Help
RSS
API
Feed
Maltego
Contact
Domain > amanrajdce.github.io
×
More information on this domain is in
AlienVault OTX
Is this malicious?
Yes
No
DNS Resolutions
Date
IP Address
2017-02-26
151.101.64.133
(
ClassC
)
2024-10-06
185.199.109.153
(
ClassC
)
Port 80
HTTP/1.1 301 Moved PermanentlyConnection: keep-aliveContent-Length: 162Server: GitHub.comContent-Type: text/htmlpermissions-policy: interest-cohort()Location: https://amanrajdce.github.io/X-GitHub-Request-Id: F7DD:FABD6:2D38D42:2E9067D:6701E662Accept-Ranges: bytesAge: 0Date: Sun, 06 Oct 2024 01:22:42 GMTVia: 1.1 varnishX-Served-By: cache-bfi-kbfi7400046-BFIX-Cache: MISSX-Cache-Hits: 0X-Timer: S1728177763.615729,VS0,VE79Vary: Accept-EncodingX-Fastly-Request-ID: 7a1be7d4ddb5c49967ddbfd39c3fa06b7070eacd html>head>title>301 Moved Permanently/title>/head>body>center>h1>301 Moved Permanently/h1>/center>hr>center>nginx/center>/body>/html>
Port 443
HTTP/1.1 200 OKConnection: keep-aliveContent-Length: 23820Server: GitHub.comContent-Type: text/html; charsetutf-8permissions-policy: interest-cohort()Last-Modified: Sun, 11 Feb 2024 18:59:53 GMTAccess-Control-Allow-Origin: *ETag: 65c91929-5d0cexpires: Sun, 06 Oct 2024 01:32:42 GMTCache-Control: max-age600x-proxy-cache: MISSX-GitHub-Request-Id: 95F4:254FC:1B1924D:1BEB370:6701E661Accept-Ranges: bytesAge: 0Date: Sun, 06 Oct 2024 01:22:42 GMTVia: 1.1 varnishX-Served-By: cache-bfi-krnt7300080-BFIX-Cache: MISSX-Cache-Hits: 0X-Timer: S1728177763.742590,VS0,VE76Vary: Accept-EncodingX-Fastly-Request-ID: 952b461fa8ed30dc7035769d02557409e5a21866 !DOCTYPE HTML>html langen>head>meta http-equivContent-Type contenttext/html; charsetUTF-8> !-- Hi, Jon Here. Please DELETE the two script> tags below if you use this HTML, otherwise my analytics will track your page --> !-- Global site tag (gtag.js) - Google Analytics --> title>Aman Raj/title> meta nameauthor contentAman Raj> meta nameviewport contentwidthdevice-width, initial-scale1> link relstylesheet typetext/css hrefstylesheet.css> link relicon typeimage/png hrefimages2/seal_icon.png>/head>body> table stylewidth:100%;max-width:800px;border:0px;border-spacing:0px;border-collapse:separate;margin-right:auto;margin-left:auto;>tbody> tr stylepadding:0px> td stylepadding:0px> table stylewidth:100%;border:0px;border-spacing:0px;border-collapse:separate;margin-right:auto;margin-left:auto;>tbody> tr stylepadding:0px> td stylepadding:2.5%;width:63%;vertical-align:middle> p styletext-align:center> name>Aman Raj/name> /p> p alignjustify>I am b> Senior Machine Learning Research Engineer /b> at a hrefhttps://www.apple.com/h>Apple Inc./a>, where I develop core vision technologies that power new user experiences across the ecosystem of Apple devices and services. /p> p alignjustify> I went to graduate school in the beautiful city of San Diego, where I completed an MS degree in Machine Learning and Data Science at a hrefhttps://www.ucsd.edu/>University of California, San Diego/a>. In Spring 2020, I defended my MS thesis titled a hrefhttps://escholarship.org/uc/item/1p85x50q> Learning Augmentation Policy Schedules for Unsupervised Depth Estimation/a> which addresses the problem of depth estimation in bad weather conditions for autonomous driving use case. /p> p alignjustify> After completing my undergraduate studies in B.Tech from a hrefhttp://dtu.ac.in/> Delhi Technological University/a>, I worked as b> Software Engineer /b> at Facebook and b> Research Intern /b> at Samsung Labs. My research work has received notable awards such as a hrefhttps://www.isprs.org/society/awards/dangermond.aspx> The Jack Dangermond Award – Best Paper/a>. /p> p styletext-align:center> a hrefmailto:amanrajdce@gmail.com>Email/a>  /  a hrefdata2/AmanRaj_CV.pdf>CV/a>  /  !