Skip to content

Commit

Permalink
update
Browse files Browse the repository at this point in the history
  • Loading branch information
caodoanh2001 committed Mar 2, 2024
1 parent e85e687 commit 9ef6f00
Show file tree
Hide file tree
Showing 9 changed files with 25 additions and 18 deletions.
11 changes: 6 additions & 5 deletions _news/announcement_1.md
Original file line number Diff line number Diff line change
@@ -1,19 +1,20 @@
---
layout: post
title: I am accepted as the final recipient of the Hyundai Global Fellowship program!
title: Congratulations! I am accepted as the final recipient of the Hyundai Global Fellowship program!
date: 2022-01-27 16:40:00
description: Hyundai Motor Chung Mong-koo Scholarship
tags: formatting links
categories: sample-posts
inline: false
---
I am pleased to announce that I am selected as the final recipient of the Hyundai Global Fellowship program.

I am pleased to announce that I am selected as the final recipient of the Hyundai Global Fellowship program.

This scholarship has a big coverage.
- Full tuition fee (including entrance fee)
- learning support fee (1,000,000won per month)
- settlement allowance (only 1 time when I enter the school)
- graduation celebration incentive (only 1 time when graduate).
- Learning support fee (1,000,000won per month)
- Settlement allowance (only 1 time when I enter the school)
- Graduation celebration incentive (only 1 time when graduate).

In the 2023 Spring semester, I will pursue a Master’s degree in Computer Engineering at Korea University, Korea, with full support from this scholarship!

Expand Down
7 changes: 4 additions & 3 deletions _news/announcement_2.md
Original file line number Diff line number Diff line change
@@ -1,8 +1,9 @@
---
layout: post
title: (Accepted) Improving Human-object Interaction with Auxiliary Semantic Information and Enhanced Instance Representation
title: Congratulations! Improving Human-object Interaction with Auxiliary Semantic Information and Enhanced Instance Representation has been accepted in Pattern Recognition Letters (IF = 5.1)
date: 2023-09-26 00:00:00
description: (Accepted) Improving Human-object Interaction with Auxiliary Semantic Information and Enhanced Instance Representation
description: Congratulations! Improving Human-object Interaction with Auxiliary Semantic Information and Enhanced Instance Representation has been accepted in Pattern Recognition Letters (IF = 5.1)

tags: formatting links
categories: sample-posts
inline: false
Expand All @@ -26,4 +27,4 @@ We will publish our source code and checkpoints for this study soon!

**P/s 2**: We all know that papers are just the results of researching period, and they are not that all, they are just some milestones. We should continue to try our best in the academic career, to bring not only theorical but also practical research to the community. There is a long road to go for achieving this.

Thank you for reading!
Thank you for reading!
2 changes: 2 additions & 0 deletions _news/announcement_3.md
Original file line number Diff line number Diff line change
Expand Up @@ -9,3 +9,5 @@ inline: false
---

Our collaborative project titled "UIT-OpenViIC: An Open-domain Benchmark for Evaluating Image Captioning in Vietnamese" is currently under review for the first round. The paper involves the joint efforts of BSc. Nghia Hieu Nguyen.

<img src="https://caodoanh2001.github.io/assets/img/uit-openviic.jpg" data-canonical-src="https://caodoanh2001.github.io/assets/img/uit-openviic.jpg" width="750" height="500" />
14 changes: 9 additions & 5 deletions _news/announcement_4.md
Original file line number Diff line number Diff line change
@@ -1,13 +1,17 @@
---
layout: post
title: (Under review) DAX-Net - a dual-branch dual-task adaptive cross-weight feature fusion network for robust multi-class cancer classification in pathology images
date: 2023-07-04 13:50:00
description: (Under review) DAX-Net - a dual-branch dual-task adaptive cross-weight feature fusion network for robust multi-class cancer classification in pathology images
title: Congratulations! Our paper "DAX-Net - a dual-branch dual-task adaptive cross-weight feature fusion network for robust multi-class cancer classification in pathology images" has been accepted in Computer Methods and Programs in Biomedicine (IF = 6.1)
date: 2024-03-02 00:00:00
description: Congratulations! Our paper "DAX-Net - a dual-branch dual-task adaptive cross-weight feature fusion network for robust multi-class cancer classification in pathology images" has been accepted in Computer Methods and Programs in Biomedicine (IF = 6.1)
tags: formatting links
categories: sample-posts
inline: false
---

D.C. Bui, B. Song, K. Kim, J.T. Kwak, DAX-Net: a dual-branch dual-task adaptive cross-weight feature fusion network for robust multi-class cancer classification in pathology images, , 2023, . Paper ( Under review )
We are pleased to announce that our paper titled 'DAX-Net: A Dual-Branch Dual-Task Adaptive Cross-Weight Feature Fusion Network for Robust Multi-Class Cancer Classification in Pathology Images' has been accepted in Computer Methods and Programs in Biomedicine (IF = 6.1).

Update: After a year, we have the review comments for this paper in first round review. Started working on the revised manuscript. Not sure what will happen, but hope the best.
<img src="https://caodoanh2001.github.io/assets/img/daxnet.jpg" data-canonical-src="https://caodoanh2001.github.io/assets/img/daxnet.jpg" width="750" height="500" />

Additionally, this marks my first journal submission accepted during my master's studies in Korea.

The code, manuscript, and datasets will be released soon!
2 changes: 1 addition & 1 deletion _news/announcement_5.md
Original file line number Diff line number Diff line change
Expand Up @@ -20,4 +20,4 @@ Meet our dedicated team:

Furthermore, we are honored to share that our paper presenting this groundbreaking solution, titled "C2T-Net: Cross-Fused Transformer-Style Networks for Pedestrian Attribute Recognition," has been accepted, and we will be delivering an oral presentation at the WACV2024-RWS Workshop. This recognition underscores the innovation and impact of our work in advancing the field of pedestrian attribute recognition.

