C. Lv, W. Lin, and B. Zhao, Intrinsic and Isotropic Resampling for 3D Point Clouds, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022 (accepted)

C. Lv, W. Lin, and B. Zhao, Approximate Intrinsic Voxel Structure for Point Cloud Simplification, IEEE Transactions on Image Processing, vol. 30, pp. 7241-7255, 2021

[Bibtex]

B. Zhao, W. Lin, and C. Lv, Fine-Grained Patch Segmentation and Rasterization for 3D Point Cloud Attribute Compression, IEEE Transactions on Circuits and Systems for Video Technology, vol. 31, no. 12, pp. 4590-4602, 2021

A complexity-aware heat kernel signature (HKS)-based patch segmentation method is developed to effectively partition a given point into fine-grained patches that are suitable for attribute image generation while well preserving the inherent spatial correlation among points.
A new patch rasterization and rectification method is developed to achieve a balance between assignment energy and intrinsic patch shape preserving.

[Bibtex]

C. Lv, W. Lin, and B. Zhao, Voxel Structure-based Mesh Reconstruction from a 3D Point Cloud, IEEE Transactions on Multimedia, vol. 24, pp. 1815-1829, 2021

A novel voxel structure-based framework was introduced to reconstruct an isotropic mesh from a point cloud keeping important geometric features such as external and internal edges.

[Project page] [Data] [Demo] [Bibtex]

J. U. Hou, B. Zhao, N. Ansari, and W. Lin, Range Image Based Point Cloud Colorization Using Conditional Generative Model, IEEE International Conference on Image Processing (ICIP), pp. 524-528, 2019

We introduce an automatic colorization scheme based on a deep generative network for 3D point clouds. The proposed approach uses the range images of point could geometry and trains a conditional generative adversarial network to predict the color of those images.

[Bibtex]

C. Xu, W. Jia, R. Wang, Xi. He, B. Zhao, Y. Zhang, Semantic Navigation of PowerPoint-Based Lecture Video for AutoNote Generation, IEEE Transactions on Learning Technologies, 2022 (accepted)

B. Zhao, S. Xu, S. Lin, R. Wang, and X. Luo, A New Visual Interface for Searching and Navigating Slide-Based Lecture Videos, 2019 IEEE International Conference on Multimedia and Expo (ICME), pp. 928-933, 2019

The interface comprehensively derives versatile semantic clues for video content indexing and visual aid generation according to visual elements, text, and mathematical expressions included on lecture slides, speeches recorded, as well as mouse and cursor pointing actions captured during a lecture.

[Demo (MP4, ~60MB)] [Bibtex]

C. Xu, R. Wang, S. Lin, X. Luo, B. Zhao, L. Shao, and M. Hu, Lecture2Note: Automatic Generation of Lecture Notes from Slide-Based Educational Videos, 2019 IEEE International Conference on Multimedia and Expo (ICME), pp. 898-903, 2019

Most educational/lecture videos on the internet are lengthy and lack of elaborate annotations. we introduced an novel method to generate note-like video summarizations by establishing the semantic relationship between visual entities in the slide-based lecture video and their descriptive speech texts.

[Bibtex]

B. Zhao, S. Lin, X. Qi, R. Wang, and X. Luo, A Novel Approach to Automatic Detection of Presentation Slides in Educational Videos, Neural Computing and Applications, vol. 29, no. 5, pp. 1369-1382, 2018

The proposed approach mainly involves five core components: shot boundary detection, training instances collection, shot classification, slide region detection and slide transition detection.

[Bibtex]

B. Zhao, S. Lin, X. Luo, S. Xu, and R. Wang, A Novel System for Visual Navigation of Educational Videos Using Multimodal Cues, ACM Multimedia, pp. 1680-1688, 2017

The system tightly integrates multimodal cues obtained from the visual, audio and textual channels of educational videos and presents them with a series of interactive visualization components. With the help of this system, users can explore the educational video content using multiple levels of details to identify content of interest with ease.

[Demo (AVI, ~60MB)] [Bibtex]

B. Zhao, S. Lin, X. Qi, Z. Zhang, X. Luo, and R. Wang, Automatic Generation of Visual-Textual Web Video Thumbnail, ACM SIGGRAPH ASIA (Posters), pp. 1-2, 2017

We proposed an automatic approach to generate magazine-cover-like thumbnail using the salient visual and textual metadata extracted from video. Compared with traditional snapshot, the synthesized thumbnail is more informative and attractive, which would be helpful for online video selection.

[Bibtex]

B. Zhao, S. Xu, S. Lin, X. Luo, and L. Duan,A New Visual Navigation System for Exploring Biomedical Open Educational Resource (OER) Videos, Journal of the American Medical Informatics Association, vol. 23, no. e1, pp. e34-e41, 2016

Biomedical videos as open educational resources (OERs) are increasingly proliferating on the Internet. Unfortunately, seeking personally valuable content from among the vast corpus of quality yet diverse OER videos is nontrivial due to limitations of today's keyword- and content-based video retrieval techniques. To address this need, this study introduces a novel visual navigation system that facilitates users' information seeking from biomedical OER videos in mass quantity by interactively offering visual and textual navigational clues that are both semantically revealing and user-friendly.

[Demo 1: Architecture (MP4, ~18MB)] [Demo 2: System (MP4, ~75MB)] [Bibtex]

J. Hou, W. Lin, G. Yue, W. Liu, and B. Zhao, Interaction-Matrix Based Personalized Image Aesthetic Assessment, IEEE Transactions on Multimedia, 2022 (Accepted)

J. Hou, W. Lin, and B. Zhao, Content-Dependency Reduction with Multi-Task Learning in Blind Stitched Panoramic Image Quality Assessment, IEEE International Conference on Image Processing (ICIP), pp. 3463-3467, 2020

We propose a multi-task learning strategy which encourages learned representation to be less dependent on image content. A siamese network with two weight-shared CNN branches is trained to simultaneously compare the quality of two images of the same scene and predict the quality score of each image.

[Bibtex]

F. Wang, S. Xu, D. Jiang, B. Zhao, X. Dai, T. Zhou, and X. Luo, Particle Hydrodynamic Simulation of Thrombus Formation Using Velocity Decay Factor, Computer Methods and Programs in Biomedicine, 2021 (Accepted)

The proposed method for thrombus formation simulation mainly consists of three steps. First, we formulate the formation of thrombus as a particle-based model and obtain the fibrin concentration of the particles with a discretized form of the convection-diffusion-reaction equation; then, we calculate the velocity decay factor using the obtained fibrin concentration. Finally, the formation of thrombus can be simulated by applying the velocity decay factor on particles.

F. Wang, S. Lin, R. Wang, Y. Li, B. Zhao, and X. Luo, Improving Incompressible SPH Simulation Efficiency by Integrating Density-Invariant and Divergence-Free Conditions, ACM SIGGRAPH (Posters), pp. 1-2, 2018

Our method shortens the time of fluid simulation by coupling the two conditions of density-invariant and divergence-free, and achieves the same simulation effect compared with other methods. Further, we regard the displacement of particles as the only basic variable of the continuity equation, which improves the stability of the fluid to a certain extent.

[Demo (MP4, ~70MB)] [Bibtex]