-
Notifications
You must be signed in to change notification settings - Fork 1
/
research.html
1 lines (1 loc) · 23 KB
/
research.html
1
<!DOCTYPE html><html lang="en"><head><meta charset="utf-8"><meta name="viewport" content="width=device-width,initial-scale=1"><link rel="shortcut icon" href="/favicon.ico"><title>Ehsan Qasemi</title><script defer="defer" src="/static/js/main.88ab3dae.js"></script><link href="/static/css/main.ad7beef5.css" rel="stylesheet"><meta charset="utf-8" data-react-helmet="true"><link href="/static/css/responsive.css" rel="stylesheet" type="text/css"></head><body><div id="root"><div><div class="super_container"><header class="header" id="main_header"><div class="header_content d-flex flex-row align-items-center justify-content-start"><div class="logo">Ehsan Qasemi</div><div class="main_nav d-flex flex-row align-items-end justify-content-start"><ul class="d-flex flex-row align-items-center justify-content-start"><li class=""><a href="/about">About</a></li><li class=""><a href="/education">Education</a></li><li class=""><a href="/research">Research</a></li><li class=""><a href="/experience">Experience</a></li><li class=""><a href="/skills">Skills</a></li><li class=""><a href="/teaching">Teaching</a></li></ul></div><div class="menu"><div class="menu_content d-flex flex-row align-items-start justify-content-end"><div class="hamburger ml-auto">menu</div><div class="menu_nav text-right"><ul><li><a href="/about">About</a></li><li><a href="/education">Education</a></li><li><a href="/research">Research</a></li><li><a href="/experience">Experience</a></li><li><a href="/skills">Skills</a></li><li><a href="/teaching">Teaching</a></li></ul></div></div></div></div></header><div class="content_container"><div class="main_content_outer d-flex flex-xl-row flex-column align-items-start justify-content-start"><div class="general_info d-flex flex-xl-column flex-md-row flex-column" id="general_information"><div class="general_info_image"><div class="background_image" style="background-image:url(/static/media/me_formal.42da6e0e71c533dfb061.jpg)"></div></div><div class="general_info_content"><div class="general_info_content_inner mCustomScrollbar" data-mcs-theme="minimal-dark"><div class="general_info_title">General Information</div><ul class="general_info_list"><li class="d-flex flex-row align-items-center justify-content-start"><div class="general_info_icon d-flex flex-column align-items-start justify-content-center"><i class="fa fa-envelope" style="color:#8583e1"></i></div><div class="general_info_text"><a href="mailto:[email protected]">[email protected]</a></div></li><li class="d-flex flex-row align-items-center justify-content-start"><div class="general_info_icon d-flex flex-column align-items-start justify-content-center"><i class="fa fa-envelope" style="color:#8583e1"></i></div><div class="general_info_text"><a href="mailto:[email protected]">[email protected]</a></div></li><li class="d-flex flex-row align-items-center justify-content-start"><div class="general_info_icon d-flex flex-column align-items-start justify-content-center"><i class="fa fa-home" style="color:#8583e1"></i></div><div class="general_info_text"><a href="http://ehsanqasemi.com">ehsanqasemi.com</a></div></li><li class="d-flex flex-row align-items-center justify-content-start"><div class="general_info_icon d-flex flex-column align-items-start justify-content-center"><i class="fa fa-github" style="color:#8583e1"></i></div><div class="general_info_text"><a href="https://github.com/proska">proska</a></div></li><li class="d-flex flex-row align-items-center justify-content-start"><div class="general_info_icon d-flex flex-column align-items-start justify-content-center"><i class="fa fa-linkedin" style="color:#8583e1"></i></div><div class="general_info_text"><a href="https://www.linkedin.com/in/ehsan-qasemi-39627477/">ehsan-qasemi</a></div></li></ul></div></div></div><div class="main_content"><div class="main_title_container d-flex flex-column align-items-start justify-content-end"><div class="main_title">My