no code implementations • 5 Feb 2025 • Hao Yin, Paritosh Parmar, Daoliang Xu, Yang Zhang, Tianyou Zheng, Weiwei Fu
Action Quality Assessment (AQA) -- the ability to quantify the quality of human motion, actions, or skill levels and provide feedback -- has far-reaching implications in areas such as low-cost physiotherapy, sports training, and workforce development.
1 code implementation • 1 Apr 2024 • Paritosh Parmar, Eric Peh, Ruirui Chen, Ting En Lam, Yuhan Chen, Elston Tan, Basura Fernando
To address this gap, we capitalize on the unique properties of cartoons and construct CausalChaos!, a novel, challenging causal Why-QA dataset built upon the iconic "Tom and Jerry" cartoon series.
3 code implementations • 20 Mar 2024 • Lauren Okamoto, Paritosh Parmar
We found that domain experts prefer our system and find it more informative than purely neural approaches to AQA in diving.
Ranked #1 on
Action Quality Assessment
on FineDiving
Action Quality Assessment
Action Quality Assessment Report Generation
+5
no code implementations • 19 Jan 2024 • Paritosh Parmar, Eric Peh, Basura Fernando
We introduce the novel concept of visually Connecting Actions and Their Effects (CATE) in video understanding.
1 code implementation • 28 Feb 2022 • Paritosh Parmar, Amol Gharat, Helge Rhodin
To that end, we propose to learn exercise-oriented image and video representations from unlabeled samples such that a small dataset annotated by experts suffices for supervised error detection.
1 code implementation • 15 Feb 2021 • Paritosh Parmar, Brendan Morris
We introduce a first of its kind paired win-fail action understanding dataset with samples from the following domains: "General Stunts," "Internet Wins-Fails," "Trick Shots," and "Party Games."
Ranked #1 on
Action Recognition
on Win-Fail Action Understanding
1 code implementation • 13 Jan 2021 • Paritosh Parmar, Jaiden Reddy, Brendan Morris
Can a computer determine a piano player's skill level?
Ranked #1 on
Skills Assessment
on Multimodal PISA
2 code implementations • 10 Dec 2019 • Paritosh Parmar, Brendan Morris
The hallucination task is treated as an auxiliary task, which can be used with any other action related task in a multitask learning setting.
Ranked #5 on
Scene Recognition
on YUP++
5 code implementations • CVPR 2019 • Paritosh Parmar, Brendan Tran Morris
Can performance on the task of action quality assessment (AQA) be improved by exploiting a description of the action and its quality?
Ranked #1 on
Action Recognition
on MTL-AQA
1 code implementation • 15 Dec 2018 • Paritosh Parmar, Brendan Tran Morris
Can learning to measure the quality of an action help in measuring the quality of other actions?
Ranked #7 on
Action Quality Assessment
on AQA-7
2 code implementations • 16 Nov 2016 • Paritosh Parmar, Brendan Tran Morris
Estimating action quality, the process of assigning a "score" to the execution of an action, is crucial in areas such as sports and health care.
no code implementations • 31 Aug 2016 • Paritosh Parmar, Brendan Tran Morris
This work explores the problem of exercise quality measurement since it is essential for effective management of diseases like cerebral palsy (CP).
no code implementations • 19 May 2014 • Paritosh Parmar
Information obtained after processing image according to the proposed method comprises of position of tangles in tangled object and which wire passes over which wire.