-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
1 parent
fbdf410
commit ccdb07e
Showing
8 changed files
with
153 additions
and
82 deletions.
There are no files selected for viewing
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -24,12 +24,11 @@ | |
</head> | ||
<body> | ||
|
||
<div class="profile"> | ||
<div class="jumbotron jumbotron-billboard"> | ||
<div class="main"> | ||
<!-- <div class="jumbotron jumbotron-billboard"> | ||
<div class="img"></div> | ||
<div class="container jumbotron-title"> | ||
<img class="personal_style" src='figures/img.jpg'><img> | ||
<!-- <div style="font-weight:bolder;color:blue;margin-bottom: 5px">Shih-Po Lee (Robert)</div> --> | ||
<div class="bio"> | ||
Hello! My name is Shih-Po (Robert) Lee. I am a second-year PhD student at Khoury College of Computer Sciences of Northeastern University | ||
My research directions are Computer Vision and Deep Learning and currently working on error detection in procedural tasks. | ||
|
@@ -46,67 +45,78 @@ | |
<a href="https://www.linkedin.com/in/shih-po-lee-9554b423a/" target="_blank">Linkedin</a> | ||
</div> | ||
</div> | ||
</div> --> | ||
<div class="container profile"> | ||
<div class="row"> | ||
<div class="col"> | ||
<a href="#research" style="margin-left:10px; margin-right:10px">Research Projects</a> | ||
<a href="#experience" style="margin-left:10px; margin-right:10px">Experience</a> | ||
<a href="#education" style="margin-left:10px; margin-right:10px">Education</a> | ||
<a href="#publication" style="margin-left:10px; margin-right:10px">Publications</a> | ||
</div> | ||
</div> | ||
<div class="row" style="margin-top: 20px"> | ||
<div class="col-9"> | ||
<div class="bio"> | ||
Hello! My name is Shih-Po (Robert) Lee. I am a second-year PhD student at Khoury College of Computer Sciences of Northeastern University. | ||
My research directions are <b>Video Understanding with Computer Vision and Deep Learning</b>. I am currently working on <b>error detection in procedural tasks</b>, | ||
which aims to detect erroneous/abnormal action/steps in the process of performing actions to complete tasks. | ||
</div> | ||
</div> | ||
<div class="col" style="text-align: center"> | ||
<img class="personal_style" src='figures/img.jpg'><img> | ||
</div> | ||
</div> | ||
<div class="row" style="margin-top: 20px"> | ||
<div class="col"> | ||
<img class="icon_css" src='figures/email.png'></img> | ||
<a href="mailto:[email protected]"> [email protected]</a> | ||
<img class="icon_css" src='figures/gcholar.png'></img> | ||
<a href="https://scholar.google.com.tw/citations?user=evmoWxUAAAAJ&hl=zh-TW" target="_blank">Google Scholar</a> | ||
<img class="icon_css" src="figures/github.png"> | ||
<a href="https://github.com/robert80203" target="_blank">Github</a> | ||
<img class="icon_css" src="figures/linkd.png"> | ||
<a href="https://www.linkedin.com/in/shih-po-lee-9554b423a/" target="_blank">Linkedin</a> | ||
</div> | ||
</div> | ||
</div> | ||
<div id="news" class="title"> | ||
News | ||
<img class="title_icon" src="figures/news.png"></img> | ||
</div> | ||
<div class="news"> | ||
6/17/2024 - attend CVPR2024 in Seattle and present paper <b>"Error Detection in Egocentric Procedural Task Videos"</b>. | ||
</div> | ||
<div class="news"> | ||
2/26/2024 - our paper has been accepted by CVPR2024. | ||
</div> | ||
<div id='research' class="title"> | ||
Research Projects | ||
<img class="title_icon" src="figures/research.png"></img> | ||
</div> | ||
<div class="title">Education</div> | ||
<table class="member_table"> | ||
<tbody> | ||
<!--<tr> | ||
<img class="bgimg" src="figures/test.jpg"></img> | ||
</tr>--> | ||
<tr> | ||
<td><img class="institute_style" src='https://brand.northeastern.edu/wp-content/uploads/2022/06/ac-grid-4-red-1.svg'><img></td> | ||
<td style="vertical-align: middle;"> | ||
<div>PhD student in Khoury College of Computer Sciences, Northeastern University, Boston, USA</div> | ||
<div class="period_style">[September 2022 - present]</div> | ||
</td> | ||
</tr> | ||
<tr> | ||
<td><img class="institute_style" src='https://www.nycu.edu.tw/userfiles/nycuch/images/20230915165412300.png'><img></td> | ||
<td style="vertical-align: middle;"> | ||
<div>Master of Science in Institute of Computer Science and Engineering, National Chiao Tung University (NCTU), Taiwan</div> | ||
