Jackie's Homepage

Jiancheng PAN 潘建成

I' m a second-year master student at the Institute of Computer Vision of Zhejiang University of Technology under the supervision of Dr. Qing Ma and Prof. Cong Bai. At the same time, I am a visiting student at the Department of Earth System Science at Tsinghua University with Prof. Xiaomeng Huang. Before that, I received the B.E. degree from Jiangxi Normal University in 2022, under the supervision of Prof. Aiwen Jiang.

I'm working as a student intern at Shanghai AI Lab .

X / Email / Google Scholar / Github / Photography

News

Apr, 2024: One paper is accepted by IEEE TGRS 2024.

Oct, 2023: Awarded the National Scholarship (Top 0.2%).

Jul, 2023: One paper is accepted by ACMMM 2023.

Apr, 2023: Successfully apply for ICMR Travel Award.

Apr, 2023: One paper is accepted by ICMR 2023.

Publications

My research interests include but are not limited to Multimodal Learning (Cross-modal Retrieval, Open-Vocabulary Object Detection, Large Vision-Language Models), Diffusion Models, and AI4Earth.

	PIR: Remote Sensing Image-Text Retrieval with Prior Instruction Representation Learning Jiancheng Pan, Muyuan Ma, Qing Ma, Cong Bai †, Shengyong Chen. Under Review, 2024 bib \| pdf \| code PIR-CLIP, a domain-specific CLIP-based method with prior instruction representation learning, is proposed to improve open-domain remote sensing image-text retrieval performance further.
	A Prior Instruction Representation Framework for Remote Sensing Image-text Retrieval Jiancheng Pan, Qing Ma, Cong Bai †. ACM International Conference on Multimedia (ACMMM), 2023, Oral bib \| pdf \| slide \| code A prior instruction representation framework PIR for remote sensing image-text retrieval, aimed at remote sensing vision-language understanding tasks to solve the semantic noise problem.
	Direction-Oriented Visual-semantic Embedding Model for Remote Sensing Image-text Retrieval Qing Ma, Jiancheng Pan, Cong Bai †. IEEE Transactions on Geoscience and Remote Sensing (TGRS), 2024 [IF: 8.2] bib \| pdf A novel remote sensing image-text retrieval model DOVE to solve the problem of visual-semantic imbalance and strengthen the association between vision and language.
	Reducing Semantic Confusion: Scene-aware Aggregation Network for Remote Sensing Cross-modal Retrieval Jiancheng Pan, Qing Ma †, Cong Bai. ACM International Conference on Multimedia Retrieval (ICMR), 2023, Oral bib \| pdf \| code A novel scene-aware remote sensing cross-modal retrieval network SWAN to reduce semantic confusion by improving the fine-grained perception of the scene.
	Deliberation on object-aware video style transfer network with longshort temporal and depth-consistent constraints Yunxin Liu, Aiwen Jiang †, Jiancheng Pan, et al. Neural Computing and Applications, 2021 [IF: 6.0] bib \| pdf An efficient video style transfer algorithm that utilizes salient object-awareness and depth consistency to achieve real-time processing, high rendering quality, and coherent stylization.