Tackling Data Bias in Painting Classification with Style Transfer (2023)
Conference Proceeding
Vijendran, M., Li, F. W., & Shum, H. P. (2023). Tackling Data Bias in Painting Classification with Style Transfer. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5 VISAPP: VISAPP (250-261). 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.

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. (2022). Aesthetic Enhancement via Color Area and Location Awareness. In Y. Yang, A. D. Parakkat, B. Deng, & S. T. Noh (Eds.), . 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.

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.

Recognising Human-Object Interactions Using Attention-based LSTMs (2019)
Conference Proceeding
Almushyti, M., & Li, F. W. (2019). Recognising Human-Object Interactions Using Attention-based LSTMs. In F. P. Vidal, G. K. . L. Tam, & J. C. Roberts (Eds.), Computer Graphics and Visual Computing (CGVC) (135-139). https://doi.org/10.2312/cgvc.20191269

Recognising Human-object interactions (HOIs) in videos is a challenge task especially when a human can interact with multiple objects. This paper attempts to solve the problem of HOIs by proposing a hierarchical framework that analyzes human-object i... Read More about Recognising Human-Object Interactions Using Attention-based LSTMs.

Deep Blind Synthesized Image Quality Assessment with Contextual Multi-Level Feature Pooling (2019)
Conference Proceeding
Wang, X., Wang, K., Yang, B., Li, F. W., & Liang, X. (2019). Deep Blind Synthesized Image Quality Assessment with Contextual Multi-Level Feature Pooling. In 2019 IEEE International Conference on Image Processing Proceedings (435-439). https://doi.org/10.1109/icip.2019.8802943

Blind image quality metrics have achieved significant improvement on traditional 2D image dataset, yet still being insufficient for evaluating synthesized images generated from depth-image-based rendering. The geometric distortions in synthesized ima... Read More about Deep Blind Synthesized Image Quality Assessment with Contextual Multi-Level Feature Pooling.

Image recoloring for home scene (2018)
Conference Proceeding
Lin, X., Wang, X., Li, F. W., Yang, B., Zhang, K., & Wei, T. (2018). Image recoloring for home scene. In VRCAI '18 Proceedings of the 16th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry. https://doi.org/10.1145/3284398.3284404

Indoor home scene coloring technology is a hot topic for home design, helping users make home coloring decisions. Image based home scene coloring is preferable for e-commerce customers since it only requires users to describe coloring expectations or... Read More about Image recoloring for home scene.

Modeling Detailed Cloud Scene from Multi-source Images (2018)
Conference Proceeding
Cen, Y., Liang, X., Chen, J., Yang, B., & Li, F. W. (2018). Modeling Detailed Cloud Scene from Multi-source Images. In H. Fu, A. Ghosh, & J. Kopf (Eds.), Pacific graphics short papers, (49-52). https://doi.org/10.2312/pg.20181278

Realistic cloud is essential for enhancing the quality of computer graphics applications, such as flight simulation. Data-driven method is an effective way in cloud modeling, but existing methods typically only utilize one data source as input. For e... Read More about Modeling Detailed Cloud Scene from Multi-source Images.

Failure rates in introductory programming revisited (2014)
Conference Proceeding
Watson, C., & Li, F. W. (2014). Failure rates in introductory programming revisited. In Å. Cajander, M. Daniels, T. Clear, & A. Pears (Eds.), Proceedings of the 2014 conference on Innovation & technology in computer science education (ITiCSE '14) (39-44). https://doi.org/10.1145/2591708.2591749

Whilst working on an upcoming meta-analysis that synthesized fifty years of research on predictors of programming performance, we made an interesting discovery. Despite several studies citing a motivation for research as the high failure rates of int... Read More about Failure rates in introductory programming revisited.

No Tests Required: Comparing Traditional and Dynamic Predictors of Programming Success (2014)
Conference Proceeding
Watson, C., Li, F. W., & Godwin, J. L. (2014). No Tests Required: Comparing Traditional and Dynamic Predictors of Programming Success. In J. . D. Dougherty, K. Nagel, A. Decker, & K. Eiselt (Eds.), Proceedings of the 45th ACM Technical Symposium on Computer Science Education (469-474). https://doi.org/10.1145/2538862.2538930

Research over the past fifty years into predictors of programming performance has yielded little improvement in the identification of at-risk students. This is possibly because research to date is based upon using static tests, which fail to reflect... Read More about No Tests Required: Comparing Traditional and Dynamic Predictors of Programming Success.

