TensorFlow: A system for large-scale machine learning
- Martín Abadi, P. Barham, Xiaoqiang Zhang
- Computer ScienceUSENIX Symposium on Operating Systems Design and…
- 27 May 2016
The TensorFlow dataflow model is described and the compelling performance that Tensor Flow achieves for several real-world applications is demonstrated.
Hyperspectral Image Dataset for Benchmarking on Salient Object Detection
- N. Imamoglu, Y. Oishi, R. Nakamura
- Environmental Science, Computer ScienceInternational Workshop on Quality of Multimedia…
- 1 May 2018
A hyperspectral salient object detection dataset with a collection of 60 hyperspectrals with their respective ground-truth binary images and representative rendered colour images (sRGB) is released.
A novel superpixel-based saliency detection model for 360-degree images
- Yuming Fang, Xiaoqiang Zhang, N. Imamoglu
- Environmental ScienceSignal processing. Image communication
- 1 November 2018
Video saliency detection by gestalt theory
- Yuming Fang, Xiaoqiang Zhang, Feiniu Yuan, N. Imamoglu, Haiwen Liu
- Environmental SciencePattern Recognition
- 1 December 2019
PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Network
- Pengfei Wang, Chengquan Zhang, Guangming Shi
- Computer ScienceAAAI Conference on Artificial Intelligence
- 12 April 2021
The PGNet is a single-shot text spotter, where the pixel-level character classification map is learned with proposed PG-CTC loss avoiding the usage of character-level annotations, and a graph refinement module (GRM) is proposed to optimize the coarse recognition and improve the end-to-end performance.
Multi-window back-projection residual networks for reconstructing COVID-19 CT super-resolution images
- Defu Qiu, Yuhu Cheng, Xuesong Wang, Xiaoqiang Zhang
- Computer ScienceComputer Methods and Programs in Biomedicine
- 8 January 2021
ROI-wise Reverse Reweighting Network for Road Marking Detection
- Xiaoqiang Zhang, Yuan Yuan, Qi Wang
- Computer ScienceBritish Machine Vision Conference
- 2018
A novel ROI-wise Reverse Reweighting Network (R3Net) is proposed to adaptively combine multi-layer features for different markings to model different ROI’s unique properties.