Ze Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Ze Zhang has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Enyuan Zhao
Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou, Zhejiang, China
5 shared publications - Jie Nie
Ocean University of China, Qingdao, China
4 shared publications - Xinyue Liang
Ocean University of China
4 shared publications - Lei Huang
Ocean University of China, Qingdao, China
2 shared publications - Ziyi Wan
College of Information Science and Engineering, Ocean University of China, Qingdao, China
2 shared publications - Di Niu
Ocean University of China
1 shared publication
Latest Publications
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 64, 4708022
Copy–Move Forgery Detection and Question-Answering for Remote Sensing Image
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 64, 4708022
Copy–Move Forgery Detection and Question-Answering for Remote Sensing Image
- Open Access
- 16 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 18 (19391404) , 18922-18940
Frequency Spectrum Adaptor for Remote Sensing Image–Text Retrieval
Remote sensing image–text retrieval (RSITR) is a critical task that involves parsing the content of remote sensing (RS) images to match semantically relevant text. Existing RSITR methods primarily focus on directly adopting pretrained models and performing transfer learning through fine-tuning, neglecting the complex high-dimensional structured information present in RS images, where texture, color, scale, and semantics are tightly coupled. Consequently, these methods exhibit limitations in handling specific receptive fields or preserving the structural information within RS images, leading to inaccurate retrieval matches. To mitigate this issue, this article proposes a frequency spectrum adapter for RSITR, which aims to perceive the unique structured information of RS images to facilitate the transfer of visual–linguistic knowledge from the natural domain to the RS domain. The main contributions of this article are as follows. First, a frequency-domain-based RS image–text retrieval adapter (FRS-Adapter) was developed. By expanding the spectral receptive field, it extracts the unique structured information of RS images, enhancing the fine-tuning effect of RS to natural scene domain transfer. Second, a unimodal filter bank was designed, which uses filter banks for unimodal spectral compression across multiple bands. Within each band, the spectral features of amplitude and phase structures are utilized to further enhance the representation of structured information. Third, a cross-modal spectrum mutual aggregation module was introduced to promote the deep integration of linguistic, spatial, and spectral information. This guides the retention of relevant frequency components and effectively reduces the impact of irrelevant frequency components. Fourth, we conduct quantitative and qualitative experiments on three large RS cross-modal retrieval datasets, validating the significant performance of the FRS-Adapter in RSITR.
- 16 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 18 (19391404) , 18922-18940
Open AccessFrequency Spectrum Adaptor for Remote Sensing Image–Text Retrieval
Remote sensing image–text retrieval (RSITR) is a critical task that involves parsing the content of remote sensing (RS) images to match semantically relevant text. Existing RSITR methods primarily focus on directly adopting pretrained models and performing transfer learning through fine-tuning, neglecting the complex high-dimensional structured information present in RS images, where texture, color, scale, and semantics are tightly coupled. Consequently, these methods exhibit limitations in handling specific receptive fields or preserving the structural information within RS images, leading to inaccurate retrieval matches. To mitigate this issue, this article proposes a frequency spectrum adapter for RSITR, which aims to perceive the unique structured information of RS images to facilitate the transfer of visual–linguistic knowledge from the natural domain to the RS domain. The main contributions of this article are as follows. First, a frequency-domain-based RS image–text retrieval adapter (FRS-Adapter) was developed. By expanding the spectral receptive field, it extracts the unique structured information of RS images, enhancing the fine-tuning effect of RS to natural scene domain transfer. Second, a unimodal filter bank was designed, which uses filter banks for unimodal spectral compression across multiple bands. Within each band, the spectral features of amplitude and phase structures are utilized to further enhance the representation of structured information. Third, a cross-modal spectrum mutual aggregation module was introduced to promote the deep integration of linguistic, spatial, and spectral information. This guides the retention of relevant frequency components and effectively reduces the impact of irrelevant frequency components. Fourth, we conduct quantitative and qualitative experiments on three large RS cross-modal retrieval datasets, validating the significant performance of the FRS-Adapter in RSITR.
- 13 June 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 291
Frequency domain transfer learning for remote sensing visual question answering
- 13 June 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 291
Frequency domain transfer learning for remote sensing visual question answering
- Open Access
- 10 March 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 21 (4) , 1-21
Language-guided Bias Generation Contrastive Strategy for Visual Question Answering
Visual question answering (VQA) is a challenging task that requires models to understand both visual and linguistic inputs and produce accurate answers. However, VQA models often exploit biases in datasets to make predictions rather than reasoning based on the inputs. Prior approaches to debiasing have suggested the implementation of a supplementary model, deliberately designed to exhibit bias, which subsequently informs the training of a resilient target model. Nevertheless, such techniques merely quantify the model’s divergence based on the statistical distribution of labels within the training dataset or in relation to unimodal branches. In this work, we propose a novel method of generating bias from the target model itself, called LEGO, which aims to combat the language guidance bias. Specifically, LEGO framework employs a generative network that assimilates the biases inherent in the target model by integrating adversarial goals with the principles of knowledge distillation. Then, we use a debiased contrastive learning strategy to model the language guidance bias of caption and question. In the process of modeling, in order to obtain robust semantic coreference, the multimodal representations of two semantic granularity are modeled by mutual information fusion and contrast learning difference modeling. We evaluate our method on various VQA-biased datasets, including VQA-CP2, GQA-OOD, and RSICD, and show that it outperforms similar methods.
