Writing nice code is not just for a better work, but for a more wonderful world.
I am currently a Software Engineer working on Shopping Search Engine at Google.
What attract me the most is to solve real-life tasks with my machine learning and engineering knowledge.
What's more, I'm excited about the technology development and to learn something new everyday!
If you share the same interesting with me, let's have a talk!
This is a project I completed as my Master Project. When browsing the image related content online, questions or topics containing more details and emotion have higher possibility to receive attention. Unfortunately, people who are not good at it may suffer. To solve it, I proposed a new NLP task named Visual Language Rewriting (VQR) which reconstructs a bland question into a detailed and emotional style according to its paired image. For the VQR task, the ability on multi-modal understanding is required.
This is a project I completed during Google Internship. The goal of this project is to help user to find out great outfit which could be achieved with apparels in their own wardrobe.
This project is part of my Sensetime internship. When training the traffic sign detection model for self-driving vehicles, because of the hardness to create a dataset with all categories balanced, I research to generate synthesized images fo rare categories. Here, we initialized with the application of style transformation on traffic object generation.
Because of the policy, no detail or code can be shared publicly.
In this challenge, I collaborated with students and professors from three different universities. Our algorithms rank 8th, 13th, and 3rd on three tracks respectively among dozens of teams from academia and industry. During the competition, I held weekly meetings, covered the work on track-3 and contributed to the other two tracks.
This is a project during the internship at Sensetime. Our ADAS system is used in Honda self-driving. My job is to improved the performance of detection model on traffic objects, including traffic light (four status), traffic sign (20 categories) and PVB (pedestrain, vehicle, bike). Besides, due to the limited computation resource, I fused all model together by using shared convolution layers while maintaining the perfect performance.
This project cannot be put on Git cause of the policy.
When talking about understanding the traffic, the number of vehicles on road is a key to describe the congestion degree. While it is hard for detection models to predict in hard cases (like traffic jams or bad weather). Therefore, borrowing the ability of crowd density estimation methods to work in extreme congestion, I designed an FCN, whose backbone is Inception-v3, to predict the density map. To obtain the accurate estimation, during training I implemented two losses on density map and bias respectively. The bias means the difference between the ground truth of the total number and the number summed on the predicted density map. Finally, the model outperforms the detection based method and runs in real-time.
View more on Github.
This work is for NVIDIA AI CITY CHALLENGE 2018 track-2, traffic anomaly detection in surveillance video. We figure out the nature among all broken vehicles, that is whenever an anomaly happens, it leads to at least one stopped vehicle, which becomes part of the video background. According to this finding, we designed a framework and our algorithm ranks the 2nd in the final competition.
View more on Github.
Also, you can find the demo video here, and paper is here.
As we all know, almost all existing license plate recognition algorithm can only be utilized in homogeneous scenes. Therefore, I built a license plate recognition system to recognize the Chinese license plate from multi-oriented images which could handle all kinds of scenes in real-time with great robustness. My system can work in real-time and real-life without any specious modification.
View more on Github.
Contact me if want to view more or get my data.
In this project, my target is to remove tough noise on the data, which is called 'all'. Using the approach of Res-Connection, the signal of noise is obtained from the first autoencoder whose input is the 'all' signal. Sequentially, the difference between the 'all' signal and the 'noise' signal is the input of the next autoencoder. A fantastic result has been acquired from the stack of autoencoders.
View more on Github.
This is a project about detecting traffic signs on the highway. Considering the accuracy and speed, I chose the Faster-RCNN to realize the target.
View more on Github.
Contact me if want to view more or get my data.This is a project I completed during my internship at Samsung China. Because of the mobile is where the program will be used, the runtime and size are equally important. The main idea is to find the line which could be lanes and then consider the change of weight on the location of lanes. Finally, we could figure out the lane or whether the car is changing lanes.
View more on Github.
I begin to touch deep learning with completing this project. As the project going on, I become familiar with the details of deep learning. I spend plenty of time on environment building and debugging actually. It is a big motivation to witness my face recognition model running.
Contact me if want to view more. The project is too large to be Gited because of the MFC stuff.
A simple but important project for me, which triggers me to explore in deep learning and the general machine learning area. I come out with a way to classify the number in pictures, dividing every picture into parts, each of which is used to fit a Guassian distribution. Obviously, the EM mothed meets my needs well.
View more on Github.
Cupertino, California, USA, 95014
+1 831-400-7538
weijiayi1217@gmail.com
Copyright © 2021 by Jiayi Wei.