Peng Gao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Peng Gao has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Guquan Jing
Beijing Normal-Hong Kong Baptist University, Zhuhai, China and Hong Kong Baptist University, Hong Kong, China
4 shared publications - Hui Zhang
Beijing Normal-Hong Kong Baptist University, Zhuhai, China
4 shared publications - Yujian Lee
Beijing Normal-Hong Kong Baptist University, Zhuhai, China
3 shared publications - Yiyang Hu
Hong Kong Baptist University, Kowloon Tong, Hong Kong, China
2 shared publications - Yunting Lai
Hong Kong Baptist University, Kowloon Tong, Hong Kong, China
2 shared publications - Jiahong Zhang
Institute of Automation, Chinese Academy of Science, Beijing, China
1 shared publication
Latest Publications
- Open Access
- 15 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 21-30
Describing-Verifying-Scoring: A Hierarchical Reasoning Framework for Zero-Shot Composed Image Retrieval
- 15 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 21-30
Open AccessDescribing-Verifying-Scoring: A Hierarchical Reasoning Framework for Zero-Shot Composed Image Retrieval
- 7 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (12) , 12830-12845
3D-Aided Pedestrian Representation Learning for Video-Based Person Re-Identification
Video-based person re-identification (Re-ID) aims to match the target pedestrian from video sequences. Recent methods perform frame-level feature extraction followed by temporal aggregation to obtain video representations. However, they pay insufficient attention to the quality of frame-level features, which suffer from issues including multi-frame misalignment, partial occlusion and appearance confusion. People live in a 3D space. 3D pedestrian representations can provide rich geometric information and shape cues that offer promising solutions to these challenges in video-based Re-ID. To mitigate these issues, this paper proposes a 3D-Aid Pedestrian Representation Learning (3DAPRL) network, which introduces 3D modality to video-based Re-ID. Specifically, two novel modules are designed, i.e., the Cross-Modal Fusion (CMF) module and the Shape-aware Spatial-Temporal Interaction (SSTI) module, to enhance pedestrian representation learning. The CMF module generates discriminative fusion representations by utilizing 3D pedestrian data, while the SSTI module learns spatial-temporal 3D shape representation which are distinguishable for finding the target pedestrian in video scenarios. Both features generated from the CMF and SSTI modules contribute to the final video representation. Extensive experiments on four challenging video-based Re-ID datasets demonstrate that our 3DAPRL network reaches better performance than state-of-the-arts methods.
- 7 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (12) , 12830-12845
3D-Aided Pedestrian Representation Learning for Video-Based Person Re-Identification
Video-based person re-identification (Re-ID) aims to match the target pedestrian from video sequences. Recent methods perform frame-level feature extraction followed by temporal aggregation to obtain video representations. However, they pay insufficient attention to the quality of frame-level features, which suffer from issues including multi-frame misalignment, partial occlusion and appearance confusion. People live in a 3D space. 3D pedestrian representations can provide rich geometric information and shape cues that offer promising solutions to these challenges in video-based Re-ID. To mitigate these issues, this paper proposes a 3D-Aid Pedestrian Representation Learning (3DAPRL) network, which introduces 3D modality to video-based Re-ID. Specifically, two novel modules are designed, i.e., the Cross-Modal Fusion (CMF) module and the Shape-aware Spatial-Temporal Interaction (SSTI) module, to enhance pedestrian representation learning. The CMF module generates discriminative fusion representations by utilizing 3D pedestrian data, while the SSTI module learns spatial-temporal 3D shape representation which are distinguishable for finding the target pedestrian in video scenarios. Both features generated from the CMF and SSTI modules contribute to the final video representation. Extensive experiments on four challenging video-based Re-ID datasets demonstrate that our 3DAPRL network reaches better performance than state-of-the-arts methods.
- Open Access
- 30 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 349-357
Contextual Reasoning for Robust Composed Image Retrieval with Vision-Language Models
- 30 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 349-357
Open AccessContextual Reasoning for Robust Composed Image Retrieval with Vision-Language Models
- Open Access
- 30 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 644-652
Text-Guided Realistic Single Image Relighting with Wavelet Mamba Diffusion Network
- 30 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 644-652
Open AccessText-Guided Realistic Single Image Relighting with Wavelet Mamba Diffusion Network
- Open Access
- 23 January 2025
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 41 (2)
MEGA-GO: functions prediction of diverse protein sequence length using Multi-scalE Graph Adaptive neural network
Motivation: The increasing accessibility of large-scale protein sequences through advanced sequencing technologies has necessitated the development of efficient and accurate methods for predicting protein function. Computational prediction models have emerged as a promising solution to expedite the annotation process. However, despite making significant progress in protein research, graph neural networks face challenges in capturing long-range structural correlations and identifying critical residues in protein graphs. Furthermore, existing models have limitations in effectively predicting the function of newly sequenced proteins that are not included in protein interaction networks. This highlights the need for novel approaches integrating protein structure and sequence data. Results: We introduce Multi-scalE Graph Adaptive neural network (MEGA-GO), highlighting the capability of capturing diverse protein sequence length features from multiple scales. The unique graph adaptive neural network architecture of MEGA-GO enables a more nuanced extraction of graph structure features, effectively capturing intricate relationships within biological data. Experimental results demonstrate that MEGA-GO outperforms mainstream protein function prediction models in the accuracy of Gene Ontology term classification, yielding 33.4%, 68.9%, and 44.6% of area under the precision-recall curve on biological process, molecular function, and cellular component domains, respectively. The rest of the experimental results reveal that our model consistently surpasses the state-of-the-art methods. Availability and implementation: The source code and data of MEGA-GO are available at https://github.com/Cheliosoops/MEGA-GO.
- 23 January 2025
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 41 (2)
Open AccessMEGA-GO: functions prediction of diverse protein sequence length using Multi-scalE Graph Adaptive neural network
Motivation: The increasing accessibility of large-scale protein sequences through advanced sequencing technologies has necessitated the development of efficient and accurate methods for predicting protein function. Computational prediction models have emerged as a promising solution to expedite the annotation process. However, despite making significant progress in protein research, graph neural networks face challenges in capturing long-range structural correlations and identifying critical residues in protein graphs. Furthermore, existing models have limitations in effectively predicting the function of newly sequenced proteins that are not included in protein interaction networks. This highlights the need for novel approaches integrating protein structure and sequence data. Results: We introduce Multi-scalE Graph Adaptive neural network (MEGA-GO), highlighting the capability of capturing diverse protein sequence length features from multiple scales. The unique graph adaptive neural network architecture of MEGA-GO enables a more nuanced extraction of graph structure features, effectively capturing intricate relationships within biological data. Experimental results demonstrate that MEGA-GO outperforms mainstream protein function prediction models in the accuracy of Gene Ontology term classification, yielding 33.4%, 68.9%, and 44.6% of area under the precision-recall curve on biological process, molecular function, and cellular component domains, respectively. The rest of the experimental results reveal that our model consistently surpasses the state-of-the-art methods. Availability and implementation: The source code and data of MEGA-GO are available at https://github.com/Cheliosoops/MEGA-GO.
- 16 August 2024
- Published by Elsevier in Computers and Electronics in Agriculture
- Vol. 225, 109338
A precise grape yield prediction method based on a modified DCNN model
- 16 August 2024
- Published by Elsevier in Computers and Electronics in Agriculture
- Vol. 225, 109338
A precise grape yield prediction method based on a modified DCNN model