Postgraduate research students

Tong Shi

Email: 2431206s@student.gla.ac.uk

Google Scholar: Google Scholar

Wechat:StoneUofG

Github:https://github.com/stonewalking

Linkedin:https://www.linkedin.com/in/tong-shi-982b0329b/

 

Research title: Interpreting and Synthesising Human Faces and Articulated Animals from Video Data

Research summary

I am focusing on 3D reconstruction and Animation.

This entails exploring: (1) Generation and manipulation of 3D and 4D visual data by using 2D images.(2) Use synthetic and distilled data from priors (3) Animating of Avatars (Human faces, Full body humans, Animals)

Publications

List by: Type | Date

Jump to: 2026 | 2024
Number of items: 2.

2026

de Almeida, Melonie, Ivanova, Daniela, Shi, Tong, Williamson, John H. ORCID logoORCID: https://orcid.org/0000-0001-8085-7853 and Henderson, Paul ORCID logoORCID: https://orcid.org/0000-0002-5198-7445 (2026) Pixel-to-4D: Camera-Controlled Image-to-Video Generation with Dynamic 3D Gaussians. In: 28th International Conference on Pattern Recognition (ICPR 26), Lyon, France, 17-22 August 2026, (Accepted for Publication)

2024

Shi, Tong, Ge, Xuri, Jose, Joemon M. ORCID logoORCID: https://orcid.org/0000-0001-9228-1759, Pugeault, Nicolas ORCID logoORCID: https://orcid.org/0000-0002-3455-6280 and Henderson, Paul ORCID logoORCID: https://orcid.org/0000-0002-5198-7445 (2024) Detail-enhanced intra- and inter-modal interaction for audio-visual emotion recognition. In: Antonacopoulos, Apostolos, Chaudhuri, Subhasis, Chellappa, Rama, Liu, Cheng-Lin, Bhattacharya, Saumik and Pal, Umapada (eds.) Pattern Recognition: 27th International Conference, ICPR 2024, Kolkata, India, December 1–5, 2024, Proceedings, Part XXI. Series: Lecture notes in computer science (15321). Springer, pp. 451-465. ISBN 9783031783050 (doi: 10.1007/978-3-031-78305-0_29)

This list was generated on Sun May 3 00:19:33 2026 BST.
Jump to: Book Sections | Conference Proceedings
Number of items: 2.

Book Sections

Shi, Tong, Ge, Xuri, Jose, Joemon M. ORCID logoORCID: https://orcid.org/0000-0001-9228-1759, Pugeault, Nicolas ORCID logoORCID: https://orcid.org/0000-0002-3455-6280 and Henderson, Paul ORCID logoORCID: https://orcid.org/0000-0002-5198-7445 (2024) Detail-enhanced intra- and inter-modal interaction for audio-visual emotion recognition. In: Antonacopoulos, Apostolos, Chaudhuri, Subhasis, Chellappa, Rama, Liu, Cheng-Lin, Bhattacharya, Saumik and Pal, Umapada (eds.) Pattern Recognition: 27th International Conference, ICPR 2024, Kolkata, India, December 1–5, 2024, Proceedings, Part XXI. Series: Lecture notes in computer science (15321). Springer, pp. 451-465. ISBN 9783031783050 (doi: 10.1007/978-3-031-78305-0_29)

Conference Proceedings

de Almeida, Melonie, Ivanova, Daniela, Shi, Tong, Williamson, John H. ORCID logoORCID: https://orcid.org/0000-0001-8085-7853 and Henderson, Paul ORCID logoORCID: https://orcid.org/0000-0002-5198-7445 (2026) Pixel-to-4D: Camera-Controlled Image-to-Video Generation with Dynamic 3D Gaussians. In: 28th International Conference on Pattern Recognition (ICPR 26), Lyon, France, 17-22 August 2026, (Accepted for Publication)

This list was generated on Sun May 3 00:19:33 2026 BST.

Supervisors

Conferences

 

Detail-enhanced intra-and inter-modal interaction for audio-visual emotion recognition (ICPR)

https://arxiv.org/pdf/2405.16701?

Splat-Portrait: Generalizing Talking Heads with Gaussian Splatting (MMM)

Pixel-to-4D: Camera-Controlled Image-to-Video Generation with Dynamic 3D Gaussians

Additional information

Please feel free to contact me for any chat/collaboration!