Page Not Found
Page not found. Your pixels are in another canvas.
Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
About me
About me
Page not in menu
This is a page not in th emain menu
Posts
Tracking as a Probability Model
This is the summarised note to deduce the predict & update tracking cycle.
An Attempt to Reduce the Number of Training Samples for Convolutional Neural Networks
Training deep neural networks can be resources-consuming. The budget required is in- creasing with the size of the dataset. During the past ten years, many achievements are dedicated to accelerating the convergence speed with heuristic or theoretical training procedures. However, we still need the whole dataset to train the network and paying for a large dataset may not pay back well if we can use a smaller subset to achieve an acceptable performance. In order to reduce the number of training samples needed, we first adapted and evaluated three methods, Patterns by Ordered Projections (POP), En- hanced Global Density-based Instance Selection (EGDIS), and Curriculum Learning (CL), to reduce the size of two image datasets, CIFAR10 and CIFAR100, for the clas- sification task. Based on the analysis, we present our main contributions: improved CL and evaluated its two variations, the Weighted Curriculum Learning (WCL) and the Boundary based Weighted Curriculum Learning (BWCL). The WCL outperforms POP and EGDIS in terms of both classification accuracy and time complexity. Also, WCL and BWCL achieve comparable performance compared with CL while keeping a portion of hard examples. Besides, we proposed a trade-off framework for WCL to select a subset of samples according to the acceptable relative accuracy and the original datasets.
portfolio
Portfolio item number 1
Short description of portfolio item number 1
Portfolio item number 2
Short description of portfolio item number 2
publications
Depth Estimation from a Single Omnidirectional Image Using Domain Adaptation
Yihong Wu, Yuwen Heng, Mahesan Niranjan, and Hansung Kim. Depth estimation from a single omnidirectional image using domain adaptation. In European Conference on Visual Media Production (CVMP), pages 1–9, 2021
CAM-SegNet: A Context-Aware Dense Material Segmentation Network for Sparsely Labelled Datasets
Yuwen Heng, Yihong Wu, Srinandan Dasmahapatra, and Hansung Kim. CAM-SegNet: A Context-Aware Dense Material Segmentation Network for Sparsely Labelled Datasets. In 17th International Conference on Computer Vision Theory and Applications (VISAPP), volume 5, pages 190–201, 2022b
Room Acoustic Properties Estimation from a Single 360° Photo
Mona Alawadh, Yihong Wu, Yuwen Heng, Luca Remaggi, Mahesan Niranjan, and Hansung Kim. Room acoustic properties estimation from a single 360° photo. In 2022 30th European Signal Processing Conference (EUSIPCO). IEEE, 2022
Enhancing Material Features Using Dynamic Backward Attention on Cross-Resolution Patches
Yuwen Heng, Yihong Wu, Srinandan Dasmahapatra, and Hansung Kim. Enhancing material features using dynamic backward attention on cross-resolution patches. In 33rd British Machine Vision Conference 2022, BMVC 2022, London, UK, November 21-24, 2022. BMVA Press, 2022a
Material Recognition for Immersive Interactions in Virtual/Augmented Reality
Yuwen Heng, Srinandan Dasmahapatra, and Hansung Kim. Material recognition for immersive interactions in virtual/augmented reality. In 2023 IEEE conference on virtual reality and 3D user interfaces abstracts and workshops (VRW), pages 577–578. IEEE, 2023
Depth Estimation for a Single Omnidirectional Image with Reversed-gradient Warming-up Thresholds Discriminator
Yihong Wu, Yuwen Heng, Mahesan Niranjan, and Hansung Kim. Depth estimation for a single omnidirectional image with reversed-gradient warming-up thresholds discriminator. In 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023
An investigation into dense material segmentation
Yuwen Heng. An investigation into dense material segmentation. PhD thesis, University of Southampton, United Kingdom, 2023
Enhancing Material Features Using Dynamic Backward Attention on Cross-Resolution Patches
Yuwen Heng, Yihong Wu, Srinandan Dasmahapatra, and Hansung Kim. Dense material segmentation with context-aware network. In A. Augusto de Sousa, Kurt Debattista, Alexis Paljic, Mounia Ziat, Christophe Hurter, Helen Purchase, Giovanni Maria Farinella, Petia Radeva, and Kadi Bouatouch, editors, Computer Vision, Imaging and Computer Graphics Theory and Applications, pages 66–88, Cham, 2023b. Springer Nature Switzerland. ISBN 978-3-031-45725-8
SliceFormer: Deep Dense Depth Estimation from a Single Indoor Omnidirectional Image using a Slice-based Transformer
Yihong Wu, Yuwen Heng, Mahesan Niranjan, and Hansung Kim. Sliceformer: Deep dense depth estimation from a single indoor omnidirectional image using a slice-based transformer. In 2024 International Conference on Electronics, Information, and Communication (ICEIC). IEEE, 2024
Advancements in 3D Lane Detection Using LiDAR Point Clouds: From Data Collection to Model Development
Runkai Zhao, Yuwen Heng, Yuanda Gao, Shilei Liu, Heng Wang, Changhao Yao, Jiawen Chen, and Weidong Cai. Advancements in 3d lane detection using lidar point clouds: From data collection to model development. In 2024 IEEE International Conference on Robotics and Automation (ICRA 2024), 2024
talks
Talk 1 on Relevant Topic in Your Field
This is a description of your talk, which is a markdown files that can be all markdown-ified like any other post. Yay markdown!
Conference Proceeding talk 3 on Relevant Topic in Your Field
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
teaching
Teaching experience 1
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Teaching experience 2
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.