Please check our published source code [here](https://github.com/caodoanh2001/upar_challenge).
Please check our published source code [here](https://github.com/caodoanh2001/upar_challenge).
5 changes: 2 additions & 3 deletions _pages/about.md
Original file line number Diff line number Diff line change
Expand Up @@ -3,22 +3,21 @@ layout: about
title: about
permalink: /
subtitle: <a href='https://uit.edu.vn'>University of Information Technology</a>. Ho Chi Minh city, Vietnam.
subtitle: <a href='http://www.kwaklab.net/'>QuilL, School of Electrical and Engineering, Korea University</a>. Seoul, Republic of Korea.
subtitle: <a href='http://www.kwaklab.net/'>QuIIL, School of Electrical and Engineering, Korea University</a>. Seoul, Republic of Korea.

profile:
align: right
image: prof_pic.jpg
image_circular: false # crops the image to make it circular
address: >
<p>Thu Duc city, Ho Chi Minh city, Vietnam</p>
<p>Seoul, Republic of Korea</p>
news: true # includes a list of news items
selected_papers: true # includes a list of papers marked as "selected={true}"
social: true # includes social icons at the bottom of the page
---

I am Doanh C. Bui, a Bachelor of Computer Science graduate from the University of Information Technology (UIT), VNU-HCM. I completed my degree in September 2022. For a brief period, from November 2022 to February 2023, I served as a teaching assistant at the Faculty of Software Engineering, UIT. Currently, I am pursuing a master's degree in the School of Electrical Engineering at Korea University, where I am in my second semester. I am fortunate to be under the guidance of Prof. Jin Tae Kwak.
I am Doanh C. Bui, a Bachelor of Computer Science graduate from the University of Information Technology (UIT), VNU-HCM. I completed my degree in September 2022. For a brief period, from November 2022 to February 2023, I served as a teaching assistant at the Faculty of Software Engineering, UIT. Currently, I am pursuing a master's degree in the School of Electrical Engineering at Korea University, where I am in my third semester, under the supervision of Prof. Jin Tae Kwak.

Throughout my academic journey, I have focused on various aspects of Computer Vision, specifically in areas such as Object Detection, Document Image Understanding, Image Captioning, and Human-Object Interaction. Presently, my research revolves around leveraging image processing techniques for histopathology images.
<!-- You can contact me via social media: [Facebook](https://facebook.com/buicaodoanh), [Linkedin](https://www.linkedin.com/in/buicaodoanh). Email: [email protected]. -->
2 changes: 1 addition & 1 deletion _posts/2023-07-08-faster-rcnn.md
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,7 @@ Vào thời điểm trước khi nhóm phương pháp R-CNN ra đời, các phư
![](https://i.imgur.com/wxFZHHH.png)
Hình 1. Minh họa phương pháp R-CNN [1].

Phương pháp này có thể được mô tả đơn giản như sau: đầu tiên thuật toán **selective search** sẽ chọn ra khoảng $N$ vùng trên ảnh có khả năng cao chứa đối tượng. Thuật toán này chủ yếu dựa vào các đặc điểm bức ảnh như màu sắc. Trong bài báo gốc, các tác giả sử dụng $N = 2000$, tức sẽ có $2000$ vùng được đề xuất trên ảnh. Từ 2000 vùng này, ta sẽ tiến hành cắt ra từ ảnh gốc, và một mạng CNN sẽ được sử dụng để trích xuất đặc trưng của 2000 vùng ảnh này. Sau đó, từ lớp đặc trưng cuối cùng sẽ đi qua 1 lớp FC để tính toán một bộ offset $(\delta x, \delta y, \delta w, \delta h)$, trong đó $(\delta x, \delta y)$ là offset tọa độ tâm của đối tượng, $(\delta w, \delta h)$ là offset chiều rộng và chiều cao của đối tượng. Như vậy, mạng sẽ học cách bo sát đối tượng và phân lớp đối tượng từ N vùng truyền vào ban đầu. Đối tượng sẽ được phân lớp bằng thuật toán SVM (Support Vector Machine).
Phương pháp này có thể được mô tả đơn giản như sau: đầu tiên thuật toán **selective search** sẽ chọn ra khoảng $N$ vùng trên ảnh có khả năng cao chứa đối tượng. Thuật toán này chủ yếu dựa vào các đặc điểm bức ảnh như màu sắc. Trong bài báo gốc, các tác giả sử dụng $$N = 2000$$, tức sẽ có $2000$ vùng được đề xuất trên ảnh. Từ 2000 vùng này, ta sẽ tiến hành cắt ra từ ảnh gốc, và một mạng CNN sẽ được sử dụng để trích xuất đặc trưng của 2000 vùng ảnh này. Sau đó, từ lớp đặc trưng cuối cùng sẽ đi qua 1 lớp FC để tính toán một bộ offset $(\delta x, \delta y, \delta w, \delta h)$, trong đó $(\delta x, \delta y)$ là offset tọa độ tâm của đối tượng, $(\delta w, \delta h)$ là offset chiều rộng và chiều cao của đối tượng. Như vậy, mạng sẽ học cách bo sát đối tượng và phân lớp đối tượng từ N vùng truyền vào ban đầu. Đối tượng sẽ được phân lớp bằng thuật toán SVM (Support Vector Machine).

> Q: offset là gì?
Expand Down
Binary file added assets/img/daxnet.jpg
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added assets/img/uit-openviic.jpg
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.

0 comments on commit 9ef6f00

Please sign in to comment.