1 code implementation • 30 Aug 2022 • Le Jiang, Shuangjun Liu, Xiangyu Bai, Sarah Ostadabbas
Here, we present a very data efficient strategy targeted for pose estimation in quadrupeds that requires only a small amount of real images from the target animal.
1 code implementation • 27 Jan 2022 • Shuangjun Liu, Sarah Ostadabbas
Computer vision has achieved great success in interpreting semantic meanings from images, yet estimating underlying (non-visual) physical properties of an object is often limited to their bulk values rather than reconstructing a dense map.
2 code implementations • 23 May 2021 • Shuangjun Liu, Michael Wan, Sarah Ostadabbas
However, recent models depend on supervised training with 3D pose ground truth data or known pose priors for their target domains.
Ranked #26 on Weakly-supervised 3D Human Pose Estimation on Human3.6M
1 code implementation • 23 May 2021 • Shuangjun Liu, Naveen Sehgal, Sarah Ostadabbas
In this paper, we focus on alleviating the negative effect of domain shift in both appearance and pose space for 3D human pose estimation by presenting our adapted human pose (AHuP) approach.
Ranked #116 on 3D Human Pose Estimation on Human3.6M (PA-MPJPE metric)
2 code implementations • 13 Oct 2020 • Xiaofei Huang, Nihang Fu, Shuangjun Liu, Sarah Ostadabbas
However, while the applications of human pose estimation have become more and more broad, models trained on large-scale adult pose datasets are barely successful in estimating infant poses due to the significant differences in their body ratio and the versatility of their poses.
2 code implementations • 20 Aug 2020 • Shuangjun Liu, Xiaofei Huang, Nihang Fu, Cheng Li, Zhongnan Su, Sarah Ostadabbas
Computer vision (CV) has achieved great success in interpreting semantic meanings from images, yet CV algorithms can be brittle for tasks with adverse vision conditions and the ones suffering from data/label pair limitation.
2 code implementations • 26 Dec 2019 • Davoud Hejazi, Shuangjun Liu, Amirreza Farnoosh, Sarah Ostadabbas, Swastik Kar
Due to their inherent variabilities, nanomaterial-based sensors are challenging to translate into real-world applications, where reliability/reproducibility is key. Recently we showed Bayesian inference can be employed on engineered variability in layered nanomaterial-based optical transmission filters to determine optical wavelengths with high accuracy/precision. In many practical applications the sensing cost/speed and long-term reliability can be equal or more important considerations. Though various machine learning tools are frequently used on sensor/detector networks to address these, nonetheless their effectiveness on nanomaterial-based sensors has not been explored. Here we show the best choice of ML algorithm in a cyber-nanomaterial detector is mainly determined by specific use considerations, e. g., accuracy, computational cost, speed, and resilience against drifts/ageing effects. When sufficient data/computing resources are provided, highest sensing accuracy can be achieved by the kNN and Bayesian inference algorithms, but but can be computationally expensive for real-time applications. In contrast, artificial neural networks are computationally expensive to train, but provide the fastest result under testing conditions and remain reasonably accurate. When data is limited, SVMs perform well even with small training sets, while other algorithms show considerable reduction in accuracy if data is scarce, hence, setting a lower limit on the size of required training data. We show by tracking/modeling the long-term drifts of the detector performance over large (1year) period, it is possible to improve the predictive accuracy with no need for recalibration. Our research shows for the first time if the ML algorithm is chosen specific to use-case, low-cost solution-processed cyber-nanomaterial detectors can be practically implemented under diverse operational requirements, despite their inherent variabilities.
1 code implementation • 3 Jul 2019 • Shuangjun Liu, Sarah Ostadabbas
Human in-bed pose estimation has huge practical values in medical and healthcare applications yet still mainly relies on expensive pressure mapping (PM) solutions.
1 code implementation • 8 Aug 2018 • Shuangjun Liu, Sarah Ostadabbas
To evaluate the performance of our synthesized datasets in training deep learning-based models, we generated a large synthetic human pose dataset, called ScanAva using 3D scans of only 7 individuals based on our proposed augmentation approach.
no code implementations • ECCV 2018 • Shuangjun Liu, Sarah Ostadabbas
When the objective is reposing a figure in an image while preserving the rest of the image, the state-of-the-art mainly assumes a single rigid body with simple background and limited pose shift, which can hardly be extended to the images under normal settings.
1 code implementation • 3 Nov 2017 • Shuangjun Liu, Yu Yin, Sarah Ostadabbas
Using the HOG rectification method, the pose estimation performance of CPM significantly improved by 26. 4% in PCK0. 1 criteria compared to the model without such rectification.