Jianan Jiang

John

Hi there! Thanks for visiting my page. 👋

🔭 I have a strong interdisciplinary background. I truly enjoy exploring the intersection of these fields, and my vision is to develop and integrate various insights into surroundings to enhance our living efficiency and quality.

🔍 Master: My focus primarily revolved around leveraging AI technologies to assist designers in enhancing their design process:

Generative AI: Diffusion Models, GANs, AutoEncoder, Vision Transformers.
Efficient Learning: Self-Supervised Learning, Multi-Modal Learning.

🔍 Undergraduate: I gained extensive experience in various engineering projects with the following interconnected aspects:

Microcontroller Development: Jetson Nano, Raspberry Pi, Stm32, PLC.
Deep Learning: Image Classfication, Object Detection.
PCB Design: Altium Designer.
Mechanical Modeling and Analysis: SolidWorks, Ansys.

Starting in my freshman year, I joined the Dean’s research group and participated in three projects. The final project, for which I was responsible, achieved notable results. It led to a breakthrough in the textile field, passed a formal technical appraisal, and facilitated collaborations with several leading companies in the industry. Furthermore, I actively participated in various technological competitions and campus activities to enrich my academic experience and campus life as a whole.

news

Dec 10, 2024	Our paper ARNet is accepted to AAAI 2025.
Nov 09, 2024	Our paper StyleWe is selected as the `Best Paper` by ACM CSCW 2024 (One of 5 Awardees, 1%).
Jul 03, 2024	Our paper HAIGEN is accepted to ACM Ubicomp/IMWUT 2024.

selected publications

AAAI’25

ARNet: Self-Supervised FG-SBIR with Unified Sample Feature Alignment and Multi-Scale Token Recycling

Jianan Jiang, Han Tang, Zhilin Jiang, Weiren Yu, and Di Wu

In Proceedings of the AAAI Conference on Artificial Intelligence, 2025

Abs DOI PDF Code

We achieved better feature alignment and representation through a straightforward framework design by optimizing features for both intra- and inter-samples, and recycling discarded patch tokens in ViT-based backbones via contrastive learning.
Ubicomp’24

HAIGEN: Towards Human-AI Collaboration for Facilitating Creativity and Style Generation in Fashion Design

Jianan Jiang, Di Wu, Hanhui Deng, Yidan Long, Wenyi Tang, and 5 more authors

Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 2024

Abs DOI PDF Video Code

We introduced a system to facilitate the entire design process with a Human-AI collaborative framework, harnessing the powerful capabilities of cloud large models and the convenience of local small models through well-designed methodologies for each modules.