Predicting Performance in an Introductory Programming Course by Logging and Analyzing Student Programming Behavior (2013)
Conference Proceeding
Watson, C., Li, F. W., & Godwin, J. L. (2013). Predicting Performance in an Introductory Programming Course by Logging and Analyzing Student Programming Behavior. In Proceedings of the 2013 IEEE 13th International Conference on Advanced Learning Technologies (ICALT 2013) (319-323). https://doi.org/10.1109/icalt.2013.99

The high failure rates of many programming courses means there is a need to identify struggling students as early as possible. Prior research has focused upon using a set of tests to assess the use of a student's demographic, psychological and cognit... Read More about Predicting Performance in an Introductory Programming Course by Logging and Analyzing Student Programming Behavior.

BlueFix: Using Crowd-sourced Feedback to Support Programming Students in Error Diagnosis and Repair (2012)
Conference Proceeding
Watson, C., Li, F. W., & Godwin, J. L. (2012). BlueFix: Using Crowd-sourced Feedback to Support Programming Students in Error Diagnosis and Repair. In E. Popescu, Q. Li, R. Klamma, H. Leung, & M. Specht (Eds.), Advances in Web-Based Learning - ICWL 2012: 11th International Conference, Sinaia, Romania, September 2-4, 2012 ; proceedings (228-239). https://doi.org/10.1007/978-3-642-33642-3_25

Feedback is regarded as one of the most important influences on student learning and motivation. But standard compiler feedback is designed for experts - not novice programming students, who can find it difficult to interpret and understand. In this... Read More about BlueFix: Using Crowd-sourced Feedback to Support Programming Students in Error Diagnosis and Repair.

Sketching-Based Skeleton Generation (2010)
Conference Proceeding
Zheng, Q., Li, F. L., & Lau, R. (2010). Sketching-Based Skeleton Generation. In 2010 3rd IEEE International Conference on Ubi-Media Computing (U-Media 2010), 5-6 July 2010, Jinhua, China (179-186). https://doi.org/10.1109/umedia.2010.5544472

Articulated character animation can be performed by manually creating and rigging a skeleton into an unfolded 3D object. Such tasks are not trivial, as it requires a substantial amount of training and practices. Although methods have been proposed to... Read More about Sketching-Based Skeleton Generation.

Active Contour Projection for Mesh Segmentation (2009)
Conference Proceeding
Yang, F., Li, F., & Lau, R. (2009). Active Contour Projection for Mesh Segmentation. In Joint Conferences on Pervasive Computing (JCPC), 2009 ; Tamsui, Taipei, Taiwan, 3 - 5 Dec. 2009 ; [including two conferences and three workshops] (865-874). https://doi.org/10.1109/jcpc.2009.5420066

Active contour methods can be used to segment a 3D mesh into parts by iteratively moving the contour to the mesh region that minimizes the contour energy. However, as the contour moves, it often does not lie on the mesh surface. To address this probl... Read More about Active Contour Projection for Mesh Segmentation.

GameOD: An Internet Based Game-On-Demand Framework (2004)
Conference Proceeding
Li, F., Lau, R., & Kilis, D. (2004). GameOD: An Internet Based Game-On-Demand Framework. In R. Lau, & G. Baciu (Eds.), . https://doi.org/10.1145/1077534.1077559

Multiplayer online 3D games are becoming very popular in recent years. However, existing games require the complete game content to be installed prior to game playing. Since the content is usually large in size, it may be difficult to run these games... Read More about GameOD: An Internet Based Game-On-Demand Framework.

Supporting Continuous Consistency in Multiplayer Online Games (2004)
Conference Proceeding
Li, F., Li, L., & Lau, R. (2004). Supporting Continuous Consistency in Multiplayer Online Games. . https://doi.org/10.1145/1027527.1027619

Multiplayer online games have become very popular in recent years. However, they generally suffer from network latency problem. If a player changes its states, it will take some time before the changes are reflected to other concurrent players. This... Read More about Supporting Continuous Consistency in Multiplayer Online Games.