-- a hrefdata2/AmanRaj-bio.txt>Biography/a>  /  --> a hrefhttps://scholar.google.co.in/citations?usersdgrTYEAAAAJ&hlen>Google Scholar/a>  /  a hrefhttps://github.com/amanrajdce>Github/a>  /  a hrefhttps://www.linkedin.com/in/amanrajdce/>LinkedIn/a> /p> /td> td stylepadding:2.5%;width:40%;max-width:40%> a hrefdata2/head_low.jpg>img stylewidth:100%;max-width:100% altprofile photo srcdata2/head_low_circle.png classhoverZoomLink>/a> /td> /tr> /tbody>/table> table width50% aligncenter border0 cellpadding20>tbody> tr> td > img srcimages2/apple.png>/td> td > img srcimages2/facebook.png>/td> td > img srcimages2/samsung.png>/td> /tr> /tbody> /table> table stylewidth:100%;border:0px;border-spacing:0px;border-collapse:separate;margin-right:auto;margin-left:auto;>tbody> tr> td stylepadding:20px;width:100%;vertical-align:middle> heading>Research/heading> p> My research interests are in computer vision, machine learning and optimization, and image processing. The majority of my research is about image and video understanding. /p> /td> /tr> /tbody>/table> table stylewidth:100%;border:0px;border-spacing:0px;border-collapse:separate;margin-right:auto;margin-left:auto;>tbody> tr onmouseoutthesis_stop() onmouseoverthesis_start()> td stylepadding:20px;width:25%;vertical-align:middle> div classone> div classtwo idccc_image3>img srcimages2/ucsd_ms_thesis_after.png altBoundary_png styleborder-style: none width190 height150>/div> img srcimages2/ucsd_ms_thesis_before.png altBoundary_png styleborder-style: none width190 height150> /div> script typetext/javascript> function thesis_start() { document.getElementById(ccc_image3).style.opacity 1; } function thesis_stop() { document.getElementById(ccc_image3).style.opacity 0; } thesis_stop() /script> /td> td width75% valignmiddle> a hrefhttps://escholarship.org/uc/item/1p85x50q> papertitle>Learning Augmentation Policy Schedules for Unsuperivsed Depth Estimation./papertitle> /a> br> strong>Aman Raj/strong> br> em>UC San Diego Electronic Theses and Dissertations, 2020 /em> br> a hrefdata2/AmanRaj_MS_Thesis_UCSD.pdf>thesis/a> / a hrefhttps://github.com/amanrajdce/laps-depth>code/a> p> My MS thesis that proposes a novel approach to augment data for unsupervised depth estimation. Our method learn data augmentation strategies from data itself./p> /td> /tr> tr> td stylepadding:20px;width:25%;vertical-align:middle> img srcimages2/suw_cvpr2020.png altBoundary_png styleborder-style: none width190 height160> /td> td width75% valignmiddle> a hrefhttps://openaccess.thecvf.com/content_CVPRW_2020/papers/w45/Ren_SUW-Learn_Joint_Supervised_Unsupervised_Weakly_Supervised_Deep_Learning_for_Monocular_CVPRW_2020_paper.pdf> papertitle>SUW-Learn: Joint Supervised, Unsupervised, Weakly Supervised Deep Learning for Monocular Depth Estimation./papertitle> /a> br> Haoyu Ren, strong>Aman Raj/strong>, Mostafa El-Khamy and Jungwon Lee br> em>CVPR/em>, 2020 br> a hrefhttps://www.youtube.com/watch?vjVaC34tloIU>video/a> / a hrefhttps://openaccess.thecvf.com/content_CVPRW_2020/supplemental/Ren_SUW-Learn_Joint_Supervised_CVPRW_2020_supplemental.pdf>supplement/a> p> A framework for deep-learning with joint supervised learning (S), unsupervised learning (U), and weakly-supervised learning (W). We deploy SUW- Learn for deep learning of the monocular depth from im- ages and video sequences./p> /td> /tr> tr> td stylepadding:20px;width:25%;vertical-align:middle> img srcimages2/signet.png altBoundary_png styleborder-style: none width190 height160> /td> td width75% valignmiddle> a hrefhttps://openaccess.thecvf.com/content_CVPR_2019/papers/Meng_SIGNet_Semantic_Instance_Aided_Unsupervised_3D_Geometry_Perception_CVPR_2019_paper.pdf> papertitle>SIGNet: Semantic Instance Aided Unsupervised 3D Geometry Perception./papertitle> /a> br> Yue Meng, Yongxi Lu, strong>Aman Raj/strong>, Samuel Sunarjo, Rui Guo, Tara Javidi, Gaurav Bansal, br> Dinesh Bharadia br> em>CVPR/em>, 2019 br> a hrefhttps://mengyuest.github.io/SIGNet/>project/a> / a