- 10 March 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 21 (4) , 1-21
Open AccessLanguage-guided Bias Generation Contrastive Strategy for Visual Question Answering
Visual question answering (VQA) is a challenging task that requires models to understand both visual and linguistic inputs and produce accurate answers. However, VQA models often exploit biases in datasets to make predictions rather than reasoning based on the inputs. Prior approaches to debiasing have suggested the implementation of a supplementary model, deliberately designed to exhibit bias, which subsequently informs the training of a resilient target model. Nevertheless, such techniques merely quantify the model’s divergence based on the statistical distribution of labels within the training dataset or in relation to unimodal branches. In this work, we propose a novel method of generating bias from the target model itself, called LEGO, which aims to combat the language guidance bias. Specifically, LEGO framework employs a generative network that assimilates the biases inherent in the target model by integrating adversarial goals with the principles of knowledge distillation. Then, we use a debiased contrastive learning strategy to model the language guidance bias of caption and question. In the process of modeling, in order to obtain robust semantic coreference, the multimodal representations of two semantic granularity are modeled by mutual information fusion and contrast learning difference modeling. We evaluate our method on various VQA-biased datasets, including VQA-CP2, GQA-OOD, and RSICD, and show that it outperforms similar methods.
- 30 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62 (01962892) , 1-13
A Spatial-Frequency Fusion Strategy Based on Linguistic Query Refinement for RSVG
Remote Sensing Visual Grounding (RSVG) represents a pivotal task aimed at pinpointing regions highly relevant to textual descriptions by parsing remote sensing image content. Existing RSVG methodologies focus on multimodal semantic integration on specific datasets, overlooking the intricate high-dimensional information present in remote sensing images, where color, scale, and semantics are tightly coupled. Consequently, these approaches exhibit limitations in handling specific receptive fields or preserving structural information within remote sensing images, leading to insufficient localization precision. To address this issue, this paper introduces a strategy that incorporates spatial frequency information, leveraging Fourier transforms to capture global structured information from remote sensing data. This is followed by a progressive aggregation across spatial, spectral, and linguistic modalities to achieve robust semantic coreference. The primary contributions of this paper are as follows: Firstly, a spatial-frequency fusion strategy based on linguistic query refinement is proposed, which enhances visual grounding performance significantly by extracting spectral features with potent spatial perception capabilities through the expansion of the spectral receptive field. Secondly, a frequency-guided spatial module is designed, utilizing amplitude and phase-structured spectral features to augment spatial representation capabilities further. Lastly, a query-aware original attention mechanism is developed, facilitating deep integration of spatial and spectral information under linguistic guidance. Extensive experimentation on the RSVGD dataset validates the efficacy of the proposed approach, demonstrating superior performance when compared to state-of-the-art methods.
- 30 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62 (01962892) , 1-13
A Spatial-Frequency Fusion Strategy Based on Linguistic Query Refinement for RSVG
Remote Sensing Visual Grounding (RSVG) represents a pivotal task aimed at pinpointing regions highly relevant to textual descriptions by parsing remote sensing image content. Existing RSVG methodologies focus on multimodal semantic integration on specific datasets, overlooking the intricate high-dimensional information present in remote sensing images, where color, scale, and semantics are tightly coupled. Consequently, these approaches exhibit limitations in handling specific receptive fields or preserving structural information within remote sensing images, leading to insufficient localization precision. To address this issue, this paper introduces a strategy that incorporates spatial frequency information, leveraging Fourier transforms to capture global structured information from remote sensing data. This is followed by a progressive aggregation across spatial, spectral, and linguistic modalities to achieve robust semantic coreference. The primary contributions of this paper are as follows: Firstly, a spatial-frequency fusion strategy based on linguistic query refinement is proposed, which enhances visual grounding performance significantly by extracting spectral features with potent spatial perception capabilities through the expansion of the spectral receptive field. Secondly, a frequency-guided spatial module is designed, utilizing amplitude and phase-structured spectral features to augment spatial representation capabilities further. Lastly, a query-aware original attention mechanism is developed, facilitating deep integration of spatial and spectral information under linguistic guidance. Extensive experimentation on the RSVGD dataset validates the efficacy of the proposed approach, demonstrating superior performance when compared to state-of-the-art methods.