Chubo Deng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Chubo Deng has a total of 40 co-authors. Here are the top co-authors by number of shared publications:
- Xian Sun
Chinese Academy of Sciences
9 shared publications - Hongfeng Yu
Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China
8 shared publications - Wanxuan Lu
Chinese Academy of Sciences, Aerospace Information Research Institute, Beijing, China
6 shared publications - Chenglong Liu
Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China
4 shared publications - Heming Yang
Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China
4 shared publications Kun Fu
Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China
4 shared publications
Latest Publications
- Open Access
- 1 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19  (19391404) , 12284-12300
GSCC: Graph-Structural Relationship Quantification for Remote Sensing Image Change Captioning
Remote Sensing Image Change Captioning (RSICC) is critical for interpreting Earth surface dynamics from bi-temporal imagery. Current approaches focus on isolating change regions in bi-temporal images, which is essential for bridging the semantic gap between multi-modal data and generating accurate captions. These approaches usually fall into two categories: relying on feature subtraction or auxiliary masks. However, subtracted features fail to distinguish true change regions and are allergic to noises, while auxiliary masks from annotated labels or pre-trained models introduce additional annotation and computational costs. In this work, we propose GSCC, a novel RSICC framework featuring a Change Feature Filtering Module (CFFM) and a Feature Fusion Module (FUM). The CFFM introduces a difference vector to quantify graph-structural relationship alterations across bi-temporal representations, which enables the model to selectively enhance significant changes without the need for external supervision. The FUM integrates multi-stage features and enriches semantic information for accurate caption generation. Extensive experiments on LEVIR-CC show GSCC outperforms state-of-the-art methods, demonstrating gains in semantic alignment and robustness. Code is available at https://github.com/RiHY99/GSCC.
- 1 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19  (19391404) , 12284-12300
Open AccessGSCC: Graph-Structural Relationship Quantification for Remote Sensing Image Change Captioning
Remote Sensing Image Change Captioning (RSICC) is critical for interpreting Earth surface dynamics from bi-temporal imagery. Current approaches focus on isolating change regions in bi-temporal images, which is essential for bridging the semantic gap between multi-modal data and generating accurate captions. These approaches usually fall into two categories: relying on feature subtraction or auxiliary masks. However, subtracted features fail to distinguish true change regions and are allergic to noises, while auxiliary masks from annotated labels or pre-trained models introduce additional annotation and computational costs. In this work, we propose GSCC, a novel RSICC framework featuring a Change Feature Filtering Module (CFFM) and a Feature Fusion Module (FUM). The CFFM introduces a difference vector to quantify graph-structural relationship alterations across bi-temporal representations, which enables the model to selectively enhance significant changes without the need for external supervision. The FUM integrates multi-stage features and enriches semantic information for accurate caption generation. Extensive experiments on LEVIR-CC show GSCC outperforms state-of-the-art methods, demonstrating gains in semantic alignment and robustness. Code is available at https://github.com/RiHY99/GSCC.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 23, 6019705
IBODet: Information-Bottleneck-Inspired Lightweight Oriented Detection in Remote Sensing Images
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 23, 6019705
IBODet: Information-Bottleneck-Inspired Lightweight Oriented Detection in Remote Sensing Images
- Open Access
- 8 October 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15  (1) , 1-10
Evolution of competitive systems in nature
Conflict between systems is ubiquitous in nature and throughout the universe, this study presents a novel field-theoretic framework for modeling competitive systems, which simplifies the modeling of interactions between similar objects by treating them as fields, and employs mathematical models to calculate and solve the evolutionary outcomes. The key contribution lies in developing and solving a novel class of nonlinear partial differential equations that incorporate \(\delta\)-source terms to characterize resource supply processes, and theoretical demonstrate that system evolution converges to three universal regimes(traveling waves, oscillations or stable equilibrium), with phase transition criteria determined by quantitative relationships between eigenvalues and supply parameters. Rigorous theoretical derivations and numerical results demonstrate that the model’s computations possess significant generality and applicability, offering a robust framework to explain various antagonistic phenomena observed in nature.- 8 October 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15  (1) , 1-10
Open AccessEvolution of competitive systems in nature
Conflict between systems is ubiquitous in nature and throughout the universe, this study presents a novel field-theoretic framework for modeling competitive systems, which simplifies the modeling of interactions between similar objects by treating them as fields, and employs mathematical models to calculate and solve the evolutionary outcomes. The key contribution lies in developing and solving a novel class of nonlinear partial differential equations that incorporate \(\delta\)-source terms to characterize resource supply processes, and theoretical demonstrate that system evolution converges to three universal regimes(traveling waves, oscillations or stable equilibrium), with phase transition criteria determined by quantitative relationships between eigenvalues and supply parameters. Rigorous theoretical derivations and numerical results demonstrate that the model’s computations possess significant generality and applicability, offering a robust framework to explain various antagonistic phenomena observed in nature. - 17 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63  (01962892) , 1-22
