Chengtao Ji
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Chengtao Ji has a total of 52 co-authors. Here are the top co-authors by number of shared publications:
- Natalia Maria Maurits
Department of Neurology, University of Groningen, University Medical Center Groningen, Groningen, The Netherlands
3 shared publications - Jos B. T. M. Roerdink
Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, Groningen, The Netherlands
2 shared publications - Li Fan
Xi'an Jiaotong-Liverpool University, Suzhou, Jiangsu, CHINA
2 shared publications - Lingyun Yu
Xi'an Jiaotong-Liverpool University Suzhou China
2 shared publications - Menglin Kong
McGill University, Montreal, Quebec, Canada
2 shared publications - Yang Xiang
Xi'an Jiaotong-Liverpool University, Suzhou, Jiangsu, CHINA
2 shared publications
Latest Publications
- 12 January 2026
- Published by Springer Nature
- p. 517-531
Dual Prototype Attentive Graph Network for Cross-Market Recommendation
- 12 January 2026
- Published by Springer Nature
- p. 517-531
Dual Prototype Attentive Graph Network for Cross-Market Recommendation
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 5361-5365
Harnessing Light for Cold-Start Recommendations: Leveraging Epistemic Uncertainty to Enhance Performance in User-Item Interactions
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 5361-5365
Open AccessHarnessing Light for Cold-Start Recommendations: Leveraging Epistemic Uncertainty to Enhance Performance in User-Item Interactions
- 19 August 2025
- Published by Springer Nature
- p. 39-54
Exploring Cultural Heritage with AR: The TAM Case Study of Nvshu
- 19 August 2025
- Published by Springer Nature
- p. 39-54
Exploring Cultural Heritage with AR: The TAM Case Study of Nvshu
- Open Access
Dual prototype attentive graph network for cross-market recommendation
Cross-market recommender systems (CMRS) aim to utilize historical data from mature markets to promote multinational products in emerging markets. However, existing CMRS approaches often overlook the potential for shared preferences among users in different markets, focusing primarily on modeling specific preferences within each market. In this paper, we argue that incorporating both market-specific and market-shared insights can enhance the generalizability and robustness of CMRS. We propose a novel approach called Dual Prototype Attentive Graph Network for Cross-Market Recommendation (DGRE) to address this. DGRE leverages prototypes based on graph representation learning from both items and users to capture market-specific and market-shared insights. Specifically, DGRE incorporates market-shared prototypes by clustering users from various markets to identify behavioural similarities and create market-shared user profiles. Additionally, it constructs item-side prototypes by aggregating item features within each market, providing valuable market-specific insights. We conduct extensive experiments to validate the effectiveness of DGRE on a real-world cross-market dataset, and the results show that considering both market-specific and market-sharing aspects in modelling can improve the generalization and robustness of CMRS.
Open AccessDual prototype attentive graph network for cross-market recommendation
Cross-market recommender systems (CMRS) aim to utilize historical data from mature markets to promote multinational products in emerging markets. However, existing CMRS approaches often overlook the potential for shared preferences among users in different markets, focusing primarily on modeling specific preferences within each market. In this paper, we argue that incorporating both market-specific and market-shared insights can enhance the generalizability and robustness of CMRS. We propose a novel approach called Dual Prototype Attentive Graph Network for Cross-Market Recommendation (DGRE) to address this. DGRE leverages prototypes based on graph representation learning from both items and users to capture market-specific and market-shared insights. Specifically, DGRE incorporates market-shared prototypes by clustering users from various markets to identify behavioural similarities and create market-shared user profiles. Additionally, it constructs item-side prototypes by aggregating item features within each market, providing valuable market-specific insights. We conduct extensive experiments to validate the effectiveness of DGRE on a real-world cross-market dataset, and the results show that considering both market-specific and market-sharing aspects in modelling can improve the generalization and robustness of CMRS.