<div class="period_style">[September 2018 - August 2020]</div> | ||
</td> | ||
</tr> | ||
<tr> | ||
<td><img class="institute_style" src='https://www.nsysu.edu.tw/var/file/0/1000/img/80/213315840.svg'><img></td> | ||
<td style="vertical-align: middle;"> | ||
<div>Bachelor of Science in Computer Science and Engineering, National Sun Yat-sen University (NSYSU), Taiwan</div> | ||
<div class="period_style">[September 2014 - July 2018]</div> | ||
</td> | ||
</tr> | ||
</tbody> | ||
</table> | ||
<div class="title">Research Projects</div> | ||
<div class="container"> | ||
<!-- <div class="research_topic"> | ||
<div class="title_css">Human Pose Estimation Using Millimeter Wave Radar</div> | ||
<div class=""> | ||
<img style="height:400px;width:500px;" src="figures/mmWave_teaser.png"><img> | ||
<div class="research_abstract"> | ||
Human pose estimation (HPE) is a widely studied task in computer vision. Given RGB images, a network predicts 2D/3D human skeletons. | ||
The figure on the right illustrates a new application in HPE by using radar signals to predict keypoints. | ||
</div> | ||
<div class="row row_css"> | ||
<div class="col-sm"> | ||
<img class="teaser_style" src="figures/EgoPER.png"><img> | ||
</div> | ||
</div> --> | ||
<div class="col-sm col_style"> | ||
<div class="research_title">Error Detection in Egocentric Procedural Task Videos</div> | ||
<div class="research_author">Shih-Po Lee, Zijia Lu, Zekun Zhang, Minh Hoai, Ehsan Elhamifar</div> | ||
<div class="research_from">IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), June 2024</div> | ||
<div class="link"><a href="https://openaccess.thecvf.com/content/CVPR2024/papers/Lee_Error_Detection_in_Egocentric_Procedural_Task_Videos_CVPR_2024_paper.pdf">PDF</a> | <a href="https://github.com/robert80203/EgoPER_official">Github</a> | <a href="https://www.khoury.northeastern.edu/home/eelhami/data.htm">Project Page</a></div> | ||
</div> | ||
</div> | ||
<div class="row row_css"> | ||
<div class="col-sm"> | ||
<img class="teaser_style" src="figures/mmWave_model.png"><img> | ||
</div> | ||
<div class="col-sm col_style"> | ||
<div class="research_title">HuPR: A Benchmark for Human Pose Estimation Using Millimeter Wave Radar</div> | ||
<div class="research_author">Shih-Po Lee, Niraj Prakash Kini, Wen-Hsiao Peng, Ching-Wen Ma, Jenq-Neng Hwang</div> | ||
<div class="research_from">IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Jan 2023</div> | ||
<div class="link"><a href="https://arxiv.org/abs/2210.12564">PDF</a> | <a href="https://github.com/robert80203/HuPR-A-Benchmark-for-Human-Pose-Estimation-Using-Millimeter-Wave-Radar">Github</a> | <a href="http://mapl.nctu.edu.tw/HuPR/">Project Page</a></div> | ||
<div class="link"><a href="https://arxiv.org/abs/2210.12564">PDF</a> | <a href="https://github.com/robert80203/HuPR-A-Benchmark-for-Human-Pose-Estimation-Using-Millimeter-Wave-Radar">Github</a> | <a href="https://mapl.cs.nycu.edu.tw/HuPR/">Project Page</a></div> | ||
</div> | ||
</div> | ||
<!-- <div class="research_topic"> | ||
<div class="title_css">Video Semantic Segmentation</div> | ||
<div class=""> | ||
<img style="height:150px;width:400px;" src="figures/ivs.png"><img> | ||
<div class="research_abstract"> | ||
Video semantic segmentation aims at predicting semantic classes for every pixel in video frames. | ||
</div> | ||
</div> | ||
</div> --> | ||
<div class="row row_css"> | ||
<div class="col-sm"> | ||
<img class="teaser_style" src="figures/GSVNet.png"><img> | ||
|
@@ -116,20 +126,10 @@ | |
<div class="research_title">GSVNet: Guided Spatially-Varying Convolution for Fast Semantic Segmentation on Video</div> | ||
<div class="research_author">Shih-Po Lee, Si-Cun Chen, Wen-Hsiao Peng</div> | ||
<div class="research_from">IEEE International Conference on Multimedia and Expo (ICME), July 2021.</div> | ||
<div class="link"><a href="https://arxiv.org/abs/2103.08834">PDF</a> | <a href="https://github.com/robert80203/GSVNet">Github</a> | <a href="http://mapl.nctu.edu.tw/GSVNet/">Project Page</a></div> | ||
<div class="link"><a href="https://arxiv.org/abs/2103.08834">PDF</a> | <a href="https://github.com/robert80203/GSVNet">Github</a> | <a href="https://mapl.cs.nycu.edu.tw/GSVNet/">Project Page</a></div> | ||
