Yang Chong

M.Eng. · New Generation Electronic Information Technology (including Quantum Technology, etc.) · GPA 3.6/4.0

• School of Information & Communication Engineering
• Research focus: computer vision, individual re-identification (ReID), vision-language models, embedded intelligent sensing systems
• First-Class Scholarship (University Level, Sep. 2026)
• 12th Datang Cup National Collegiate New Generation ICT Competition — Industry-Education Integration 5G+ Innovation Application Track, Team 3rd Prize (May 2025)

B.Eng. · Electronic Information Engineering · GPA 3.9/4.0

• Sichuan Province Outstanding Graduate (2023)
• National Scholarship (Dec. 2022)
• 13th LanQiao Cup National Software and IT Professionals Competition — Sichuan Division, MCU Design & Development (University Group), Individual 3rd Prize (May 2022)
• National Encouragement Scholarship (Dec. 2021)

Feature compression and open-set rejection unified on a CLIP-ReID backbone; identity error rate improved by 27%, meeting the single-fish engineering freeze standard

This project delivers a single-fish video runtime system for open-world fish individual re-identification. Centred on track-level identity lifecycle management, five core mechanisms — including Fast Warm-up, post-confirmation identity retention, and dynamic confidence updating — solve stable recognition under track breaks, frame-quality fluctuation, and identity conflicts.

Python · PyTorch · CLIP · ReID · Open-Set Recognition · Feature Compression

Full-device engineering: from the fish passage structure to multi-threaded synchronized acquisition software

Three 25 fps video streams are captured stably, and acquisition-plus-annotation efficiency improved by 80% over the manual workflow. A reusable engineering build-and-operation standard now supports downstream dataset production.

Embedded Systems · RFID · Global Shutter Cameras · Python Multithreading · USB 3.2 · UPVC Structural Design

A self-built bilingual portfolio: full-site SSG static pre-rendering with automated Vercel deployment

Delivered the public deployment with full-site SSG static pre-rendering and CDN caching, improving first-screen loading performance by over 60%; built a research showcase that visualises experiment data, flowcharts and key metrics of the fish individual re-identification projects; implemented a GitHub + Vercel automated deployment pipeline that releases after each commit, cutting the launch cycle to 2 minutes; and now serves as the online job portfolio in place of a traditional static resume.

Next.js · TypeScript · Tailwind CSS · Vercel · Git · MDX

A controlled multi-method experiment driving tagging standardization and selection guidance

Dorsal injection marking survival for adult fish improved to 80%; a tagging-method selection guide by fish size class was produced, providing a stable marking basis for subsequent individual-recognition dataset construction.

Experimental Design · Control Experiment · Standardized Workflow · Animal Tagging Techniques · Data Consolidation