I was born in Tianjin, China, graduated from Tianjin Experimental High School, and received my BS and MS degrees from Tianjin University. Now I am an incoming software engineer at Microsoft.
I am a front-end developer, Android developer, and a computer vision researcher, while aiming to become a full-stack engineer. I feel passionate about the Internet, software development, and computer science.
Reach me at email.
Sep 2015 - Jul 2019, BS of CS @ College of Intelligence and Computing, Tianjin University, Tianjin, China.
- weighted grade: 90.72; GPA: 3.80; rank: 4/~120.
- received the Tianjin Government Scholarship (award: 8k CNY) in Dec 2016 and Dec 2017.
- passed bands 4 and 6 of the College English Test (CET).
Sep 2019 - Apr 2022, MS of CS @ College of Intelligence and Computing, Tianjin University, Tianjin, China.
- weighted grade: 89.13; GPA: 3.64; rank: 1/~120.
- received the First Class Academic Scholarship (award: 12k CNY) in Dec 2019.
- received the Second Class Academic Scholarship (award: 4k CNY) in Dec 2020 and Dec 2021.
- published three academic papers, two of which were published in the top conference CVPR and top journal TIP.
Jan 2017 - Apr 2022, Part-time Android Developer @ TwTStudio, Tianjin University, Tianjin, China.
I develop and maintain on-campus Android applications such as WePeiYang and TruthBBS. WePeiYang is an on-campus Android application that helps Tianjin University students check their grades and class schedules, provide feedback to the university's administrative units, and more. This application has thousands of student users. I completed the common and gpa2 modules. In the common module, I built a lot of common components based on Retrofit, OkHttp, LiveData and some modern features of Kotlin programming language to facilitate the coding of business modules. In the gpa2 module, I wrote several custom Views to display GPA by line and radar charts.
Jul 2018 - Aug 2018, Software Engineer Intern @ Consumer BG AI Application Department, Huawei, Beijing, China.
I joined the Consumer Business Group to develop AI algorithm prototypes for cell phone cameras. In the field of computer vision, I pre-researched algorithms for artificial intelligence applications, replicating and improving algorithms proposed in published papers. During this period, I completed the quantification of a deep learning based real-time HDR algorithm running on DSP.
Apr 2019 - Jun 2019, Software Engineer Intern @ UGC Huoshan Video, ByteDance, Beijing, China.
I joined the Douyin/Huoshan team to develop and maintain the "Huoshan Video" application (and its international version "Vigo"). The development uses the Android native technology stack, including popular languages, packages and frameworks such as Kotlin, Jetpack, Retrofit, RxJava, etc. During this time, I implemented several features for our Android app, including: personalization options for country-specific users, a scrolling autoplay switch, and more. I became familiar with the process of conducting A/B tests, how to internationalize in an application, and competently performed these tasks with solid Android native development skills.
Jul 2021 - Oct 2021, Software Engineer Intern @ STCA OXO, Microsoft, Beijing, China.
I joined the Office eXperience grOup to develop and maintain Teams Approvals App which is a multi-platform application I was mainly involved in front-end development, and the main technology stack used in the project is React and TypeScript.
- I implemented the front-end part of the feature called "New Request Page". This was an update to the current UX design that affected the main flow of our application and required careful and experienced coding. I read through the relevant source code, assisted in writing the full development documentation, refactored the legacy code, and completed the work smoothly and successfully.
- I fixed a bug about user authentication caused by an internal API upgrade. I mined user logs through the Kusto query language, investigated its cause in the source code, communicated with the API provider, and finally made a workaround by modifying the back-end part of our code base.
Since Jul 2022, Software Engineer @ STCA OXO, Microsoft, Beijing, China.
Qing Guo, Wei Feng, Ruijun Gao, Yang Liu, and Song Wang. Exploring the Effects of Blur and Deblurring to Visual Object Tracking. In IEEE Transactions on Image Processing (TIP), 30:1812-1824, 2021. IEEE Xplore
This paper explores the effects of blur and deblurring to visual object tracking, and designs a general GAN-based scheme to improve a tracker's robustness to motion blur. I conducted a series of experiments on GPU servers, debugged codes espectially in deep learning, and drew figures based on quantitive results and cases.
Ruijun Gao, Qing Guo, Felix Juefei-Xu, Hongkai Yu, Huazhu Fu, Wei Feng, Yang Liu, and Song Wang. Can You Spot the Chameleon? Adversarially Camouflaging Images from Co-Salient Object Detection. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022. arXiv GitHub
In this paper, we identify a novel task: adversarial co-saliency attack. Our method, without any information on the state-of-the-art CoSOD methods, leads to significant performance degradation on various co-saliency detection datasets and makes the co-salient objects undetectable. This can have strong practical benefits in properly securing the large number of personal photos currently shared on the internet. Moreover, our method is potential to be utilized as a metric for evaluating the robustness of CoSOD methods.
Ruijun Gao, Qing Guo, Hongkai Yu, and Wei Feng. Adversarial Attack Method Against Image Classification Based on Haze Perturbation. In Scientia Sinica Informationis (SSI), 2022. SciEngine
In this work, for the first attempt, we study the effects of haze on DNNs from the perspective of adversarial attack and propose two adversarial haze attack methods, which achieve comparable attack success rates and transferability to state-of-the-art attacks. This work would contribute to the evaluation and enhancement of the robustness of DNNs against haze perturbation that may happen in the real world.
Qian Zhang, Qing Guo, Ruijun Gao, Felix Juefei-Xu, Hongkai Yu, and Wei Feng. Adversarial Relighting Against Face Recognition. In IEEE Transactions on Image Processing (TIP). (Under review)
- Excellent: Python, Kotlin, Java.
- Competent: Go, Shell, CSS.
- Excellent: Android, PyTorch.
- Proficient: Flutter, React.
- Competent: TensorFlow, Vue.
- Excellent: Retrofit, Okio, RxJava, NumPy.
- Proficient: Glide, OkHttp, JetPack.