Xiaoyi Han

Short Bio

My Name is Xiaoyi Han.

My research lies at the intersection of Computer Vision and Natural Language Processing, with a particular focus on Multi-Modal Learning (Scene Graph Generation). My research interests are broad, ranging from basic Computer Vision tasks such as Object Detection and Image Segmentation, to exploring the frontiers of Cross-Modal understanding and generation, such as Image Caption and Video Question Answering, etc.

News

[Oct. 2024] My paper about Fire and Smoke Detection Method is accepted to ACM MM asia 2024.🔥
[Jun. 2024] My paper about Fire and Smoke Detection Benchmark is accepted to PRCV 2025.🔥

Selected Publications [Google Scholar]

acm mm asia

Fire and Smoke Detection with Burning Intensity Representation

Xiaoyi Han, Yanfei Wu, Nan Pu, Zunlei Feng, Qifei Zhang, Yijun Bei, Lechao Cheng

ACM Multimedia Asia Conference ((MM Asia), 2024.

Arxiv Code Project Page ACM BibTex

prcv

Benchmarking Multi-Scene Fire and Smoke Detection

Xiaoyi Han, Nan Pu, Zunlei Feng, Yijun Bei, Qifei Zhang, Lechao Cheng, Liang Xue

Pattern Recognition and Computer Vision (PRCV), 2024.

Arxiv Code Project Page Springer BibTex

Projects

A Simple Computer Vision Project written with Pytorch (22 Github Stars)

This project includes Image Classification and Object Detection tasks, and semantic segmentation task will be added later.

Honors and Awards

[Jul. 2018] Outstanding Graduates of Beijing Ordinary Colleges and Universities.✨
[Nov. 2016] Chinese National Scholarship for the 2015-2016 Academic Year.✨