</div> | ||
</div> | ||
</div> | ||
<!-- <div class="research_topic"> | ||
<div class="title_css">Weakly-Supervised Semantic Segmentation</div> | ||
<div class=""> | ||
<img style="height:250px;width:300px;" src="figures/wsss.png"><img> | ||
<div class="research_abstract"> | ||
Since pixel-wise annotations for image semantic segmentation are hard to obtain, weakly-supervised semantic segmentation adopts image-level classes to generate pseudo | ||
sematic segmentation labels for training a segmentation network. | ||
</div> | ||
</div> | ||
</div> --> | ||
<div class="row row_css"> | ||
<div class="col-sm"> | ||
<img class="teaser_style" src="figures/WSGCN.png"><img> | ||
|
@@ -138,11 +138,14 @@ | |
<div class="research_title">Weakly-Supervised Image Semantic Segmentation Using Graph Convolutional Networks</div> | ||
<div class="research_author">Shun-Yi Pan*, Cheng-You Lu*, Shih-Po Lee, Wen-Hsiao Peng</div> | ||
<div class="research_from">IEEE International Conference on Multimedia and Expo (ICME), July 2021.</div> | ||
<div class="link"><a href="https://arxiv.org/abs/2103.16762">PDF</a> | <a href="https://github.com/Xavier-Pan/WSGCN">Github</a> | <a href="http://mapl.nctu.edu.tw/WSGCN/">Project Page</a></div> | ||
<div class="link"><a href="https://arxiv.org/abs/2103.16762">PDF</a> | <a href="https://github.com/Xavier-Pan/WSGCN">Github</a> | <a href="https://mapl.cs.nycu.edu.tw/WSGCN/">Project Page</a></div> | ||
</div> | ||
</div> | ||
</div> | ||
<div class="title">Experience</div> | ||
<div id="experience" class="title"> | ||
Experience | ||
<img class="title_icon" src="figures/experience.png"></img> | ||
</div> | ||
<table class="member_table"> | ||
<tbody> | ||
<tr> | ||
|
@@ -168,9 +171,42 @@ | |
</tr> | ||
</tbody> | ||
</table> | ||
<div class="title">Publications</div> | ||
<div id="education" class="title"> | ||
Education | ||
<img class="title_icon" src="figures/education.png"></img> | ||
</div> | ||
<table class="member_table"> | ||
<tbody> | ||
<tr> | ||
<td><img class="institute_style" src='https://brand.northeastern.edu/wp-content/uploads/2022/06/ac-grid-4-red-1.svg'><img></td> | ||
<td style="vertical-align: middle;"> | ||
<div>PhD student in Khoury College of Computer Sciences, Northeastern University, Boston, USA</div> | ||
<div class="period_style">[September 2022 - present]</div> | ||
</td> | ||
</tr> | ||
<tr> | ||
<td><img class="institute_style" src='https://www.nycu.edu.tw/userfiles/nycuch/images/20230915165412300.png'><img></td> | ||
<td style="vertical-align: middle;"> | ||
<div>Master of Science in Institute of Computer Science and Engineering, National Chiao Tung University (NCTU), Taiwan</div> | ||
<div class="period_style">[September 2018 - August 2020]</div> | ||
</td> | ||
</tr> | ||
<tr> | ||
<td><img class="institute_style" src='https://www.nsysu.edu.tw/var/file/0/1000/img/80/213315840.svg'><img></td> | ||
<td style="vertical-align: middle;"> | ||
<div>Bachelor of Science in Computer Science and Engineering, National Sun Yat-sen University (NSYSU), Taiwan</div> | ||
<div class="period_style">[September 2014 - July 2018]</div> | ||
</td> | ||
</tr> | ||
</tbody> | ||
</table> | ||
<div id="publication" class="title"> | ||
Publications | ||
<img class="title_icon" src="figures/publication.png"></img> | ||
</div> | ||
<div class="publication"> | ||
<ul> | ||
<li><u>S.-P. Lee</u>, Z. Lu, Z. Zhang, M. Hoai, and E. Elhamifar, "Error Detection in Egocentric Procedural Task Videos" <i>IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), </i>June 2024.</li> | ||
<li><u>S.-P. Lee</u>, N. P. Kini, W.-H. Peng, C.-W. Ma, and J.-N. Hwang, "HuPR: A Benchmark for Human Pose Estimation Using Millimeter Wave Radar" <i>IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), </i>Jan 2023.</li> | ||
<li><u>S. P. Lee</u>, S. C. Chen, and W. H. Peng, "GSVNet: Guided Spatially-Varying Convolution for Fast Semantic Segmentation on Video" <i>IEEE International Conference on Multimedia and Expo (ICME),</i> July 2021.</li> | ||
<li>S. Y. Pan, C. Y. Lu, <u>S. P. Lee</u>, and W. H. Peng, "Weakly-Supervised Image Semantic Segmentation Using Graph Convolutional Networks" <i>IEEE International Conference on Multimedia and Expo (ICME),</i> July 2021.</li> | ||
|