar Sangam,
Shruti Vyas,
Yogesh S Rawat,
Mubarak Shah
CVPR, 2021
arxiv /
dataset /
bibtex /
web page
This paper outlines the TinyAction Challenge held at CVPR 2021, focusing on recognizing real-world
low-resolution activities in security videos. It introduces the benchmark dataset TinyVIRAT-v2, an
extension of TinyVIRAT, featuring naturally occurring low-resolution actions from security videos.
The challenge aims to address the difficulty of action recognition in tiny regions, providing a
benchmark for state-of-the-art methods.
|
|
Gabriella: An Online System for Real-Time Activity Detection in Untrimmed Security
Videos
Mamshad Nayeem Rizve, Ugur Demir, Praveen Tirupattur, Aayush Jung Rana, Kevin Duarte, Ishan Dave, Yogesh S Rawat, Mubarak Shah
ICPR, 2020 (Best paper award)
arxiv /
project
page /
bibtex /
slides
/
video
Gabriella consists of three stages: tubelet extraction, activity classification, and online
tubelet merging. Gabriella utilizes a localization network for tubelet extraction, with a novel
Patch-Dice loss to handle variations in actor size, and a Tubelet-Merge Action-Split (TMAS)
algorithm to detect activities efficiently and robustly.
|
|
ThoughtViz: Visualizing Human Thoughts Using Generative Adversarial Network
Praveen Tirupattur,
Yogesh S Rawat,
Concetto Spampinato,
Mubarak Shah
ACM MM, 2018
code /
bibtex /
poster
This paper explores decoding and visualizing human thoughts through Brain Computer Interface (BCI)
research.
Using ElectroEncephaloGram (EEG) signals, the proposed conditional Generative Adversarial Network
(GAN) effectively synthesizes visual representations of specific thoughts, such as digits,
characters, or objects.
The study showcases the potential of extracting meaningful visualizations from limited EEG data,
demonstrating the explicit encoding of thoughts in brain signals for semantically relevant image
generation.
|
|
Research Scientist Intern
Amazon Inc., Palo Alto, California, USA. May 2023- Nov 2023
Mentor: Jay Krishnan
Worked on representation learning for long-form video understanding with vision-language training. Explored
the idea of leveraging pre-trained Large Language Models (LLMs) to improve temporal understanding
of video models.
|
|
Research Scientist Intern
Pinterest Inc., Remote, USA. May 2022 - Aug 2022
Mentor: Rex Wu
Worked on building a unified model for both image and video representation learning. Explored large-scale
self-supervised training to learn representations for multiple visual modalities. Obtained improved
performance over the in-house image-based model using the multi-modal training.
|
Achievements and Awards
![Trophy Image](images/trophy.png) |
1st place, 2021 -
PMiss@0.02tfa, ActivityNet ActEV SDL (CVPR)
1st place, 2020 -
PMiss and nAUDC, ActivityNet ActEV SDL (CVPR)
Best Paper Award, 2020 -
International Conference on Pattern Recognition ( ICPR )
ORCGS Doctoral Fellowship, 2017 - University of Central Florida
|
![](images/cvf.jpeg) |
Organizer, Tiny Actions Workshop (CVPR
2022)
Organizer, Tiny Actions Workshop (CVPR
2021)
Reviewer, CVPR 2024, 2023, 2022
Reviewer, ICCV 2023
Reviewer, ECCV 2022
Reviewer, CVIP 2022, 2023
Reviewer, IEEE Transaction
on Image Processing
Reviewer, IEEE
Transactions on Multimedia
Reviewer, Machine Vision and Applications
|
|