ReCon1M: A Large-Scale Benchmark Dataset for Relation Comprehension in Remote Sensing Imagery
Scene graph generation (SGG) is a high-level visual understanding and reasoning task aimed at extracting entities (such as objects) and their interrelationships from images. Significant progress has been made in the study of SGG in natural images in recent years, but its exploration in the domain of remote sensing images remains very limited. The complex characteristics of remote sensing images necessitate higher time and manual interpretation costs for annotation compared to natural images. The lack of a large-scale public SGG benchmark is a major impediment to the advancement of SGG-related research in aerial imagery. In this article, we introduce the first publicly available large-scale, million-level relation dataset in the field of remote sensing images, which is named ReCon1M. Specifically, our dataset is built upon FAIR1M and comprises 22 262 images. It includes annotations for 873 761 object bounding boxes across 60 categories and 1 052 223 relation triplets across 59 categories based on these bounding boxes. We provide a detailed description of the dataset’s characteristics and statistical information. In addition, an efficient global context-aware network (EGCAN) is proposed to improve inference efficiency in dense relation prediction through an object-pair pre-screening mechanism. By integrating visual, spatial, and semantic features, EGCAN captures fine-grained pairwise features and object-level contextual information to enhance its ability to discriminate relation. We conduct two object detection tasks and three subtasks within SGG on this dataset, assessing the performance of mainstream methods on these tasks. The experimental results show that the proposed EGCAN achieves state-of-the-art (SOTA) performance in 17 out of 24 accuracy metrics across three tasks and delivers the best performance in frames per second (FPS) for model inference. The ReCon1M dataset and related resources are available at https://recon1m-dataset.github.io/
- 17 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63  (01962892) , 1-22
ReCon1M: A Large-Scale Benchmark Dataset for Relation Comprehension in Remote Sensing Imagery
Scene graph generation (SGG) is a high-level visual understanding and reasoning task aimed at extracting entities (such as objects) and their interrelationships from images. Significant progress has been made in the study of SGG in natural images in recent years, but its exploration in the domain of remote sensing images remains very limited. The complex characteristics of remote sensing images necessitate higher time and manual interpretation costs for annotation compared to natural images. The lack of a large-scale public SGG benchmark is a major impediment to the advancement of SGG-related research in aerial imagery. In this article, we introduce the first publicly available large-scale, million-level relation dataset in the field of remote sensing images, which is named ReCon1M. Specifically, our dataset is built upon FAIR1M and comprises 22 262 images. It includes annotations for 873 761 object bounding boxes across 60 categories and 1 052 223 relation triplets across 59 categories based on these bounding boxes. We provide a detailed description of the dataset’s characteristics and statistical information. In addition, an efficient global context-aware network (EGCAN) is proposed to improve inference efficiency in dense relation prediction through an object-pair pre-screening mechanism. By integrating visual, spatial, and semantic features, EGCAN captures fine-grained pairwise features and object-level contextual information to enhance its ability to discriminate relation. We conduct two object detection tasks and three subtasks within SGG on this dataset, assessing the performance of mainstream methods on these tasks. The experimental results show that the proposed EGCAN achieves state-of-the-art (SOTA) performance in 17 out of 24 accuracy metrics across three tasks and delivers the best performance in frames per second (FPS) for model inference. The ReCon1M dataset and related resources are available at https://recon1m-dataset.github.io/
- 28 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63  (01962892) , 1-18
Ringmo-SenseV2: Remote Sensing Foundation Model for Spatiotemporal Prediction Based on Multisource Heterogeneous Time-Series Data
The rapid development of Remote Sensing (RS) technology has generated a vast amount of heterogeneous time series data from various sources, including drone videos, satellite time-series images, and multi-object trajectories. Effectively processing and analyzing this multi-source heterogeneous data for accurate spatiotemporal prediction is crucial in fields such as environmental protection and disaster response. In this paper, we propose a universal predictive foundation model named Ringmo-SenseV2 to learn the general evolutionary patterns of RS elements from massive heterogeneous data. Ringmo- SenseV2 features a Mixture-of-Heterogeneous-Experts (MoHE) Transformer, which unifies the modeling of multi-source heterogeneous time-series data. Additionally, to better capture the complex dependencies across different spatiotemporal locations, we introduce a hypergraph translator, treating embeddings of different spatiotemporal locations as nodes and employing hypergraph convolution for information propagation. Furthermore, to enhance the model’s adaptability to different evolution speeds during pre-training, we implement the Adaptive tube Masking (AM) strategy, which controls prediction difficulty by adaptively setting mask proportions for sequences with varying evolution speeds. Extensive experiments demonstrate that Ringmo-SenseV2 exhibits outstanding performance across various RS prediction tasks. Further tests on scene graph generation for RS images showcase the model’s ability to extract image features, thereby enhancing image perception tasks.
