SZShan Zhao

Shan Zhao

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Shan Zhao has a total of 18 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Hierarchical Scene-Graph Consistency Learning for Remote Sensing Image-Text Retrieval

    by Shaofan Chen, Wentao Ma, Tongqing Zhou, Yue Liu, Wenxuan Tu, Xiaoxing Zhang, Shan Zhao, Lichuan Gu, Xinwang Liu


  • FRCL-MNER: A Finer Grained Rank-Based Contrastive Learning Framework for Multimodal NER

    by Tianwei Yan, Shan Zhao, Wentao Ma, Shezheng Song, Chengyu Wang, Zhibo Rao, Shizhao Chen, Zhigang Luo, Xinwang Liu

    Multimodal named entity recognition (MNER) is an emerging field that aims to automatically detect named entities and classify their categories, utilizing input text and auxiliary resources such as images. While previous studies have leveraged object detectors to preprocess images and fuse textual semantics with corresponding image features, these methods often overlook the potential finer grained information within each modality and may exacerbate error propagation due to predetection. To address these issues, we propose a finer grained rank-based contrastive learning (FRCL) framework for MNER. This framework employs a global-level contrastive learning to align multimodal semantic features and a Top-K rank-based mask strategy to construct positive–negative pairs, thereby learning a finer grained multimodal interaction representation. Experimental results from three well-known social media datasets reveal that our approach surpasses existing strong baselines, and achieves up to a 1.54% improvement on the Twitter2015 dataset. Extensive discussions further confirm the effectiveness of our approach. We will release the source code on https://github.com/augusyan/FRCL.


  • FedSH: Towards Privacy-Preserving Text-Based Person Re-Identification

    by Wentao Ma, Xinyi Wu, Shan Zhao, Tongqing Zhou, Dan Guo, Lichuan Gu, Zhiping Cai, Meng Wang

    Text-based person re-identification (ReID) has enabled canonical applications in searching for and tracking targets from large-scale surveillance images with textual descriptions. Yet, existing text-based person ReID systems employ centralized model training that gathers images captured by different institutes' cameras into one place, which poses severe privacy threats to sensitive institutional information. This work is then devoted to exploring privacy-preserving text-based person ReID and proposes the framework of FedSH by tailoring the federated learning paradigm for distributed searching knowledge extraction. Specifically, FedSH resolves the local model generalization and entity boundary obscuring limitations, caused by inner-institute data homogeneity and inter-institute data heterogeneity, via building multi-granularity feature representation and a semantically self-aligned network. Meanwhile, it reduces the communication burden introduced by the embedding for multiple modals by updating common representation subspaces during federated learning. Experimental results on two public benchmarks demonstrate that our method can achieve at most 16.47% and 16.02% person ReID performance improvement by the Rank-1 metric, compared with 6 State-of-The-Art (SoTA) baselines and 6 ablation studies. We believe that our work will inspire the community to investigate the potential of implementing Federated Learning in real-world image retrieval and ReID scenarios.