1 code implementation • 16 May 2024 • Jiancheng Pan, Muyuan Ma, Qing Ma, Cong Bai, ShengYong Chen
Continuing with the above, we propose PIR-CLIP, a domain-specific CLIP-based framework for remote sensing image-text retrieval, to address semantic noise in remote sensing vision-language representations and further improve open-domain retrieval performance.
1 code implementation • ACMMM 2023 • Jiancheng Pan, Qing Ma, Cong Bai
Our highlight is the proposal of a paradigm that draws on prior knowledge to instruct adaptive learning of vision and text representations.
Ranked #5 on Cross-Modal Retrieval on RSICD
no code implementations • 12 Oct 2023 • Qing Ma, Jiancheng Pan, Cong Bai
Our highlight is to conduct visual and textual representations in latent space, directing them as close as possible to a redundancy-free regional visual representation.
Ranked #6 on Cross-Modal Retrieval on RSITMD
1 code implementation • Machines 2023 • Zihang Wang, Xueying Sun, Hao Wei, Qing Ma, Qiang Zhang
To tackle this challenge, we proposed a pioneering two-stage hybrid Convolutional Neural Network (CNN) architecture, which connects segmentation and pose estimation in tandem.
Ranked #1 on 6D Pose Estimation using RGBD on YCB-Video
2 code implementations • ICMR 2023 • Jiancheng Pan, Qing Ma, Cong Bai
Furthermore, as the diversity and differentiation of remote sensing scenes weaken the understanding of scenes, a new metric, namely, scene recall is proposed to measure the perception of scenes by evaluating scene-level retrieval performance, which can also verify the effectiveness of our approach in reducing semantic confusion.
Ranked #7 on Cross-Modal Retrieval on RSICD
no code implementations • 27 Nov 2021 • Qing Ma, Junjun Jiang, Xianming Liu, Jiayi Ma
Learning-based methods usually use a convolutional neural network (CNN) to learn the implicit priors of HSIs.
no code implementations • 14 May 2021 • Qing Ma, Jae Chul Koh, WonSook Lee
In this paper, we introduce frequency domain loss as a constraint to further improve the quality of the RefSR results with fine details and without obvious artifacts.