Research</div></div><div class="portfolio_categories button-group filters-button-group"><ul><li class="portfolio_category activeis-checked">All</li><li class="portfolio_category active">NLP</li><li class="portfolio_category active">CV</li><li class="portfolio_category active">ML</li><li class="portfolio_category active">Other</li></ul></div><div class="main_content_scroll mCustomScrollbar container-fluid" data-mcs-theme="minimal-dark"><div class="portfolio_grid grid clearfix row"><div class="grind-item-bundle col-12"><h3 class="portfolio_item_title">Preconditioned Visual Language Inference with Weak Supervision</h3><div class="container"><div class="portfolio_item row"><img src="/static/media/overview.7a6bb44c8b3218e8bfba.png" alt=""><a href="/research/prism"><div class="portfolio_item_content d-flex flex-column align-items-center justify-content-center"></div></a></div><div class="portfolio-item-description row"><strong>Brief: </strong>Introduce a learning resource the task of preconditioned visual language inference and rationalization (PVLIR).</div></div></div><div class="grind-item-bundle col-12"><h3 class="portfolio_item_title">TRIVIA: Traffic-Domain Video Question Answering with Automatic Captioning</h3><div class="container"><div class="portfolio_item row"><img src="/static/media/trivia_main.da9eb48d536807cfe255.png" alt=""><a href="/research/trivia"><div class="portfolio_item_content d-flex flex-column align-items-center justify-content-center"></div></a></div><div class="portfolio-item-description row"><strong>Brief: </strong>Proposed a novel synthetic captioning method to incorporate traffic domain knowledge into video-language models, to improve Traffic question/answering performance of selective video-language models by 20%</div></div></div><div class="grind-item-bundle col-12"><h3 class="portfolio_item_title">PInKS: Preconditioned Commonsense Inference with Weak Supervision</h3><div class="container"><div class="portfolio_item row"><img src="/static/media/PInKS_Overview.e3cf5364cf89bd873e6d.jpg" alt=""><a href="/research/pinks"><div class="portfolio_item_content d-flex flex-column align-items-center justify-content-center"></div></a></div><div class="portfolio-item-description row"><strong>Brief: </strong>Propose an improved model for reasoning with preconditions through minimum supervision. </div></div></div><div class="grind-item-bundle col-12"><h3 class="portfolio_item_title">PaCo: Preconditions Attributed to Commonsense Knowledge</h3><div class="container"><div class="portfolio_item row"><img src="/static/media/MCQ_Overview_2-trimmy.bc022aee55227a5b05e7.png" alt=""><a href="/research/paco"><div class="portfolio_item_content d-flex flex-column align-items-center justify-content-center"></div></a></div><div class="portfolio-item-description row"><strong>Brief: </strong>Propose suite of tasks to evaluate preconditioned inference of commonsense knowledge in SOTA models</div></div></div><div class="grind-item-bundle col-12"><h3 class="portfolio_item_title">AutoUnload: Optimizing Oracle Heatwave for Efficient Data Management</h3><div class="container"><div class="portfolio_item row"><img src="/static/media/heatwave_logo.029c678ba4433e0d292a.png" alt=""><a href="/research/autounload"><div class="portfolio_item_content d-flex flex-column align-items-center justify-content-center"></div></a></div><div class="portfolio-item-description row"><strong>Brief: </strong>Introduced and implemented AutoUnload and AutoUnload Advisor for Oracle Heatwave</div></div></div><div class="grind-item-bundle col-12"><h3 class="portfolio_item_title">VIPHY: Probing "Visible" Physical Commonsense Knowledge</h3><div class="container"><div class="portfolio_item row"><img src="/static/media/intro.3c197757b1242f5f3ecb.png" alt=""><a href="/research/viphy"><div class="portfolio_item_content d-flex flex-column align-items-center justify-content-center"></div></a></div><div class="portfolio-item-description row"><strong>Brief: </strong>Build an automatic pipeline to calibrate and probe visible aspects of commonsense in visual language models.