Shuman Tian

ORCID: 0000-0003-3366-0227
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Image Enhancement Techniques
  • Advanced Neural Network Applications
  • Advanced Image Processing Techniques
  • Animal Vocal Communication and Behavior
  • Wildlife-Road Interactions and Conservation
  • Digital Media Forensic Detection
  • Advanced Vision and Imaging
  • Marine animal studies overview
  • Video Surveillance and Tracking Methods
  • Robotics and Sensor-Based Localization
  • UAV Applications and Optimization
  • Advanced Image Fusion Techniques
  • Explainable Artificial Intelligence (XAI)
  • Image and Signal Denoising Methods
  • Domain Adaptation and Few-Shot Learning
  • Remote Sensing and LiDAR Applications

National University of Defense Technology
2023

Sun Yat-sen University
2023

Chungbuk National University
2023

Beihang University
2017

This work reviews the results of NTIRE 2023 Challenge on Image Shadow Removal. The described set solutions were proposed for a novel dataset, which captures wide range object-light interactions. It consists 1200 roughly pixel aligned pairs real shadow free and affected images, captured in controlled environment. data was white-box setup, using professional equipment lights acquisition sensors. challenge had number 144 participants registered, out 19 teams compared final ranking. extend...

10.1109/cvprw59228.2023.00179 article EN 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) 2023-06-01

This report introduces two high-quality datasets Flickr360 and ODV360 for omnidirectional image video super-resolution, respectively, reports the NTIRE 2023 challenge on 360° super-resolution. Unlike ordinary 2D images/videos with a narrow field of view, can represent whole scene from all directions in one shot. There exists large gap between image/video both degradation restoration processes. The is held to facilitate development super-resolution by considering their special...

10.1109/cvprw59228.2023.00174 article EN 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) 2023-06-01

Flying bird detection has recently attracted increasing attention in computer vision, which becomes an urgent task with the opening up of low-altitude airspace. However, compared to conventional object tasks, it is much more challenging trap flying birds aerial videos due small target sizes, complex backgrounds great variations and disturbances bird-like objects. In this paper, we propose a unified framework termed glance-and-stare (GSD) videos. The GSD inspired by fact that human beings...

10.1109/tcsvt.2017.2764959 article EN IEEE Transactions on Circuits and Systems for Video Technology 2017-10-23

Existing methods for shadow removal in high-resolution images may not be effective due to challenges such as the time-consuming nature of training and loss visual data during image cropping or resizing, highlighting necessity development more efficient methods. In this paper, we propose a novel Pyramid Ensemble Structure (PES) High Resolution Image Shadow Removal. Our approach takes advantage multiple scales by constructing pyramid inputs that allow capturing wide range sizes shapes. We then...

10.1109/cvprw59228.2023.00138 article EN 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) 2023-06-01

With the opening up of low-altitude airspace, flying bird detection has recently attracted increasing attention in computer vision to avoid strike. However, compared with conventional object tasks, it is much more challenging detect birds aerial videos due existence small-sized targets, complexity backgrounds great variations and disturbances bird-like objects. Motivated by intuition birds' periodicity, we propose a new method solve problem novel framework, termed pattern clustering (FPC),...

10.1109/icnsurv.2017.8011931 article EN 2019 Integrated Communications, Navigation and Surveillance Conference (ICNS) 2017-04-01

Flying bird detection based on the safety of low-altitude airspace • Detect flying birds in aerial videos Birds' periodicity pattern clustering (FPC)

10.1109/icnsurv.2017.8012009 article EN 2019 Integrated Communications, Navigation and Surveillance Conference (ICNS) 2017-04-01

Ensemble of machine learning models yields improved performance as well robustness. However, their memory requirements and inference costs can be prohibitively high. Knowledge distillation is an approach that allows a single model to efficiently capture the approximate ensemble while showing poor scalability demand for re-training when introducing new teacher models. In this paper, we study if utilize meta-learning strategy directly predict parameters with comparable ensemble. Hereto,...

10.48550/arxiv.2210.01973 preprint EN other-oa arXiv (Cornell University) 2022-01-01

10.1109/cvprw59228.2023.00004 article EN 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) 2023-06-01
Coming Soon ...