Zhaohuan ZHAN

Lecturer of Faculty of Engineering at SMBU

Email：[email protected]

詹昭煥

深圳北理莫斯科大學(xué)工程系 講師

Dr. Zhaohuan ZHAN received his Ph.D. from Sun Yat-sen University in 2024, primarily focusing on research and teaching in the fields of embodied intelligence and multimodal information processing. He published numerous papers in relevant journals and conferences, including top-tier venues in artificial intelligence such as IEEE TCSVT, Neurocomputing, and CVPR, among others. He also serves as a reviewer for important journals and conferences, including Information Fusion, IEEE TCSVT, ICCV, ACM MM, Neurocomputing, and The Visual Computer.

2024年在中山大學(xué)獲得博士學(xué)位，主要從事具身智能、多模態(tài)信息處理等領(lǐng)域的科研和教學(xué)工作。在相關(guān)領(lǐng)域期刊和會(huì)議上發(fā)表多篇論文，其中包括人工智能頂級(jí)期刊及會(huì)議IEEE TCSVT、Neurocomputing、CVPR等。擔(dān)任Information Fusion、IEEE TCSVT、ICCV、ACM MM、Neurocomputing、The visual computer等重要刊物和會(huì)議審稿人。

教育背景

2019年9月-2024年12月：中山大學(xué)，計(jì)算機(jī)科學(xué)與技術(shù)，博士

2016年9月-2019年6月：四川大學(xué)，信息與通信工程，碩士

2012年9月-2016年6月：東北大學(xué)，自動(dòng)化，學(xué)士

研究方向

具身智能、多模態(tài)信息處理、計(jì)算機(jī)視覺(jué)

招生信息

研究生招生：招收計(jì)算機(jī)、人工智能和自動(dòng)化相關(guān)專(zhuān)業(yè)研究生，提供算力、機(jī)器人和無(wú)人機(jī)等硬件平臺(tái)支持，歡迎對(duì)具身智能感興趣的同學(xué)聯(lián)系我。

基本要求：1.務(wù)實(shí)的科研態(tài)度，具有自我驅(qū)動(dòng)力；2.良好的編程能力。

本科生招生：招收有志于具身智能方向科學(xué)研究、科研競(jìng)賽的本科生。

基本要求：1.持之以恒的科研態(tài)度，參與定期討論。

Selected papers

[1] Zhaohuan Zhan, Jinghui Qin, Wei Zhuo, and Guang Tan, Enhancing vision and language navigation with prompt-based scene knowledge, IEEE Transactions on Circuits and Systems for Video Technology, 2024, 34(10):9745 - 9756.

[2] Zhaohuan Zhan, Liang Lin, and Guang Tan, Object-aware navigation for remote embodied visual referring expression, Neurocomputing, 2023, 515: 68-78.

[3] Yi Zhu, Fengda Zhu, Zhaohuan Zhan, Bingqian Lin, Jianbin Jiao, Xiaojun Chang, and Xiaodan Liang, Vision-dialog navigation by exploring cross-modal memory, IEEE/CVF conference on computer vision and pattern recognition, 2020, 10730-10739.

[4] Songchen Han, Zhaohuan Zhan, Wei Li, and Xinyan Zhang, Recurrently exploiting co-saliency of target for part-based visual tracking, EURASIP Journal on Advances in Signal Processing, 2019, (2019): 1-12.

[5] Songchen Han, Bihao Zhang, Wei Li, and Zhaohuan Zhan, Moving Object Detection for Airport Scene Using Patterns of Motion and Appearance, Journal of Aerospace Information Systems, 2021, 18(11): 852-859.

[6] 詹昭煥, 韓松臣, 李煒, 余麗莎, 基于傾向流和深度學(xué)習(xí)的機(jī)場(chǎng)運(yùn)動(dòng)目標(biāo)檢測(cè), 交通信息與安全, 2019, 1:49-57.