Projects
Guanxiong Sun, Yang Hua, Guosheng Hu, Neil Robertson
In ECCV, 2022
A transformer backbone designed for dense video tasks, e.g., video object detection, video instance segmentation.
In ECCV, 2022
A transformer backbone designed for dense video tasks, e.g., video object detection, video instance segmentation.
Guanxiong Sun, Yang Hua, Guosheng Hu, Neil Robertson
In ECCV, 2022
We present a simple yet effecitve framework to address the computational bottlenecks when adapting SOTA video object detection methods to modern one-stage detectors.
In ECCV, 2022
We present a simple yet effecitve framework to address the computational bottlenecks when adapting SOTA video object detection methods to modern one-stage detectors.
Guanxiong Sun, Yang Hua, Guosheng Hu, Neil Robertson
In AAAI, 2021
We propose a novel memory bank to effectively model long-range temporal correlations between frames for video object detection. At the same time, our method can run in a very fast speed.
In AAAI, 2021
We propose a novel memory bank to effectively model long-range temporal correlations between frames for video object detection. At the same time, our method can run in a very fast speed.
Gonging Luo, Guanxiong Sun, Kuanquan Wang, Suyu Dong, Henggui Zhang
In CinC, 2016
This study develops a new left ventricle (LV) volumes prediction method without time-consuming segmentation using deep learning technology.
In CinC, 2016
This study develops a new left ventricle (LV) volumes prediction method without time-consuming segmentation using deep learning technology.
Suyu Dong, Gonging Luo, Guanxiong Sun, Kuanquan Wang, Henggui Zhang
In CinC, 2016
We present an end-to-end framework to estimate the left ventricular (LV) volume from 3D echocardiography data. Specifically, we introduce a novel unsupervised learning method to train a CNN for feature extraction. Then, the random forests method is used to predicts the LV volume.
In CinC, 2016
We present an end-to-end framework to estimate the left ventricular (LV) volume from 3D echocardiography data. Specifically, we introduce a novel unsupervised learning method to train a CNN for feature extraction. Then, the random forests method is used to predicts the LV volume.