- 12 April 2025
- Published by Springer Nature in Journal of Visualization
- Vol. 28 (3) , 511-533
A comparative study of table-sized physicalization and digital visualization
- 12 April 2025
- Published by Springer Nature in Journal of Visualization
- Vol. 28 (3) , 511-533
A comparative study of table-sized physicalization and digital visualization
- 18 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 71 (1) , 367-378
Topology-Aware Keypoint Detection via Skeleton-Based Shape Matching
3D keypoint detection endeavors to identify well-aligned and semantically consistent elements that reflect object shapes within point clouds, which plays a significant role in wide-ranging applications such as navigation and object tracking based on mobile devices. While existing approaches prioritize either salient features or statistic distributions for alignment, they overlook the underlying spatial topology of shapes. Although some recent methods take potential skeletons into account, they fail to associate this representation with local and global topology, thus reconciling comprehensive coverage and semantic awareness. To address this, we reckon keypoint detection as the skeleton-based shape matching and propose a two-branch framework that explicitly localizes the keypoints with broad coverage and semantic coherence in an unsupervised manner. Specifically, one branch incorporates the keypoint detector with a skeleton generator to infer the coarse skeletons that represent the global topology. Meanwhile, another branch leverages skeletal sphere estimation to generate the skeletal point set that sustains the local structures, serving as the foundation for optimizing the skeletons formed by keypoints. Since these skeletal representations capture both the structural essence and semantic attributes of a shape, our model is capable of extracting semantically rich keypoints with good alignment. We extensively evaluate our method on different datasets to demonstrate its effectiveness and competitiveness in 3D keypoint detection.
- 18 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 71 (1) , 367-378
Topology-Aware Keypoint Detection via Skeleton-Based Shape Matching
3D keypoint detection endeavors to identify well-aligned and semantically consistent elements that reflect object shapes within point clouds, which plays a significant role in wide-ranging applications such as navigation and object tracking based on mobile devices. While existing approaches prioritize either salient features or statistic distributions for alignment, they overlook the underlying spatial topology of shapes. Although some recent methods take potential skeletons into account, they fail to associate this representation with local and global topology, thus reconciling comprehensive coverage and semantic awareness. To address this, we reckon keypoint detection as the skeleton-based shape matching and propose a two-branch framework that explicitly localizes the keypoints with broad coverage and semantic coherence in an unsupervised manner. Specifically, one branch incorporates the keypoint detector with a skeleton generator to infer the coarse skeletons that represent the global topology. Meanwhile, another branch leverages skeletal sphere estimation to generate the skeletal point set that sustains the local structures, serving as the foundation for optimizing the skeletons formed by keypoints. Since these skeletal representations capture both the structural essence and semantic attributes of a shape, our model is capable of extracting semantically rich keypoints with good alignment. We extensively evaluate our method on different datasets to demonstrate its effectiveness and competitiveness in 3D keypoint detection.
- Open Access
- 22 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 44-50
Immersive Virtual Reality for Digital Cultural Tourism
With the development of virtual reality (VR) technology, digital technology and informationization have driven the transformation and upgrading of the cultural and tourism industries. Although digital tourism platforms can offer online interactions, they still have several limitations such as technological constraints and insufficient user experience. Digital cultural tourism (DCT) cannot fully replace real sensory experiences such as touch and smell. To enhance the immersive experience of users roaming in the virtual Suzhou Classical Garden (SCG), we focused not only on 3D modeling and rendering but also on enhancing user experience and interactivity. During the 3D modeling phase, we employed geometry-based modeling techniques to create the architectural models and used VRoid Studio to create character models. In the rendering process, the ink wash art style was applied, providing users with a unique visual experience. In developing interactive functions, we implemented voice narration and AI communication, integrating ERNIE-Bot and GPT-SoVITS technologies to inject more intelligence and immersive experience into the dialogue system. This integration enhances the interactive functions and provides users with a smoother and more authentic interactive experience. Additionally, we tested the response rate for the AI communication function and used questionnaires to investigate user experience. The results indicate that virtual scene (VS) design and rendering have received high ratings. In the future, we will continue to develop the functions of virtual characters, striving to provide users with a more immersive virtual tour experience of the SCG.
