Zezhong Ma

Zezhong Ma

Auto-generated profile, based on publicly available information

Zezhong Ma

Chongqing Geomatic and Remote Sensing Center, Chongqing 401147, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 April 2021 in Information
Verified
Journal Article
Open access
PDF file
PLPenglong Li
Penglong Li
ZSZuoqin Shi
Zuoqin Shi
YDYi Ding
Yi Ding
LZLing Zhao
Ling Zhao
ZMZezhong Ma
Zezhong Ma
Haifeng LiHaifeng Li
Haifeng Li
Museum cultural relics represent a special material cultural heritage, and modern interpretations of them are needed in current society. Based on the catalogue data of cultural relics published by the State Administration of Cultural Heritage, this paper analyzes the continuity and intermittentness of cultural relics in time series by using the method of continuity judgment of cultural relics, analyzes the aggregation and migration of cultural relics in space by using the method of spatial analysis, and then uses cosine similarity to explain the similarity distribution in space and time. The results show that the overall distribution of cultural relics exhibits the characteristics of class aggregation, dynasty aggregation and regional aggregation. From the perspective of a time scale, cultural relics have different “life cycles”, displaying continuity, intermittentness, and similarity. From the perspective of a spatial scale, the cultural relic distribution forms a small “cultural communication circle”, showing aggregation, migration, and similarity. The temporal and spatial distribution of cultural relics exhibited more similar characteristics among dynasties that were closer together than those that were far away.

1 February 2026 in Remote Sensing
Verified
Journal Article
Open access
PDF file
LLLi Li
Li Li
ZMZezhong Ma
Zezhong Ma
Haifeng LiHaifeng Li
Haifeng Li
ZHZhenyang Huang
Zhenyang Huang
Remote sensing image semantic segmentation faces substantial challenges in training and transferring models across images with varying resolutions. This issue can be effectively mitigated by continuously learning knowledge derived from new resolutions; however, this learning process is severely plagued by catastrophic forgetting. To address this problem, this paper proposes a novel continual learning framework termed Language-Guided Resolution-Continual Learning (i.e., LaGu-RCL), which alleviates catastrophic forgetting through two complementary strategies. On the one hand, a multi-resolution image augmentation pipeline is introduced to synthesize higher- and lower-resolution variants for each training batch, allowing the model to learn from images of diverse resolutions at every training step. On the other hand, a language-guided learning strategy is proposed to aggregate features of the same resolution while separating those of different resolutions. This ensures that the knowledge acquired from previously learned resolutions is not disrupted by that from unseen resolutions, thereby mitigating catastrophic forgetting. To validate the effectiveness of the proposed approach, we construct MR-ExcavSeg, a multi-resolution dataset covering several counties in Chongqing, and conduct comparative experiments between LaGu-RCL and several state-of-the-art continual learning baselines. Experimental results demonstrate that LaGu-RCL achieves significantly superior segmentation performance and continual learning capability, verifying its advantages.