Fg-T2M: Fine-Grained Text-Driven Human Motion Generation via Diffusion Model (2023)
Conference Proceeding
Wang, Y., Leng, Z., Li, F. W. B., Wu, S., & Liang, X. (in press). Fg-T2M: Fine-Grained Text-Driven Human Motion Generation via Diffusion Model.

Text-driven human motion generation in computer vision is both significant and challenging. However, current methods are limited to producing either deterministic or imprecise motion sequences, failing to effectively control the temporal and spatial... Read More about Fg-T2M: Fine-Grained Text-Driven Human Motion Generation via Diffusion Model.

HSE: Hybrid Species Embedding for Deep Metric Learning (2023)
Conference Proceeding
Yang, B., Sun, H., Li, F. W. B., Chen, Z., Cai, J., & Song, C. (in press). HSE: Hybrid Species Embedding for Deep Metric Learning.

Deep metric learning is crucial for finding an embedding function that can generalize to training and testing data, including unknown test classes. However, limited training samples restrict the model's generalization to downstream tasks. While addin... Read More about HSE: Hybrid Species Embedding for Deep Metric Learning.

A Mixed Reality Training System for Hand-Object Interaction in Simulated Microgravity Environments (2023)
Conference Proceeding
Zhou, K., Chen, C., Ma, Y., Leng, Z., Shum, H. P., Li, F. W., & Liang, X. (in press). A Mixed Reality Training System for Hand-Object Interaction in Simulated Microgravity Environments. In Proceedings of the 2023 International Symposium on Mixed and Augmented Reality

As human exploration of space continues to progress, the use of Mixed Reality (MR) for simulating microgravity environments and facilitating training in hand-object interaction holds immense practical significance. However, hand-object interaction in... Read More about A Mixed Reality Training System for Hand-Object Interaction in Simulated Microgravity Environments.

DrawGAN: Multi-view Generative Model Inspired By The Artist's Drawing Method (2023)
Conference Proceeding
Yang, B., Chen, Z., Li, F. W. B., Sun, H., & Cai, J. (in press). DrawGAN: Multi-view Generative Model Inspired By The Artist's Drawing Method.

We present a novel approach for modeling artists' drawing processes using an architecture that combines an unconditional generative adversarial network (GAN) with a multi-view generator and multi-discriminator. Our method excels in synthesizing vario... Read More about DrawGAN: Multi-view Generative Model Inspired By The Artist's Drawing Method.

Gamifying Experiential Learning Theory (2023)
Conference Proceeding
Alsaqqaf, A., & Li, F. W. (in press). Gamifying Experiential Learning Theory. In ICWL 2022, SETE 2022: Learning Technologies and Systems (16-28). https://doi.org/10.1007/978-3-031-33023-0_2

Aesthetic Enhancement via Color Area and Location Awareness (2022)
Conference Proceeding
Yang, B., Wang, Q., Li, F. W., Liang, X., Wei, T., Zhu, C., …Noh, S. (2022). Aesthetic Enhancement via Color Area and Location Awareness. . https://doi.org/10.2312/pg.20221247

Choosing a suitable color palette can typically improve image aesthetic, where a naive way is choosing harmonious colors from some pre-defined color combinations in color wheels. However, color palettes only consider the usage of color types without... Read More about Aesthetic Enhancement via Color Area and Location Awareness.

Tackling Data Bias in Painting Classification with Style Transfer (2022)
Conference Proceeding
Vijendran, M., Li, F. W., & Shum, H. P. (in press). Tackling Data Bias in Painting Classification with Style Transfer. . https://doi.org/10.5220/0011776600003417

It is difficult to train classifiers on paintings collections due to model bias from domain gaps and data bias from the uneven distribution of artistic styles. Previous techniques like data distillation, traditional data augmentation and style transf... Read More about Tackling Data Bias in Painting Classification with Style Transfer.

STIT: Spatio-Temporal Interaction Transformers for Human-Object Interaction Recognition in Videos (2022)
Conference Proceeding
Almushyti, M., & Li, F. W. (2022). STIT: Spatio-Temporal Interaction Transformers for Human-Object Interaction Recognition in Videos. . https://doi.org/10.1109/icpr56361.2022.9956030

Recognizing human-object interactions is challenging due to their spatio-temporal changes. We propose the SpatioTemporal Interaction Transformer-based (STIT) network to reason such changes. Specifically, spatial transformers learn humans and objects... Read More about STIT: Spatio-Temporal Interaction Transformers for Human-Object Interaction Recognition in Videos.

Geometric Features Informed Multi-person Human-object Interaction Recognition in Videos (2022)
Conference Proceeding
Qiao, T., Men, Q., Li, F. W., Kubotani, Y., Morishima, S., & Shum, H. P. (2022). Geometric Features Informed Multi-person Human-object Interaction Recognition in Videos. . https://doi.org/10.1007/978-3-031-19772-7_28

Human-Object Interaction (HOI) recognition in videos is important for analysing human activity. Most existing work focusing on visual features usually suffer from occlusion in the real-world scenarios. Such a problem will be further complicated when... Read More about Geometric Features Informed Multi-person Human-object Interaction Recognition in Videos.

STGAE: Spatial-Temporal Graph Auto-Encoder for Hand Motion Denoising (2021)
Conference Proceeding
Zhou, K., Cheng, Z., Shum, H. P., Li, F. W., & Liang, X. (2021). STGAE: Spatial-Temporal Graph Auto-Encoder for Hand Motion Denoising. . https://doi.org/10.1109/ismar52148.2021.00018

Hand object interaction in mixed reality (MR) relies on the accurate tracking and estimation of human hands, which provide users with a sense of immersion. However, raw captured hand motion data always contains errors such as joints occlusion, disloc... Read More about STGAE: Spatial-Temporal Graph Auto-Encoder for Hand Motion Denoising.