</div></div></div><div class="grind-item-bundle col-12"><h3 class="portfolio_item_title">A Neuro-symbolic Architecture for Intelligent Traffic Monitoring</h3><div class="container"><div class="portfolio_item row"><img src="/static/media/HANS-arch1.c7746eee1e1a643e9929.png" alt=""><a href="/research/traffickg"><div class="portfolio_item_content d-flex flex-column align-items-center justify-content-center"></div></a></div><div class="portfolio-item-description row"><strong>Brief: </strong>Human-Assisted Neuro-Symbolic Architecture for Multi-modal Intelligent Traffic Monitoring</div></div></div><div class="grind-item-bundle col-12"><h3 class="portfolio_item_title">CSKG: Consolidating Commonsense Knowledge</h3><div class="container"><div class="portfolio_item row"><img src="/static/media/cskg_logo.d915e2eed4392e002ee0.png" alt=""><a href="/research/cskg"><div class="portfolio_item_content d-flex flex-column align-items-center justify-content-center"></div></a></div><div class="portfolio-item-description row"><strong>Brief: </strong>In this work, we investigate and consolidate various resources of commonsense knowledge into a first integrated commonsense knowledge graph.</div></div></div><div class="grind-item-bundle col-12"><h3 class="portfolio_item_title">CoreQuisite: Contextual Preconditions of Commonsense Knowledge.</h3><div class="container"><div class="portfolio_item row"><img src="/static/media/cq_overview_mini.4fdeec34137af6704df9.png" alt=""><a href="/research/cq"><div class="portfolio_item_content d-flex flex-column align-items-center justify-content-center"></div></a></div><div class="portfolio-item-description row"><strong>Brief: </strong>Evaluate reasoning with preconditions in SOTA models by proposing a multiple-choice question answering dataset</div></div></div><div class="grind-item-bundle col-12"><h3 class="portfolio_item_title">DSBox: Data Scientist In A Box</h3><div class="container"><div class="portfolio_item row"><img src="/static/media/dsbox.1a76d1f5f56a7510c297.png" alt=""><a href="/research/dsbox"><div class="portfolio_item_content d-flex flex-column align-items-center justify-content-center"></div></a></div><div class="portfolio-item-description row"><strong>Brief: </strong>End-to-End Automated Machine Learning (E2E-AutoML) seeks to automate the machine learning pipeline generation process. In this work we present DSBox, an expandable, multi-modal E2E-AutoML system, that can go directly from raw data to ML pipeline with minimal human supervision. We show DSBox is able to outperform human experts and beat state-of-the-art AutoML systems (ML-Plan, Auto-sklearn, TPOT) through evaluation on 468 diverse datasets with multiple media and task types.</div></div></div><div class="grind-item-bundle col-12"><h3 class="portfolio_item_title">Tabular Data to Knowledge Graph Matching</h3><div class="container"><div class="portfolio_item row"><img src="/static/media/tableU.6accc485fda2cb3320b5.jpg" alt=""><a href="/research/tableund"><div class="portfolio_item_content d-flex flex-column align-items-center justify-content-center"></div></a></div><div class="portfolio-item-description row"><strong>Brief: </strong>Aim of this research is to understand tabular data based on actual contents and the meta-data of table (e.g. styling, headers) and map the content to entities and relations from knowledge graphs such as dbpedia and wikidata.</div></div></div><div class="grind-item-bundle col-12"><h3 class="portfolio_item_title">Detecting Autism Spectrum Disorder (ASD): Learning Empirical Space for Spatio-temporal Data Analysis</h3><div class="container"><div class="portfolio_item row"><img src="/static/media/Vitruvianischer_Mann.eb614f7a409830340fba.png" alt=""><a href="/research/asd"><div class="portfolio_item_content d-flex flex-column align-items-center justify-content-center"></div></a></div><div class="portfolio-item-description row"><strong>Brief: </strong>Here, we investigated spatio-temporal data analysis methods in motor-based early ASD (autism spectrum disorder) detection application. The challenge here is processing the stream multi-modal (Motion, fMRI, EEG, and DTI) information with the goal of detecting early signs of ASD in the human subject. We propose two solutions, with the ability to achieve 80% accuracy. Additionally, we have extracted a set of entropy-based features that can help explain the decision-making process of the network and improve confidence in the results.