1 code implementation • 25 Oct 2023 • Soroush Mehraban, Vida Adeli, Babak Taati
Our proposed GCNFormer module exploits the local relationship between adjacent joints, outputting a new representation that is complementary to the transformer output.
Ranked #1 on 3D Human Pose Estimation on MPI-INF-3DHP
1 code implementation • 22 Aug 2023 • Caroline Malin-Mayor, Vida Adeli, Andrea Sabo, Sergey Noritsyn, Carolina Gorodetsky, Alfonso Fasano, Andrea Iaboni, Babak Taati
In this work we train a deep neural network to map from a two dimensional pose sequence, extracted from a video of an individual walking down a hallway toward a wall-mounted camera, to a set of three-dimensional spatiotemporal gait features averaged over the walking sequence.
1 code implementation • NeurIPS 2023 • Saeid Naeini, Raeid Saqur, Mozhgan Saeidi, John Giorgi, Babak Taati
In this paper we present the novel Only Connect Wall (OCW) dataset and report results from our evaluation of selected pre-trained language models and LLMs on creative problem solving tasks like grouping clue words by heterogeneous connections, and identifying correct open knowledge domain connections in respective groups.
Ranked #1 on Only Connect Walls Dataset Task 1 (Grouping) on OCW (# Correct Groups metric, using extra training data)
Only Connect Walls Dataset Task 1 (Grouping) Only Connect Walls Dataset Task 2 (Connections)
no code implementations • 22 Aug 2022 • Saeid Alavi Naeini, Leif Simmatis, Deniz Jafari, Diego L. Guarin, Yana Yunusova, Babak Taati
Computer vision techniques can help automate or partially automate clinical examination of orofacial impairments to provide accurate and objective assessments.
2 code implementations • 7 May 2021 • Andrea Sabo, Sina Mehdizadeh, Andrea Iaboni, Babak Taati
This work leverages novel spatial-temporal graph convolutional network (ST-GCN) architectures and training procedures to predict clinical scores of parkinsonism in gait from video of individuals with dementia.
1 code implementation • 8 Jan 2021 • Siavash Rezaei, Abhishek Moturu, Shun Zhao, Kenneth M. Prkachin, Thomas Hadjistavropoulos, Babak Taati
However, existing computer vision techniques for pain detection are not validated on faces of older adults or people with dementia, and this population is not represented in existing facial expression datasets of pain.
Ranked #1 on Pain Intensity Regression on UNBC-McMaster ShoulderPain dataset (Pearson Correlation Coefficient metric)
no code implementations • 18 Mar 2020 • Diego L. Guarin, Aidan Dempster, Andrea Bandini, Yana Yunusova, Babak Taati
We are developing an automated system for assessment of orofacial function in PD that can be used in-home or in-clinic and can provide useful and objective clinical information that informs disease management.
no code implementations • 25 Oct 2019 • Diego L. Guarin, Yana Yunusova, Babak Taati, Joseph R Dusseldorp, Suresh Mohan, Joana Tavares, Martinus M. van Veen, Emily Fortier, Tessa A. Hadlock, Nate Jowett
Objective: To develop an ML algorithm for accurate facial landmarks localization in photographs of facial palsy patients, and use it as part of an automated computer-aided diagnosis system.
no code implementations • 17 May 2019 • Azin Asgarian, Shun Zhao, Ahmed B. Ashraf, M. Erin Browne, Kenneth M. Prkachin, Alex Mihailidis, Thomas Hadjistavropoulos, Babak Taati
We perform our evaluation not only on frontal faces but also on profile faces and in various regions of the face.
no code implementations • 3 Dec 2018 • Azin Asgarian, Parinaz Sobhani, Ji Chao Zhang, Madalin Mihailescu, Ariel Sibilia, Ahmed Bilal Ashraf, Babak Taati
Transfer learning can help overcome this issue by transferring the knowledge from readily available datasets (source) to a new dataset (target).
no code implementations • 3 Dec 2018 • Ahmed Ashraf, Shehroz Khan, Nikhil Bhagwat, Mallar Chakravarty, Babak Taati
As a result, machine learning models do not generalize even when trained on imaging datasets that were captured to study the same variable of interest.
no code implementations • 28 Aug 2017 • Azin Asgarian, Ahmed Bilal Ashraf, David Fleet, Babak Taati
We propose a subspace transfer learning method, in which we select a subspace from the source that best describes the target space.
1 code implementation • 25 Jul 2017 • Michael H. Li, Tiago A. Mestre, Susan H. Fox, Babak Taati
Conclusion: This paper presents the first application of deep learning for vision-based assessment of parkinsonism and LID and demonstrates promising performance for the future translation of deep learning to PD clinical practices.
no code implementations • 26 Oct 2016 • Babak Taati, Pranay Lohia, Avril Mansfield, Ahmed Ashraf
The analysis explores: computing spatiotemporal parameters of gait in a video captured from an arbitrary viewpoint; the relationship between parameters of gait from the last few steps before the obstacle and falling vs. not falling; and the predictive capacity of a multivariate model in predicting a fall in the presence of an unexpected obstacle.
no code implementations • 12 Oct 2016 • Shehroz S. Khan, Babak Taati
We propose two methods for automatic tightening of reconstruction error from only the normal activities for better identification of unseen falls.