hrefhttps://openaccess.thecvf.com/content_CVPR_2019/supplemental/Meng_SIGNet_Semantic_Instance_CVPR_2019_supplemental.pdf>supplement/a> p> SIGNet integrates semantic information to make depth and flow predictions consistent with objects and robust to low lighting conditions. SIGNet is shown to improve upon the state-of-the-art unsupervised learning for depth prediction./p> /td> /tr> tr> td stylepadding:20px;width:25%;vertical-align:middle> img srcimages2/robocodes_cvpr2018.png altBoundary_png styleborder-style: none width190 height160> /td> td width75% valignmiddle> a hrefhttps://research.fb.com/wp-content/uploads/2018/06/A-Holistic-Framework-for-Addressing-the-World-using-Machine-Learning.pdf> papertitle>A Holistic Framework for Addressing the World using Machine Learning./papertitle> /a> br> Ilke Demir, Forest Hughes, strong>Aman Raj/strong>, Kaunil Dhruv, Suryanarayana Murthy Muddla, Sanyam Garg, Barrett Doo, Ramesh Raskar br> em>CVPR/em>, 2018 br> a hrefhttps://research.fb.com/publications/a-holistic-framework-for-addressing-the-world-using-machine-learning/>project/a> p>We propose an automatic generative algorithm to create street addresses from satellite imagery. Our addressing scheme is coherent with the street topology, linear and hierarchical to follow human perception, and universal to be used as a unified geocoding system./p> /td> /tr> tr onmouseoutccc_stop() onmouseoverccc_start()> td stylepadding:20px;width:25%;vertical-align:middle> div classone> div classtwo idccc_image1>img srcimages2/isprs2018_after.png altBoundary_png styleborder-style: none width190 height90>/div> img srcimages2/isprs2018_before.png altBoundary_png styleborder-style: none width190 height90> /div> script typetext/javascript> function ccc_start() { document.getElementById(ccc_image1).style.opacity 1; } function ccc_stop() { document.getElementById(ccc_image1).style.opacity 0; } ccc_stop() /script> /td> td width75% valignmiddle> a hrefhttps://www.mdpi.com/2220-9964/7/3/84/htm> papertitle>Generative Street Addresses from Satellite Imagery./papertitle> /a> br> Ilke Demir, Forest Hughes, strong>Aman Raj/strong>, Kaunil Dhruv, Suryanarayana Murthy Muddla, Sanyam Garg, Barrett Doo, Ramesh Raskar br> em>ISPRS/em>, 2018   font colorred>strong>(The Jack Dangermond Award – Best Paper)/strong>/font> br> a hrefhttps://research.fb.com/publications/generative-street-addresses-from-satellite-imagery/>project/a> / a hrefhttps://github.com/facebookresearch/street-addresses>code/a> / a hrefhttps://2017.stateofthemap.us/program/generative-street-addresses.html> talk /a> p>Our algorithm starts with extracting roads from satellite imagery by utilizing deep learning. Then, it uniquely labels the regions, roads, and structures using graph and proximity-based algorithms./p> /td> /tr> tr> td stylepadding:20px;width:25%;vertical-align:middle> img srcimages2/robocodes_cvpr2017.png altBoundary_png styleborder-style: none width190 height60> /td> td width75% valignmiddle> a hrefhttps://research.fb.com/wp-content/uploads/2017/07/cvpr_ev_final_sent.pdf?> papertitle>Robocodes: Towards Generative Street Addresses from Satellite Imagery./papertitle> /a> br> Ilke Demir, Forest Hughes, strong>Aman Raj/strong>, Kleovoulos Tsourides, Divyaa Ravichandran, Suryanarayana Murthy, Kaunil Dhruv, Sanyam Garg, Jatin Malhotra, Barrett Doo, Grace Kermani, Ramesh Raskar br> em>CVPR/em>, 2017   font colorred>strong>(Best Paper Award)/strong>/font> br> a hrefhttps://research.fb.com/publications/robocodes-towards-generative-street-addresses-from-satellite-imagery/>project/a> / a hrefhttps://github.com/facebookresearch/street-addresses>code/a> / a hrefhttps://research.fb.com/advancing-computer-vision-technologies-at-cvpr-2017/> blog /a> / a hrefhttps://www.geospatialworld.net/blogs/mapping-unmapped-facebook-mit-project/> news /a> p>We describe our automatic generative algorithm to create street addresses (Robocodes) from satellite images by learning and labeling regions, roads, and blocks./p> /td> /tr> tr onmouseoutfpga_stop() onmouseoverfpga_start()> td stylepadding:20px;width:25%;vertical-align:middle> div classone> div classtwo idccc_image2>img srcimages2/fpga_after.png altBoundary_png styleborder-style: none width190 height90>/div> img srcimages2/fpga_before.png altBoundary_png styleborder-style: none width190 height90> /div> script typetext/javascript> function fpga_start() { document.getElementById(ccc_image2).style.opacity 1; } function fpga_stop() { document.getElementById(ccc_image2).style.opacity 0; } fpga_stop() /script> /td> td width75% valignmiddle> a hrefdata2/fpga_icctict_2016.pdf> papertitle>FPGA Accelerated Abandoned Object Detection./papertitle> /a> br> Rajesh Rohilla, strong>Aman Raj/strong>, Saransh Kejriwal, Rajiv Kapoor br> em>ICCTICT, IEEE/em> 2016 br> a hrefdata2/icctict_2016.pdf>slides/a> p> We propose a hardware implementation of abandoned object detection algorithm on FPGA aimed for making a custom chip that can do real-time inference on live video feed./p> /td> /tr> tr> td stylepadding:20px;width:25%;vertical-align:middle> img srcimages2/cmu_result.png altBoundary_png styleborder-style: none width190 height160> /td> td width75% valignmiddle> a hrefdata2/CMU-RI-TR-AmanRaj.pdf> papertitle>Multi-Scale Convolutional Architecture for Semantic Segmentation./papertitle> /a> br> strong>Aman Raj/strong>, Daniel Maturana, Sebastian Scherer br> em>RI Technical Reports, CMU/em> 2015 br> a hrefhttps://www.ri.cmu.edu/publications/multi-scale-convolutional-architecture-for-semantic-segmentation/>project/a> / a hrefdata2/cmu_slides.pdf>slides/a> p> This work exploits the geocentric encoding of a depth image and uses a multi-scale deep convolutional neural network architecture that captures high and low- level features of a scene to generate rich semantic labels./p> /td> /tr> tr> td stylepadding:20px;width:25%;vertical-align:middle> img srcimages2/icvgip2014.png altBoundary_png styleborder-style: none width190 height160> /td> td width75% valignmiddle> a hrefdata2/ICVGIP_2014.pdf> papertitle>Digitization of Historic Inscription Images using Cumulants based Simultaneous Blind Source Extraction./papertitle> /a> br> N. Jayanthi, Ayush Tomar, strong>Aman Raj/strong>, S. Indu, Santanu Chaudhury br> em>ICVGIP /em> 2014 br> p> Proposed technique provides a suitable method to separate the text layer from the historic inscription images by considering the problem as blind source separation which aims to calculate the independent components from a linear mixture of source signals, by maximizing a contrast function based on higher order cumulants./p> /td> /tr> tr> td stylepadding:20px;width:25%;vertical-align:middle> img srcimages2/accv2014.png altBoundary_png styleborder-style: none width190 height130> /td> td width75% valignmiddle> a hrefdata2/ACCV_2014.pdf> papertitle>Enhancement and Retrieval of Historic Inscription Images./papertitle> /a> br> S. Indu, Ayush Tomar, strong>Aman Raj/strong>, Santanu Chaudhury br> em>ACCV /em> 2014 br> p> Binarization of inscription images using the proposed cumulants based Blind Source Extraction(BSE) method, and store them in a digital library with their corresponding historic information which can be retrieved later using image retrieval algorithms such as BoW./p> /td> /tr> /tbody>/table> table width100% aligncenter border0 cellspacing0 cellpadding20>tbody> tr> td> heading>Patents/heading> /td> /tr> /tbody>/table> table width100% aligncenter border0 cellpadding20>tbody> tr> td width75% valignmiddle> a hrefhttps://patentimages.storage.googleapis.com/a1/45/ec/2bdb1b2faadf96/US20210124985A1.pdf> papertitle>System and Method for Deep Machine Learning for Computer Vision Applications /papertitle> /a> br> US20210124985A1, US20220391632A1 /td> /tr> /tbody>/table> table width100% aligncenter border0 cellspacing0 cellpadding20>tbody> tr> td> heading>Miscellaneous/heading> /td> /tr> /tbody>/table> table width100% aligncenter border0 cellpadding20>tbody> tr> td stylepadding:20px;width:25%;vertical-align:middle>img srcimages2/ucsd_lib_logo.png styleborder-style: none width130 height130>/td> td width75% valigncenter> a hrefhttps://sites.google.com/eng.ucsd.edu/cse12spring/home>Teaching Assistant, CSE 12 - Spring 2019/a> br> /td> /tr> !