</div></div></div><div class="grind-item-bundle col-12"><h3 class="portfolio_item_title">Adversarial Depth Estimation based on Left-Right Consistency</h3><div class="container"><div class="portfolio_item row"><img src="/static/media/adepthLR.d9cffe6fa723c38dc328.jpg" alt=""><a href="/research/adepthlr"><div class="portfolio_item_content d-flex flex-column align-items-center justify-content-center"></div></a></div><div class="portfolio-item-description row"><strong>Brief: </strong>In this work, we build upon previous work on using Left-Right consistency for depth estimation. The conventional approach in such methods is using a series of hand-designed loss metrics to measure the consistency between the left-eye and right-image, which limits the capabilities of such models. In this work, we borrow from Generative Adversarial Networks (GAN) and propose a method for LR-Consistency that learns the consistency/loss function with goal of discriminating the inconsistent Images.</div></div></div><div class="grind-item-bundle col-12"><h3 class="portfolio_item_title">Deep Leaning in Art History</h3><div class="container"><div class="portfolio_item row"><img src="/static/media/baroque_sample.914267b515a5033fcf3c.jpg" alt=""><a href="/research/deep_art"><div class="portfolio_item_content d-flex flex-column align-items-center justify-content-center"></div></a></div><div class="portfolio-item-description row"><strong>Brief: </strong>In this work, we studied deep learning applications in elucidating the relationships among painting. The painting dataset consists of three periods of Pre-Baroque, Baroque, and post-baroque.</div></div></div><div class="grind-item-bundle col-12"><h3 class="portfolio_item_title">Deep Leaning and Empirical Topology in Music Style Detection</h3><div class="container"><div class="portfolio_item row"><img src="/static/media/G_img.6c81d78bbe35a8e261bd.png" alt=""><a href="/research/deep_music"><div class="portfolio_item_content d-flex flex-column align-items-center justify-content-center"></div></a></div><div class="portfolio-item-description row"><strong>Brief: </strong>Investigate deep learning applications as the computational intelligence medium for classification of music pieces according to style and historical period, such as Baroque, Classical and Romantic periods.</div></div></div><div class="grind-item-bundle col-12"><h3 class="portfolio_item_title">Deep Learning Features in Atmospheric Chemistry</h3><div class="container"><div class="portfolio_item row"><img src="data:image/jpeg;base64,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" alt=""><a href="/research/deep_air"><div class="portfolio_item_content d-flex flex-column align-items-center justify-content-center"></div></a></div><div class="portfolio-item-description row"><strong>Brief: </strong>Big data local-to-global methods in analysis and prediction of dynamics in atmospheric chemistry spatiotemporal data.</div></div></div><div class="grind-item-bundle col-12"><h3 class="portfolio_item_title">Hardware Security Module</h3><div class="container"><div class="portfolio_item row"><img src="/static/media/HSM.074cb840a8efc5eaeb9c.png" alt=""><a href="/research/hsm"><div class="portfolio_item_content d-flex flex-column align-items-center justify-content-center"></div></a></div><div class="portfolio-item-description row"><strong>Brief: </strong></div></div></div><div class="grind-item-bundle col-12"><h3 class="portfolio_item_title">Blokus-Duo AI Agent based on Monte-Carlo Tree Search (MCTS)</h3><div class="container"><div class="portfolio_item