- 28 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63  (01962892) , 1-18
Ringmo-SenseV2: Remote Sensing Foundation Model for Spatiotemporal Prediction Based on Multisource Heterogeneous Time-Series Data
The rapid development of Remote Sensing (RS) technology has generated a vast amount of heterogeneous time series data from various sources, including drone videos, satellite time-series images, and multi-object trajectories. Effectively processing and analyzing this multi-source heterogeneous data for accurate spatiotemporal prediction is crucial in fields such as environmental protection and disaster response. In this paper, we propose a universal predictive foundation model named Ringmo-SenseV2 to learn the general evolutionary patterns of RS elements from massive heterogeneous data. Ringmo- SenseV2 features a Mixture-of-Heterogeneous-Experts (MoHE) Transformer, which unifies the modeling of multi-source heterogeneous time-series data. Additionally, to better capture the complex dependencies across different spatiotemporal locations, we introduce a hypergraph translator, treating embeddings of different spatiotemporal locations as nodes and employing hypergraph convolution for information propagation. Furthermore, to enhance the model’s adaptability to different evolution speeds during pre-training, we implement the Adaptive tube Masking (AM) strategy, which controls prediction difficulty by adaptively setting mask proportions for sequences with varying evolution speeds. Extensive experiments demonstrate that Ringmo-SenseV2 exhibits outstanding performance across various RS prediction tasks. Further tests on scene graph generation for RS images showcase the model’s ability to extract image features, thereby enhancing image perception tasks.
- 19 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63  (01962892) , 1-13
SoPerModel: Leveraging Social Perception for Multi-Agent Trajectory Prediction
Trajectory prediction is an essential task within various automation systems. Recent studies have highlighted that the social interactions among multiple agents are crucial for accurate predictions, relying on empirically derived human-imposed constraints to model these interactions. However, from a sociological perspective, agents’ interactions exhibit significant inherent randomness. Dependence on a priori knowledge may lead to biased estimations of data distributions across different scenarios, failing to account for this randomness. Consequently, such methodologies often do not comprehensively capture the full spectrum of social influences, thus limiting the models’ predictive efficacy. To address these issues, we propose a novel multi-agent trajectory prediction framework, SoPerModel, which incorporates a Freeform Social Evolution Module (FSEM) and a Local Perception Attention mechanism (LPA). The FSEM enables SoPerModel to naturally capture representative social interactions among agents without the reliance on additional human-derived priors. Through LPA, the model integrates both local and global social interaction information and leverages them to enhance trajectory prediction performance. Our framework is empirically evaluated on real-world trajectory prediction datasets, and the results demonstrate that our approach achieves a highly competitive performance compared with state-of-the-art models.