- 22 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 44-50
Open AccessImmersive Virtual Reality for Digital Cultural Tourism
With the development of virtual reality (VR) technology, digital technology and informationization have driven the transformation and upgrading of the cultural and tourism industries. Although digital tourism platforms can offer online interactions, they still have several limitations such as technological constraints and insufficient user experience. Digital cultural tourism (DCT) cannot fully replace real sensory experiences such as touch and smell. To enhance the immersive experience of users roaming in the virtual Suzhou Classical Garden (SCG), we focused not only on 3D modeling and rendering but also on enhancing user experience and interactivity. During the 3D modeling phase, we employed geometry-based modeling techniques to create the architectural models and used VRoid Studio to create character models. In the rendering process, the ink wash art style was applied, providing users with a unique visual experience. In developing interactive functions, we implemented voice narration and AI communication, integrating ERNIE-Bot and GPT-SoVITS technologies to inject more intelligence and immersive experience into the dialogue system. This integration enhances the interactive functions and provides users with a smoother and more authentic interactive experience. Additionally, we tested the response rate for the AI communication function and used questionnaires to investigate user experience. The results indicate that virtual scene (VS) design and rendering have received high ratings. In the future, we will continue to develop the functions of virtual characters, striving to provide users with a more immersive virtual tour experience of the SCG.
- 19 November 2024
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 139
Transformer-based partner dance motion generation
- 19 November 2024
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 139
Transformer-based partner dance motion generation
- Open Access
A Comparative Study of Table Sized Physicalization and Digital Visualization
Data physicalization is gaining popularity in public and educational contexts due to its potential to make abstract data more tangible and understandable. Despite its growing use, there remains a significant gap in our understanding of how large-size physical visualizations compare to their digital counterparts in terms of user comprehension and memory retention. This study aims to bridge this knowledge gap by comparing the effectiveness of visualizing school building history data on large digital screens versus large physical models. Our experimental approach involved 32 participants who were exposed to one of the visualization mediums. We assessed their user experience and immediate understanding of the content, measured through tests after exposure, and evaluated memory retention with follow-up tests seven days later. The results revealed notable differences between the two forms of visualization: physicalization not only facilitated better initial comprehension but also significantly enhanced long-term memory retention. Furthermore, user feedback on usability was also higher on physicalization. These findings underscore the substantial impact of physicalization in improving information comprehension and retention. This study contributes crucial insights into future visualization media selection in educational and public settings.
Open AccessA Comparative Study of Table Sized Physicalization and Digital Visualization
Data physicalization is gaining popularity in public and educational contexts due to its potential to make abstract data more tangible and understandable. Despite its growing use, there remains a significant gap in our understanding of how large-size physical visualizations compare to their digital counterparts in terms of user comprehension and memory retention. This study aims to bridge this knowledge gap by comparing the effectiveness of visualizing school building history data on large digital screens versus large physical models. Our experimental approach involved 32 participants who were exposed to one of the visualization mediums. We assessed their user experience and immediate understanding of the content, measured through tests after exposure, and evaluated memory retention with follow-up tests seven days later. The results revealed notable differences between the two forms of visualization: physicalization not only facilitated better initial comprehension but also significantly enhanced long-term memory retention. Furthermore, user feedback on usability was also higher on physicalization. These findings underscore the substantial impact of physicalization in improving information comprehension and retention. This study contributes crucial insights into future visualization media selection in educational and public settings.
- Open Access
- 1 June 2024
- Published by Springer Nature in Journal of King Saud University Computer and Information Sciences
- Vol. 36 (5)
GCN: A hybrid hypergraph convolution network for skeleton-based action recognition- 1 June 2024
- Published by Springer Nature in Journal of King Saud University Computer and Information Sciences
- Vol. 36 (5)
Open AccessGCN: A hybrid hypergraph convolution network for skeleton-based action recognition