row"><img src="/static/media/blokus.3509c33b43961cf02ac4.jpg" alt=""><a href="/research/blokus"><div class="portfolio_item_content d-flex flex-column align-items-center justify-content-center"></div></a></div><div class="portfolio-item-description row"><strong>Brief: </strong>This research focuses on our proposed hardware architecture on a highly scalable, shared-memory, MonteCarlo Tree Search (MCTS) based Blokus-Duo solver. Our design is inspired from parallel MCTS algorithms and is potentially capable of obtaining maximum possible parallelism from MCTSalgorithm. We also combine MCTS with set of pruning heuristics to increase both the memory and Logic Element (LE) utilizations.</div></div></div><div class="grind-item-bundle col-12"><h3 class="portfolio_item_title">Maestro: A High Performance AES Encryption / Decryption System</h3><div class="container"><div class="portfolio_item row"><img src="/static/media/aes.782246bb18ff34eaf94b.jpg" alt=""><a href="/research/aes"><div class="portfolio_item_content d-flex flex-column align-items-center justify-content-center"></div></a></div><div class="portfolio-item-description row"><strong>Brief: </strong>This research focuses on our proposed hardware architecture on a highly scalable, shared-memory, MonteCarlo Tree Search (MCTS) based Blokus-Duo solver. Our design is inspired from parallel MCTS algorithms and is potentially capable of obtaining maximum possible parallelism from MCTSalgorithm. We also combine MCTS with set of pruning heuristics to increase both the memory and Logic Element (LE) utilization.</div></div></div><div class="grind-item-bundle col-12"><h3 class="portfolio_item_title">Embedded Stream Encryption</h3><div class="container"><div class="portfolio_item row"><img src="/static/media/pardis.f695e7158a621e635853.png" alt=""><a href="/research/pardis"><div class="portfolio_item_content d-flex flex-column align-items-center justify-content-center"></div></a></div><div class="portfolio-item-description row"><strong>Brief: </strong></div></div></div><div class="grind-item-bundle col-12"><h3 class="portfolio_item_title">Stochastic Methods and Monte-Carlo Tree Search (MCTS) Applications in High Level Synthesis</h3><div class="container"><div class="portfolio_item row"><img src="/static/media/hls.0617e6f1fee2eb136766.jpg" alt=""><a href="/research/hls"><div class="portfolio_item_content d-flex flex-column align-items-center justify-content-center"></div></a></div><div class="portfolio-item-description row"><strong>Brief: </strong>In this work, we address the problem of scheduling in high-level synthesis application. We propose a new scheduling algorithm based on Monte-Carlo (MC) simulation that uses MC Tree Search (MCTS)method as the heart of our scheme handles the schedulingto produce optimized scheduling with both time and resource constraints.</div></div></div><div class="grind-item-bundle col-12"><h3 class="portfolio_item_title">Subthreshold Memory Compiler</h3><div class="container"><div class="portfolio_item row"><img src="/static/media/memory.4f28db6cb4325fa1c96d.jpg" alt=""><a href="/research/submem"><div class="portfolio_item_content d-flex flex-column align-items-center justify-content-center"></div></a></div><div class="portfolio-item-description row"><strong>Brief: </strong>In this work, we investigated SRAM memory architectures to work in subthreshold voltage range for low-power applications. We have proposed a set of cell architectures that improve read, write, and hold stability compared to state-of-the-art cell architectures. Finally, we developed our in-house memory compiler tool that assembles such memory cells into full SRAM memory with arbitrary size.</div></div></div></div></div></div></div></div></div></div></div><div style="text-align:center">Copyright ©<script>document.write((new Date).getFullYear().toString())</script>2023All rights reserved | This template is made with <i aria-hidden="true" class="fa fa-heart-o"></i> by <a href="https://colorlib.com" target="_blank">Colorlib</a></div></body></html>