More Like this

1. Finding 709 Defects in 258 Projects: An Experience Report on Applying CodeQL to Open-Source Embedded Software (Experience Paper)

   https://doi.org/10.5281/zenodo.15200316  

   Shen, Mingjie; Pillai, Akul Abhilash; Yuan, Brian A; Davis, James C; Machiry, Aravind (January 2025, Zenodo)

   This artifact contains the GitHub workflows to run CodeQL on EMBOSS repositories in our dataset, the results of running CodeQL on these repositories, and our manual analysis of CodeQL results. 

   more » « less
2. UniPose: Unified human pose estimation in single images and videos

   Artacho, Bruno; Savakis, Andreas (January 2020, IEEE Conference on Computer Vision and Pattern Recognition)

   We propose UniPose, a unified framework for human pose estimation, based on our “Waterfall” Atrous Spatial Pooling architecture, that achieves state-of-art-results on several pose estimation metrics. Current pose estimation methods utilizing standard CNN architectures heavily rely on statistical postprocessing or predefined anchor poses for joint localization. UniPose incorporates contextual segmentation and joint localization to estimate the human pose in a single stage, with high accuracy, without relying on statistical postprocessing methods. The Waterfall module in UniPose leverages the efficiency of progressive filtering in the cascade architecture, while maintaining multiscale fields-of-view comparable to spatial pyramid configurations. Additionally, our method is extended to UniPoseLSTM for multi-frame processing and achieves state-of-theart results for temporal pose estimation in Video. Our results on multiple datasets demonstrate that UniPose, with a ResNet backbone and Waterfall module, is a robust and efficient architecture for pose estimation obtaining state-ofthe-art results in single person pose detection for both single images and videos 

   more » « less
3. Graph neural networks in EEG spike detection

   https://doi.org/10.1016/j.artmed.2023.102663  

   Mohammed, Ahmed Hossam; Cabrerizo, Mercedes; Pinzon, Alberto; Yaylali, Ilker; Jayakar, Prasanna; Adjouadi, Malek (November 2023, Artificial Intelligence in Medicine)

   Objective: This study develops new machine learning architectures that are more adept at detecting interictal epileptiform discharges (IEDs) in scalp EEG. A comparison of results using the average precision (AP) metric is made with the proposed models on two datasets obtained from Baptist Hospital of Miami and Temple University Hospital. Methods: Applying graph neural networks (GNNs) on functional connectivity (FC) maps of different frequency sub-bands to yield a novel architecture we call FC-GNN. Attention mechanism is applied on a complete graph to let the neural network select its important edges, hence bypassing the extraction of features, a model we refer to as CA-GNN. Results: On the Baptist Hospital dataset, the results were as follows: Vanilla Self-Attention → 0.9029 ± 0.0431, Hierarchical Attention → 0.8546 ± 0.0587, Vanilla Visual Geometry Group (VGG) → 0.92 ± 0.0618, Satelight → 0.9219 ± 0.046, FC-GNN → 0.9731 ± 0.0187, and CA-GNN → 0.9788 ± 0.0125. In the same order, the results on the Temple University Hospital dataset are 0.9692, 0.9113, 0.97, 0.9575, 0.963, and 0.9879. Conclusion: Based on the good results they yield, GNNs prove to have a strong potential in detecting epileptogenic activity. Significance: This study opens the door for the discovery of the powerful role played by GNNs in capturing IEDs, which is an essential step for identifying the epileptogenic networks of the affected brain and hence improving the prospects for more accurate 3D source localization. 

   more » « less
4. Sampling-based Sublinear Low-rank Matrix Arithmetic Framework for Dequantizing Quantum Machine Learning

   https://doi.org/10.1145/3549524  

   Chia, Nai-Hui; Gilyén, András Pal; Li, Tongyang; Lin, Han-Hsuan; Tang, Ewin; Wang, Chunhao (October 2022, Journal of the ACM)

   We present an algorithmic framework for quantum-inspired classical algorithms on close-to-low-rank matrices, generalizing the series of results started by Tang’s breakthrough quantum-inspired algorithm for recommendation systems [STOC’19]. Motivated by quantum linear algebra algorithms and the quantum singular value transformation (SVT) framework of Gilyén et al. [STOC’19], we develop classical algorithms for SVT that run in time independent of input dimension, under suitable quantum-inspired sampling assumptions. Our results give compelling evidence that in the corresponding QRAM data structure input model, quantum SVT does not yield exponential quantum speedups. Since the quantum SVT framework generalizes essentially all known techniques for quantum linear algebra, our results, combined with sampling lemmas from previous work, suffice to generalize all prior results about dequantizing quantum machine learning algorithms. In particular, our classical SVT framework recovers and often improves the dequantization results on recommendation systems, principal component analysis, supervised clustering, support vector machines, low-rank regression, and semidefinite program solving. We also give additional dequantization results on low-rank Hamiltonian simulation and discriminant analysis. Our improvements come from identifying the key feature of the quantum-inspired input model that is at the core of all prior quantum-inspired results: ℓ²-norm sampling can approximate matrix products in time independent of their dimension. We reduce all our main results to this fact, making our exposition concise, self-contained, and intuitive. 

   more » « less
5. Interesting Directions in Flavor Physics

   Datta, Alakabha (June 2024, Andromeda Publishing and Academic Services)

   Flavor physics continues to be an interesting avenue to look for beyond the standard model (SM) physics. Recent results from flavor physics, both in the quark and lepton sectors, hint at possible new physics. In this work we focus on some flavor physics results, mainly in b decays, and speculate on possible new physics interpretations of these results. We also present a model that can connect some of the B anomalies to the MiniBooNe anomaly and the muon g − 2 measurement. 

   more » « less