no code implementations • 14 Feb 2024 • Yang Qian, Yinan Sun, Ali Kargarandehkordi, Onur Cezmi Mutlu, Saimourya Surabhi, Pingyi Chen, Zain Jabbar, Dennis Paul Wall, Peter Washington
We find that the performance of the model pre-trained using our Tik-Tok dataset is comparable to models trained on larger action recognition datasets (95. 3% on UCF101 and 53. 24% on HMDB51).
no code implementations • 19 Mar 2023 • Yang Qian, Ali Kargarandehkordi, Onur Cezmi Mutlu, Saimourya Surabhi, Mohammadmahdi Honarmand, Dennis Paul Wall, Peter Washington
Emotions play an essential role in human communication.
no code implementations • 19 Mar 2023 • Onur Cezmi Mutlu, Mohammadmahdi Honarmand, Saimourya Surabhi, Dennis P. Wall
We introduce Temporal consistency for Test-time adaptation (TempT) a novel method for test-time adaptation on videos through the use of temporal coherence of predictions across sequential frames as a self-supervision signal.
Facial Expression Recognition Facial Expression Recognition (FER) +2
1 code implementation • 18 Aug 2021 • Anish Lakkapragada, Aaron Kline, Onur Cezmi Mutlu, Kelley Paskov, Brianna Chrisman, Nate Stockham, Peter Washington, Dennis Wall
This work aims to demonstrate the feasibility of deep learning technologies for detecting hand flapping from unstructured home videos as a first step towards validating whether models and digital technologies can be leveraged to aid with autism diagnoses.
no code implementations • 10 Jan 2021 • Peter Washington, Aaron Kline, Onur Cezmi Mutlu, Emilie Leblanc, Cathy Hou, Nate Stockham, Kelley Paskov, Brianna Chrisman, Dennis P. Wall
Activity recognition computer vision algorithms can be used to detect the presence of autism-related behaviors, including what are termed "restricted and repetitive behaviors", or stimming, by diagnostic instruments.
no code implementations • 10 Jan 2021 • Peter Washington, Onur Cezmi Mutlu, Emilie Leblanc, Aaron Kline, Cathy Hou, Brianna Chrisman, Nate Stockham, Kelley Paskov, Catalin Voss, Nick Haber, Dennis Wall
While the F1-score for a one-hot encoded classifier is much higher (94. 33% vs. 78. 68%) with respect to the ground truth CAFE labels, the output probability vector of the crowd-trained classifier more closely resembles the distribution of human labels (t=3. 2827, p=0. 0014).