- 19 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63  (01962892) , 1-13
SoPerModel: Leveraging Social Perception for Multi-Agent Trajectory Prediction
Trajectory prediction is an essential task within various automation systems. Recent studies have highlighted that the social interactions among multiple agents are crucial for accurate predictions, relying on empirically derived human-imposed constraints to model these interactions. However, from a sociological perspective, agents’ interactions exhibit significant inherent randomness. Dependence on a priori knowledge may lead to biased estimations of data distributions across different scenarios, failing to account for this randomness. Consequently, such methodologies often do not comprehensively capture the full spectrum of social influences, thus limiting the models’ predictive efficacy. To address these issues, we propose a novel multi-agent trajectory prediction framework, SoPerModel, which incorporates a Freeform Social Evolution Module (FSEM) and a Local Perception Attention mechanism (LPA). The FSEM enables SoPerModel to naturally capture representative social interactions among agents without the reliance on additional human-derived priors. Through LPA, the model integrates both local and global social interaction information and leverages them to enhance trajectory prediction performance. Our framework is empirically evaluated on real-world trajectory prediction datasets, and the results demonstrate that our approach achieves a highly competitive performance compared with state-of-the-art models.
- 27 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63  (01962892) , 1-19
Hypergraph-Guided Multimodal Prototype for Remote Sensing Scene Understanding
Noticeable achievements have been made in entity-level perception tasks (e.g., object detection) in remote sensing image interpretation. But for remote sensing images carrying rich content, individual perception cannot well obtain the interaction patterns between entities. The recognition of relationships between entities is the key to deeply understanding remote sensing scenes. In this paper, we propose a hypergraph-guided multimodal prototype network (HMPNet), which performs relation recognition by matching relation representations with multimodal predicate prototypes. To overcome the imbalance of modal information in the matching process, a multimodal calibration strategy is devised, taking into account the image sub-prototype and text sub-prototype, which makes prediction results more reliable. Meanwhile, to align image and text sub-prototypes and explore relevant semantic patterns, the multimodal hypergraph is constructed to efficiently capture the associations between heterogeneous prototypes. Experimental results show that the performance of our model can reach the state-of-the-art (SOTA) level on the remote sensing scene graph generation task.
- 27 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63  (01962892) , 1-19
Hypergraph-Guided Multimodal Prototype for Remote Sensing Scene Understanding
Noticeable achievements have been made in entity-level perception tasks (e.g., object detection) in remote sensing image interpretation. But for remote sensing images carrying rich content, individual perception cannot well obtain the interaction patterns between entities. The recognition of relationships between entities is the key to deeply understanding remote sensing scenes. In this paper, we propose a hypergraph-guided multimodal prototype network (HMPNet), which performs relation recognition by matching relation representations with multimodal predicate prototypes. To overcome the imbalance of modal information in the matching process, a multimodal calibration strategy is devised, taking into account the image sub-prototype and text sub-prototype, which makes prediction results more reliable. Meanwhile, to align image and text sub-prototypes and explore relevant semantic patterns, the multimodal hypergraph is constructed to efficiently capture the associations between heterogeneous prototypes. Experimental results show that the performance of our model can reach the state-of-the-art (SOTA) level on the remote sensing scene graph generation task.
- 1 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63, 1-21
Scene-Specific Multiprototype Network for Remote Sensing Scene Graph Generation
- 1 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63, 1-21
Scene-Specific Multiprototype Network for Remote Sensing Scene Graph Generation
- 18 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 61  (01962892) , 1-21
RingMo-Sense: Remote Sensing Foundation Model for Spatiotemporal Prediction via Spatiotemporal Evolution Disentangling
Remote sensing spatiotemporal prediction aims to infer future trends from historical spatiotemporal data, e.g., videos and time series images, has a broad application prospect in many fields. The foundation model is a promising research direction for spatiotemporal information mining because of its robust feature extraction capability, and has made rapid progress in natural scenes. Nevertheless, due to the spatially multi-scale and temporally multi-scale properties in remote sensing data, these methods still encounter bottlenecks when applied to remote sensing. Therefore, we propose a foundation model for remote sensing spatiotemporal prediction via spatiotemporal evolution decoupling, abbreviated as RingMo-Sense. Considering spatial affinity, temporal continuity, and spatiotemporal interaction, we construct spatial, temporal, and spatiotemporal triple-branch prediction networks. Specifically, we use parameter-sharing and progressive joint training strategies to achieve stable long-range prediction and parameter reduction simultaneously. In addition, we build a remote sensing spatiotemporal dataset by collecting various remote sensing videos and time series images. The experimental results on six downstream spatiotemporal tasks demonstrate that the proposed model yields competitive performance.
