Fengguang Peng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Fengguang Peng has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
Hang Shi
4 shared publications- Rui Miao
Zhejiang Lab, Hangzhou, Zhejiang, China
2 shared publications - Bo Li
School of Artificial Intelligence, Beihang University, Beijing, China
1 shared publication - Dong Dong
Tsinghua University
1 shared publication - Gang Wang
Beijing Institute of Basic Medical Sciences, Beijing, China
1 shared publication Lijun Zhang
School of Computer Science and Engineering, Beihang University, Beijing, China
1 shared publication
Latest Publications
- 5 June 2025
- Published by Elsevier in Pattern Recognition
- Vol. 169
Progressive frequency-decoupled network with neighbor-aware self-evolving convolution kernels for pansharpening
- 5 June 2025
- Published by Elsevier in Pattern Recognition
- Vol. 169
Progressive frequency-decoupled network with neighbor-aware self-evolving convolution kernels for pansharpening
- 7 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (1) , 634-649
RGB-T Tracking With Template-Bridged Search Interaction and Target-Preserved Template Updating
The goal of RGB-Thermal (RGB-T) tracking is to utilize the synergistic and complementary strengths of RGB and TIR modalities to enhance tracking in diverse situations, with cross-modal interaction being a crucial element. Earlier methods often simply combine the features of the RGB and TIR search frames, leading to a coarse interaction that also introduced unnecessary background noise. Many other approaches sample candidate boxes from search frames and apply different fusion techniques to individual pairs of RGB and TIR boxes, which confines cross-modal interactions to local areas and results in insufficient context modeling. Additionally, mining video temporal contexts is also under-explored in RGB-T tracking. To alleviate these limitations, we propose a novel Template-Bridged Search region Interaction (TBSI) module that exploits templates as the medium to bridge the cross-modal interaction between RGB and TIR search regions by gathering and distributing target-relevant object and environment contexts. An Illumination Guided Fusion (IGF) module is designed to adaptively fuse RGB and TIR search region tokens with a global illumination factor. Furthermore, in the inference stage, we also propose an efficient Target-Preserved Template Updating (TPTU) strategy, leveraging the temporal context within video sequences to accommodate the target’s appearance change. Our proposed modules are integrated into a ViT backbone for joint feature extraction, search-template matching, and cross-modal interaction. Extensive experiments on three popular RGB-T tracking benchmarks demonstrate our method achieves new state-of-the-art performances.
- 7 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (1) , 634-649
RGB-T Tracking With Template-Bridged Search Interaction and Target-Preserved Template Updating
The goal of RGB-Thermal (RGB-T) tracking is to utilize the synergistic and complementary strengths of RGB and TIR modalities to enhance tracking in diverse situations, with cross-modal interaction being a crucial element. Earlier methods often simply combine the features of the RGB and TIR search frames, leading to a coarse interaction that also introduced unnecessary background noise. Many other approaches sample candidate boxes from search frames and apply different fusion techniques to individual pairs of RGB and TIR boxes, which confines cross-modal interactions to local areas and results in insufficient context modeling. Additionally, mining video temporal contexts is also under-explored in RGB-T tracking. To alleviate these limitations, we propose a novel Template-Bridged Search region Interaction (TBSI) module that exploits templates as the medium to bridge the cross-modal interaction between RGB and TIR search regions by gathering and distributing target-relevant object and environment contexts. An Illumination Guided Fusion (IGF) module is designed to adaptively fuse RGB and TIR search region tokens with a global illumination factor. Furthermore, in the inference stage, we also propose an efficient Target-Preserved Template Updating (TPTU) strategy, leveraging the temporal context within video sequences to accommodate the target’s appearance change. Our proposed modules are integrated into a ViT backbone for joint feature extraction, search-template matching, and cross-modal interaction. Extensive experiments on three popular RGB-T tracking benchmarks demonstrate our method achieves new state-of-the-art performances.
- 13 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62 (01962892) , 1-16
Attention-Guided Progressive Frequency-Decoupled Network for Pan-Sharpening
Existing pan-sharpening methods focus more on the processing of spatial domain features, which is difficult to balance for multiresolution performance, and prone to difficulties such as edge blurring or artifacts. In this paper, we propose an Attention-guided Progressive Frequency-decoupled Network, termed APFNN, to improve the performance of fused images in terms of spatial enhancement and spectral fidelity. The decoupling and fusion of the frequency-domain features are used as the main body, and the two-stage progressive network framework is built with the auxiliary correction by the spatial domain features, realizing fine-grained interactive fusion of dual-domain features. To optimize the APFNN, spatial feature characteristics processed with Cascading Interactive Attention (CIAtt) are used as guidance information, combined with the features of the high-resolution panchromatic image and low-resolution multispectral image for high-frequency and low-frequency decoupling, embedded into the residual dense module to form a new feature extraction component and perform subtle frequency feature fusion. Extensive qualitative and quantitative experiments have been conducted on a variety of datasets, verifying that the proposed APFNN outperforms state-of-the-art methods both in reduced-resolution and full-resolution image pan-sharpening.
- 13 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62 (01962892) , 1-16
Attention-Guided Progressive Frequency-Decoupled Network for Pan-Sharpening
Existing pan-sharpening methods focus more on the processing of spatial domain features, which is difficult to balance for multiresolution performance, and prone to difficulties such as edge blurring or artifacts. In this paper, we propose an Attention-guided Progressive Frequency-decoupled Network, termed APFNN, to improve the performance of fused images in terms of spatial enhancement and spectral fidelity. The decoupling and fusion of the frequency-domain features are used as the main body, and the two-stage progressive network framework is built with the auxiliary correction by the spatial domain features, realizing fine-grained interactive fusion of dual-domain features. To optimize the APFNN, spatial feature characteristics processed with Cascading Interactive Attention (CIAtt) are used as guidance information, combined with the features of the high-resolution panchromatic image and low-resolution multispectral image for high-frequency and low-frequency decoupling, embedded into the residual dense module to form a new feature extraction component and perform subtle frequency feature fusion. Extensive qualitative and quantitative experiments have been conducted on a variety of datasets, verifying that the proposed APFNN outperforms state-of-the-art methods both in reduced-resolution and full-resolution image pan-sharpening.
- 1 November 2023
- Published by Elsevier in Pattern Recognition
- Vol. 147
Region-adaptive and context-complementary cross modulation for RGB-T semantic segmentation
- 1 November 2023
- Published by Elsevier in Pattern Recognition
- Vol. 147
Region-adaptive and context-complementary cross modulation for RGB-T semantic segmentation