CakeResume Talent Search

business development, and customer relationship maintenance 24 Merchants, 6 IPs. NFT generation and 3D modeling Web 3.0, Metaverse, NFT-related consultant. OctFeb 2021 Project Engineer Acer Studying cutting-edge AI/DL skills to implement on a medical AI project. 92% accuracy on glaucoma CDR detection. Familiar with object detection, segmentation, and classification AI scenario. Good communication skills with doctors' demands and collaboration with colleagues. Patent Disclosure: Ultrasound detect and notify system. (serial number: I學歷 SepJun 2 National Taiwan University of Science and Technology Masters in Electrical Engineering Thesis

as well, I develop robust solutions that encompass various programming paradigms. Passionate about staying up-to-date with the latest advancements, I excel at leveraging AI and computer vision techniques to derive valuable insights from visual data. I have successfully applied my knowledge in domains like image classification, object detection, and video analytics. As a lifelong learner, I continuously seek professional growth, exploring emerging technologies and frameworks to expand my skill set. I collaborate with cross-functional teams, employing popular Deep Learning frameworks like TensorFlow and PyTorch, as well as libraries like OpenCV. Contributing to

Detection: Detect Player Contacts from Sensor and Video Data, 2023/03/03 AIGC (生成式AI): - Bronze medal (solo): (Kaggle) Stable Diffusion - Image to Prompts: Deduce the prompts that generated our "highly detailed, sharp focus, illustration, 3d renders of majestic, epic" images, 2023/05/16 Object detection (目標檢測): - 4th place (solo): (Aidea AI CUP) 肺腺癌病理切片影像之腫瘤氣道擴散偵測競賽 I：運用物體偵測作法於找尋STAS, 2022/06/02

. Research scope : Computer Vision : Object detection/tracking, Person Re-Identification and Video Stabilization. Projects: Single object trackingI.I.S. Research, Framework:python/pytorch • Designed a post-processing method NeighborTrack[CVPR2023] to introduce neighbor and temporal information to alleviate the error tracking of single object tracking. • Proved NeighborTrack is the state-of-the-art single-object tracking model as the accuracy on LaSOT is 72.2% AUC. NeighborTrack: Single Object Tracking by Bipartite Matching With Neighbor Tracklets and Its Applications to Sports [code] Multiple object trackingI.I.S.

Automated Android apps with Appium and Allure report framework. Developed Wi-Fi AP auto-switch channel tools with Selenium. Redesigned and refactored a multiple mobile devices control system with async processes to improve performance and reliability. Developed a automation control tool for ChromeOS devices. Trained an object detection model with YOLOV3 and integrated the model into applications to improving accuracy of automation and verification. Education National Kaohsiung University of Applied Sciences, Master’s Degree, Industrial Engineering, 2018 ~ 2021 Dissertation title: "Automatic Control System Based on Computer Vision" III Digital Education Institute, Engineer’s Degree, Big

and developing a fund sales platform. Dec 2019 – Mar 2020 Full Stack Engineer • DT42 Independently designed and constructed the user interface for the AI deep learning platform Epeuva. Developed a local labeling tool for data scientists, reducing manual efforts by a factor of 10. Enhanced real-time object and behavior detection visualization on local devices, winning the Ecosystem Prize at the Audi Innovation Award. May 2017 – Mar 2019 Front-End Developer • QNAP Collaborated on various Proof of Concepts (POCs) with backend engineers and UI designers. Engaged independently in the early-stage front-end development of