Chaohong Tan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Chaohong Tan has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Haiyan Li
Beijing University of Civil Engineering and Architecture
2 shared publications - Junfeng Liu
Department of Water Conservancy and Civil Engineering, Beijing Vocational College of Agriculture, Beijing 102442, China
2 shared publications - Lei Shi
Communication University of China, Beijing, China
2 shared publications - Xiaoran Zhang
Key Laboratory of Urban Stormwater System and Water Environment, Ministry of Education, Beijing University of Civil Engineering and Architecture, Beijing 102616, China
2 shared publications - Ziyang Zhang
Key Laboratory of Urban Stormwater System and Water Environment, Ministry of Education, Beijing University of Civil Engineering and Architecture, Beijing 102616, China
2 shared publications - Chen Ma
Institute of Cyberspace Security Zhejiang University of Technology 310023 Hangzhou China
1 shared publication
Latest Publications
- 9 November 2025
- Published by Elsevier in Information Fusion
- Vol. 127
Generative recommender systems: A comprehensive survey on model, framework, and application
- 9 November 2025
- Published by Elsevier in Information Fusion
- Vol. 127
Generative recommender systems: A comprehensive survey on model, framework, and application
- 13 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 12 (5) , 3671-3683
SGG-MVAR: Cross-Modal Retrieval With Scene Graph Generation and Multiview Attribute Relationship Guidance
Cross-modal retrieval is crucial for achieving accurate and efficient information retrieval by establishing semantic correlations between heterogeneous images and text. However, traditional image-text training sets suffer from information asymmetry, which includes short lengths and limited sentence structures. This phenomenon often results in insufficient representations of essential visual information. We introduce Rich-Dataset, which offers extensive semantic information. It includes diverse real-life image-text pairs and AI-generated content across domains such as news, entertainment, education, and posters. Compared with classic benchmarks such as Flickr30k and MS-COCO, RichDataset exhibits a novel and balanced distribution. Existing cross-modal retrieval models face challenges in extracting distinct features from the emerging data, leading to low retrieval accuracy. We propose SGG-MVAR, a comprehensive retrieval model guided by multiview scene information and semantic relationships. Leveraging a scene knowledge database, our model parses scene graphs and identifies differences in attributes and relationships. We conduct extensive experiments to evaluate our proposed dataset and model. All experimental results consistently demonstrate a significant improvement in recall for cross-modal retrieval.
- 13 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 12 (5) , 3671-3683
SGG-MVAR: Cross-Modal Retrieval With Scene Graph Generation and Multiview Attribute Relationship Guidance
Cross-modal retrieval is crucial for achieving accurate and efficient information retrieval by establishing semantic correlations between heterogeneous images and text. However, traditional image-text training sets suffer from information asymmetry, which includes short lengths and limited sentence structures. This phenomenon often results in insufficient representations of essential visual information. We introduce Rich-Dataset, which offers extensive semantic information. It includes diverse real-life image-text pairs and AI-generated content across domains such as news, entertainment, education, and posters. Compared with classic benchmarks such as Flickr30k and MS-COCO, RichDataset exhibits a novel and balanced distribution. Existing cross-modal retrieval models face challenges in extracting distinct features from the emerging data, leading to low retrieval accuracy. We propose SGG-MVAR, a comprehensive retrieval model guided by multiview scene information and semantic relationships. Leveraging a scene knowledge database, our model parses scene graphs and identifies differences in attributes and relationships. We conduct extensive experiments to evaluate our proposed dataset and model. All experimental results consistently demonstrate a significant improvement in recall for cross-modal retrieval.
- Open Access
- 4 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 45-47
Openlab: A One-Stop Service Platform for Software-Defined Networks Emulation
The emergence of emerging services such as 5G/6G and AIGC has put forward higher requirements for future networks. More and more new network architectures are being proposed, and it is necessary to verify the correctness of new networking designs by emulating networks. However, existing platforms are inadequate in usability and scalability, failing to fully meet all the networking needs of future software-defined network experiment services. In this paper, we present Openlab, an open emulation platform for future network technology verification. Openlab uses virtualization technology to share heterogeneous resources and provides users with an on-demand, independent, and isolated simulation environment by test slice. In addition, it provides a user-friendly service interface to achieve one-click and multi-layer deployment of large-scale cross-domain testing environments. We evaluated the scalability of the platform by deploying real use cases.
- 4 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 45-47
Open AccessOpenlab: A One-Stop Service Platform for Software-Defined Networks Emulation
The emergence of emerging services such as 5G/6G and AIGC has put forward higher requirements for future networks. More and more new network architectures are being proposed, and it is necessary to verify the correctness of new networking designs by emulating networks. However, existing platforms are inadequate in usability and scalability, failing to fully meet all the networking needs of future software-defined network experiment services. In this paper, we present Openlab, an open emulation platform for future network technology verification. Openlab uses virtualization technology to share heterogeneous resources and provides users with an on-demand, independent, and isolated simulation environment by test slice. In addition, it provides a user-friendly service interface to achieve one-click and multi-layer deployment of large-scale cross-domain testing environments. We evaluated the scalability of the platform by deploying real use cases.
- 8 September 2022
- Published by Springer Nature in Journal of Nanoparticle Research
- Vol. 24 (9) , 1-16
Stability of SiO2 nanoparticles with complex environmental conditions with the presence of electrolyte and NOM
- 8 September 2022
- Published by Springer Nature in Journal of Nanoparticle Research
- Vol. 24 (9) , 1-16
Stability of SiO2 nanoparticles with complex environmental conditions with the presence of electrolyte and NOM
- 7 July 2020
- Published by Springer Nature in Journal of Soils and Sediments
- Vol. 20 (9) , 3487-3501
Concentration and speciation of trace metals and metalloids from road-deposited sediments in urban and rural areas of Beijing, China
- 7 July 2020
- Published by Springer Nature in Journal of Soils and Sediments
- Vol. 20 (9) , 3487-3501
Concentration and speciation of trace metals and metalloids from road-deposited sediments in urban and rural areas of Beijing, China