- 18 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 61  (01962892) , 1-21
RingMo-Sense: Remote Sensing Foundation Model for Spatiotemporal Prediction via Spatiotemporal Evolution Disentangling
Remote sensing spatiotemporal prediction aims to infer future trends from historical spatiotemporal data, e.g., videos and time series images, has a broad application prospect in many fields. The foundation model is a promising research direction for spatiotemporal information mining because of its robust feature extraction capability, and has made rapid progress in natural scenes. Nevertheless, due to the spatially multi-scale and temporally multi-scale properties in remote sensing data, these methods still encounter bottlenecks when applied to remote sensing. Therefore, we propose a foundation model for remote sensing spatiotemporal prediction via spatiotemporal evolution decoupling, abbreviated as RingMo-Sense. Considering spatial affinity, temporal continuity, and spatiotemporal interaction, we construct spatial, temporal, and spatiotemporal triple-branch prediction networks. Specifically, we use parameter-sharing and progressive joint training strategies to achieve stable long-range prediction and parameter reduction simultaneously. In addition, we build a remote sensing spatiotemporal dataset by collecting various remote sensing videos and time series images. The experimental results on six downstream spatiotemporal tasks demonstrate that the proposed model yields competitive performance.
- Open Access
- 6 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 16  (19391404) , 2690-2702
A Light-Weighted Hypergraph Neural Network for Multimodal Remote Sensing Image Retrieval
With the continuous maturity of remote sensing technology, the obtained remote sensing images' quality and quantity have surpassed any previous period. In this context, the content-based remote sensing image retrieval (CBRSIR) task attracts a lot of attention and research interest. Nowadays, the previous CBRSIR works mainly face the following problems. First of all, few works can realize one to many cross-modal image retrieval task (such as using optical image to retrieve SAR, optical images at the same time); secondly, researches mainly focus on small-area, target-level retrieval, and few on semantic-level retrieval of the whole image; last but not the least, most of the existing networks are characterized by massive parameters and huge computing need, which cannot be applied to resource-constrained edge devices with power and storage limit. For the sake of alleviating these bottlenecks, the paper introduces a novel light-weighted non-local semantic fusion network based on hypergraph structure for CBRSIR (abbreviated as HGNLSF-Net). Specifically, in the framework, using the topological characteristics of hypergraph, the relationship among multiple nodes can be modeled, so as to understand the global features on remote sensing images better with fewer parameters and less computation. In addition, since the non-local semantics often involves a lot of noise, the hard-link module is constructed to filter noise. A series of experimental results on typical CBRSIR dataset, i.e., MMRSIRD well show that with fewer parameters, the proposed HGNLSF-Net outperforms other methods and achieves optimal retrieval performance.
- 6 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 16  (19391404) , 2690-2702
Open AccessA Light-Weighted Hypergraph Neural Network for Multimodal Remote Sensing Image Retrieval
With the continuous maturity of remote sensing technology, the obtained remote sensing images' quality and quantity have surpassed any previous period. In this context, the content-based remote sensing image retrieval (CBRSIR) task attracts a lot of attention and research interest. Nowadays, the previous CBRSIR works mainly face the following problems. First of all, few works can realize one to many cross-modal image retrieval task (such as using optical image to retrieve SAR, optical images at the same time); secondly, researches mainly focus on small-area, target-level retrieval, and few on semantic-level retrieval of the whole image; last but not the least, most of the existing networks are characterized by massive parameters and huge computing need, which cannot be applied to resource-constrained edge devices with power and storage limit. For the sake of alleviating these bottlenecks, the paper introduces a novel light-weighted non-local semantic fusion network based on hypergraph structure for CBRSIR (abbreviated as HGNLSF-Net). Specifically, in the framework, using the topological characteristics of hypergraph, the relationship among multiple nodes can be modeled, so as to understand the global features on remote sensing images better with fewer parameters and less computation. In addition, since the non-local semantics often involves a lot of noise, the hard-link module is constructed to filter noise. A series of experimental results on typical CBRSIR dataset, i.e., MMRSIRD well show that with fewer parameters, the proposed HGNLSF-Net outperforms other methods and achieves optimal retrieval performance.