ZHOU Yanghong - CAFI Research Group

Home > Staffs 2025 > 01 Team members > ZHOU Yanghong

Dr. ZHOU Yanghong

Deputy Team Leader, Research Assistant Professor at PolyU

staff description

Business development for computer aided fashion intelligence and marketing/design for computer aided fashion intelligence

It seems we can’t find what you’re looking for.

Journal

A cross-feature interaction network for 3D human pose estimation

Peng, J., Zhou, Y., & Mok, P. Y.* (2025). A cross-feature interaction network for 3D human pose estimation. Pattern Recognition Letters.

Journal

Efficient and Effective Detection of Repeated Pattern from Fronto-Parallel Images with Unknown Visual Contents

Qu, H., Zhou, Y., Mok, P. Y., Flatz, G., & Li, L. (2025). Efficient and Effective Detection of Repeated Pattern from Fronto-Parallel Images with Unknown Visual Contents. Signals, 6(1), 4.

Journal

Content Decoupled and Enhanced GAN for Sketch-guided Flexible Fashion Editing

Sun, Z., Zhou, Y., & Mok, P. Y.* (2025). CoDE-GAN: Content Decoupled and Enhanced GAN for Sketch-guided Flexible Fashion Editing. ACM Transactions on Multimedia Computing, Communications and Applications.

Journal

Blockchain-Driven Innovation in Fashion Supply Chain Contractual Party Evaluations As An Emerging Collaboration Model

Qiao, M., Chen, X., Zhou, Y., & Mok, P. Y.* (2025). Blockchain-Driven Innovation in Fashion Supply Chain Contractual Party Evaluations As An Emerging Collaboration Model. Blockchain: Research and Applications, 100266.

Journal

Feature Field Fusion for few-shot novel view synthesis

Li, J., Zhou, Y., Fan, J., Shou, D., Xu, S., & Mok, P. Y.* (2025). Feature Field Fusion for few-shot novel view synthesis. Image and Vision Computing, 42105465.

Journal

Knowledge enhanced multi-task learning for simultaneous optimization of human parsing and pose estimation

Zhou, Y., & Mok, P. Y.* (2024). Knowledge enhanced multi-task learning for simultaneous optimization of human parsing and pose estimation. Engineering Applications of Artificial Intelligence, 138, 109413

Journal

EHFusion: an efficient heterogeneous fusion model for group-based 3D human pose estimation

Peng, J., Zhou, Y., & Mok, P. Y.* (2024). EHFusion: an efficient heterogeneous fusion model for group-based 3D human pose estimation. The Visual Computer, 1-23.

Top conference

Zero-shot sketch based image retrieval via modality capacity guidance

Zhou, Y., Liu, D., & Mok, P. Y.* (2024, August). Zero-shot sketch based image retrieval via modality capacity guidance. In Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence (IJCAI) (pp. 1780-1787).

Top conference

KTPFormer: Kinematics and Trajectory Prior Knowledge-Enhanced Transformer for 3D Human Pose Estimation

Jihua Peng, Yanghong Zhou, and P. Y. Mok*, KTPFormer: Kinematics and Trajectory Prior Knowledge-Enhanced Transformer for 3D Human Pose Estimation, In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2024), Jun 17-21 2024, Seattle WA, USA.

Top conference

SCNeRF: Feature-Guided Neural Radiance Field from Sparse Inputs

Junting Li, Yanghong Zhou, and P. Y. Mok*, SCNeRF: Feature-Guided Neural Radiance Field from Sparse Inputs, In Proceedings of the IEEE/CVF 51Conference on Computer Vision and Pattern Recognition (CVPR 2024), Jun 17-21 2024, Seattle WA, USA

Dr. ZHOU Yanghong

Deputy Team Leader, Research Assistant Professor at PolyU

staff description

A cross-feature interaction network for 3D human pose estimation

Peng, J., Zhou, Y., & Mok, P. Y.* (2025). A cross-feature interaction network for 3D human pose estimation. Pattern Recognition Letters.

Efficient and Effective Detection of Repeated Pattern from Fronto-Parallel Images with Unknown Visual Contents

Qu, H., Zhou, Y., Mok, P. Y., Flatz, G., & Li, L. (2025). Efficient and Effective Detection of Repeated Pattern from Fronto-Parallel Images with Unknown Visual Contents. Signals, 6(1), 4.

Content Decoupled and Enhanced GAN for Sketch-guided Flexible Fashion Editing

Sun, Z., Zhou, Y., & Mok, P. Y.* (2025). CoDE-GAN: Content Decoupled and Enhanced GAN for Sketch-guided Flexible Fashion Editing. ACM Transactions on Multimedia Computing, Communications and Applications.

Blockchain-Driven Innovation in Fashion Supply Chain Contractual Party Evaluations As An Emerging Collaboration Model

Qiao, M., Chen, X., Zhou, Y., & Mok, P. Y.* (2025). Blockchain-Driven Innovation in Fashion Supply Chain Contractual Party Evaluations As An Emerging Collaboration Model. Blockchain: Research and Applications, 100266.

Feature Field Fusion for few-shot novel view synthesis

Li, J., Zhou, Y., Fan, J., Shou, D., Xu, S., & Mok, P. Y.* (2025). Feature Field Fusion for few-shot novel view synthesis. Image and Vision Computing, 42105465.

Knowledge enhanced multi-task learning for simultaneous optimization of human parsing and pose estimation

Zhou, Y., & Mok, P. Y.* (2024). Knowledge enhanced multi-task learning for simultaneous optimization of human parsing and pose estimation. Engineering Applications of Artificial Intelligence, 138, 109413

EHFusion: an efficient heterogeneous fusion model for group-based 3D human pose estimation

Peng, J., Zhou, Y., & Mok, P. Y.* (2024). EHFusion: an efficient heterogeneous fusion model for group-based 3D human pose estimation. The Visual Computer, 1-23.

Zero-shot sketch based image retrieval via modality capacity guidance

Zhou, Y., Liu, D., & Mok, P. Y.* (2024, August). Zero-shot sketch based image retrieval via modality capacity guidance. In Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence (IJCAI) (pp. 1780-1787).

KTPFormer: Kinematics and Trajectory Prior Knowledge-Enhanced Transformer for 3D Human Pose Estimation

Jihua Peng, Yanghong Zhou, and P. Y. Mok*, KTPFormer: Kinematics and Trajectory Prior Knowledge-Enhanced Transformer for 3D Human Pose Estimation, In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2024), Jun 17-21 2024, Seattle WA, USA.

SCNeRF: Feature-Guided Neural Radiance Field from Sparse Inputs

Junting Li, Yanghong Zhou, and P. Y. Mok*, SCNeRF: Feature-Guided Neural Radiance Field from Sparse Inputs, In Proceedings of the IEEE/CVF 51Conference on Computer Vision and Pattern Recognition (CVPR 2024), Jun 17-21 2024, Seattle WA, USA

Got a brilliant concept?

Quick Links

Get in Touch