-- tr> td stylepadding:20px;width:25%;vertical-align:middle> img srcimages2/velo.png altBoundary_png styleborder-style: none width190 height130> /td> td width75% valignmiddle> a hrefhttps://vimeo.com/149376920> papertitle>Velo/papertitle> /a> p> As Data Scientist at SupplyAI Inc. developed predictive intelligent models for logistics in supply chain. Models that allocates shipper for a particular order, predicts various delays in delivering it, estimating pickup date of order by shipper, predicting returns on orders. /p> /td> /tr> --> tr onmouseoutcomic_stop() onmouseovercomic_start()> td stylepadding:20px;width:25%;vertical-align:middle> div classone> div classtwo idccc_comic>img srcimages2/comic_polyglot_after.png altBoundary_png styleborder-style: none width190 height130>/div> img srcimages2/comic_polyglot_before.png altBoundary_png styleborder-style: none width190 height130> /div> script typetext/javascript> function comic_start() { document.getElementById(ccc_comic).style.opacity 1; } function comic_stop() { document.getElementById(ccc_comic).style.opacity 0; } comic_stop() /script> /td> td width75% valignmiddle> a hrefdata2/comicpolyglot.pdf> papertitle>Comic Polyglot/papertitle> /a> br> em>CMU Winter School, 2014 /em>   font colorred>strong>(Best Project Award)/strong>/font> br> a hrefdata2/comicpolyglot.pdf>poster/a> p> Comic Polyglot-A system that identifies the text regions in comic strips like Manga and subsequently translates it’s Japanese text into English using an OCR engine while maintaining the syntax. It is aimed to help English-speaking manga comic readers. /p> /td> /tr> tr onmouseoutluna_stop() onmouseoverluna_start()> td stylepadding:20px;width:25%;vertical-align:middle> div classone> div classtwo idccc_luna>img srcimages2/lunabot_after.png altBoundary_png styleborder-style: none width190 height130>/div> img srcimages2/lunabot_before.png altBoundary_png styleborder-style: none width190 height130> /div> script typetext/javascript> function luna_start() { document.getElementById(ccc_luna).style.opacity 1; } function luna_stop() { document.getElementById(ccc_luna).style.opacity 0; } luna_stop() /script> /td> td width75% valignmiddle> a hrefdata2/lunabot_photos.pdf> papertitle>Lunabot/papertitle> /a> br> em>NASAs Lunabotics Mining Competition, 2013/em> br> a hrefdata2/lunabot_sys_eng_paper.pdf>paper/a> / a hrefdata2/lunabot_outreach.pdf>outreach/a> / a hrefdata2/lunabot_photos.pdf>gallery/a> p>Aaravya Lunabot - DTU’s official entry into NASA Lunabotics Mining Competition 2013. The challenge required student teams to design and build a mining robot that can traverse the simulated lunar chaotic terrain, excavate lunar regolith and deposit the regolith into a collector bin within ten minutes. /p> /td> /tr> /tbody>/table> table stylewidth:100%;border:0px;border-spacing:0px;border-collapse:separate;margin-right:auto;margin-left:auto;>tbody> tr> td stylepadding:0px> br> p styletext-align:right;font-size:small;> Website design from a hrefhttps://jonbarron.info/>here/a> /p> /td> /tr> /tbody>/table> /td> /tr> /table>/body>/html>
View on OTX
|
View on ThreatMiner
Please enable JavaScript to view the
comments powered by Disqus.
Data with thanks to
AlienVault OTX
,
VirusTotal
,
Malwr
and
others
. [
Sitemap
]