-
11/2023 [Open] We are recruiting two postdocs at Tongji University, details can be found here
-
08/2022 [Closed] Journal of Imaging - Call for Papers: Special Issue on Visual Learning with Multi-Task Supervision.
-
01/2022 [Closed] Autonomous Intelligent Systems - Call for Papers: Special Issue on Developing Reliable Machine Learning Methods for Autonomous Systems.
-
12/2021 [Closed] One UK PhD position on visual recognition with minimal supervision. [more]
-
11/2021 [Closed] We have two PhD projects opened at EPSRC CDT Smart Medical Imaging for 2022 intake: (1) Exploiting multi-task learning for endoscopic vision in robotic surgery. (2) AI-Enabled Assessment of Cardiac Function from Echocardiography. International applicants are welcomed!
-
08/2021 [Closed] One post-doc position in computer vision and remote sensing imagery. [more]
-
07/2021 [Closed] One UK PhD position on exploiting multi-task learning for endoscopic vision in robotic surgery. [more]
- 05/2021 [Closed] One UK PhD position as a joint of BMEIS and NMS at King’s. [more]
-
05/2021 [Closed] One UK PhD postion open at EPSRC CDT Smart Medical Imaging. [more]
-
11/2020 [Closed] One funded PhD positions on medical imaging processing. [more]
- 10/2020 [Closed] One funded research assistant! [more]
Opportunity
Title
Research Associate in Computer Vision/Remote Sensing Imagery
Content
The objective of this post-doc is to study deep learning methods for visual recognition of urban and rural scenes in remote sensing imagery. Key infrastructure types such as dams, reservoirs, roads, rails, trees etc will be identified and segmented in visual images; densities/distributions of these infrastructures over different areas will be analyzed. The challenge lies in the recognition of both objects and stuffs in images, where the latter (e.g. reservoirs, trees) often do not have specific spatial extent or shape and is largely unexplored; furthermore, because of the utility of remote sensing imagery, the target infrastructures also differ in appearance and resolutions from their traditional observations.
This post is part of the European H-2020 project ReSET. The PDRA will be supervised by Dr. Miaojing Shi in the Department of Informatics; and will also work closely with Prof. Mark Mulligan from the Department of Geography within the framework of ReSET.
The post holder should have a PhD in a relevant field (Image Processing, Computer vision, Machine learning) and a good publication track records on high-quality conferences/journals; preferably have worked on projects such as image classification, semantic segmentation, and crowd counting; and have prior experiences working on remote sensing, time serials, and geographic data.
This post will be offered on an a fixed-term contract for 12 months
Opportunity
Title
Exploiting multi-task learning for endoscopic vision in robotic surgery
Content
Multi-task learning is common in deep learning, where clear evidence shows that jointly learning correlated tasks can improve on individual performances. Notwithstanding, in reality, many tasks are processed independently. The reasons are manifold: 1) many tasks are not strongly correlated, benefits might be obtained for only one or none of the tasks in joint learning; 2) the scalability of learning multiple tasks is limited with the number of tasks in terms of both network optimization and practical implementation. Having a scalable and robust multi-task learning strategy however is very meaningful and of substantial potential in many real applications, i.e. endoscopic image processing. This project studies multi-task learning in endoscopic vision for robotic surgery with a particular focus on depth and optical flow estimation, surgical instrument detection and anatomy recognition, as well as surgical action recognition. The aim is to design effective multi-task learning strategies to improve the performance on all tasks.
Candidates are requested to send an initial expression of interest to Dr.Shi (miaojing.shi@kcl.ac.uk ).
Opportunity
Title
Visual recognition with limited supervision in deep learning context
Content
The goal of this PhD is to study object detection/segmentation in images or video with limited supervision. This task will be placed into a setting where only image-level annotation is provided. To begin, additional supervision such as clicks, strokes, or bounding boxes may also be assumed. Towards the end of the PhD, the student is expected to work with datasets of mixed levels of supervision, including a harder, semi-supervised setting where there are only a few image-level labels as well as a large amount of unlabeled images. Few-shot learning is another challenging direction to explore.
Several ideas can be investigated in the context of deep learning. For instance, generative adversarial learning can be employed to either augment the dataset or bridge the predicted detections with their ground truth. Recurrent neural networks can be applied to video segmentation in particular to localize and segment semantic parts across nearby frames. On unstructured image datasets, ideas like random-walk label propagation can be extended across pairs or groups of images. Deep metric learning and cross-category transfer learning can be studied in a few-shot scenario.
The candidate should ideally have a master degree in Computer Science, Applied Mathematics or Electrical Engineering; solid mathematical background and programming skills; fluency in English language; preferably, prior experience in computer vision, machine learning and deep learning.
This is a UK studentship for three years. The target starting date is Oct. 2022. The PhD will be supervised by Dr Miaojing Shi and Dr Michael Spratling. Work will be carried out within the Department of Informatics, King’s College London. More details can be found here: https://www.kcl.ac.uk/informatics/postgraduate/research-degrees.
Application Instructions: Candidates are requested to send an initial expression of interest to me (miaojing.shi@kcl.ac.uk ) preferably with updated CV and motivation letter.
Opportunity
Title
One UK PhD position open as a joint of BMEIS and NMS at King's
Content
Details here: https://www.kcl.ac.uk/study/funding/fairness-in-ai-for-cardiac-imaging
Opportunity
Title
AI-Enabled Assessment of Cardiac Function from Echocardiography
Content
Details here: https://www.imagingcdt.com/project/ai-enabled-assessment-of-cardiac-function-from-echocardiography
Opportunity
Title
Semi-supervised detection and tracking of instruments for robotic surgery guidance
Content
Details here: https://www.imagingcdt.com/project/semi-supervised-detection-and-tracking-of-instruments-for-robotic-surgery-guidance/
Opportunity
Title
Remote sensing and machine learning to detect global dams and associated reservoirs
Content
This project is supported by King’s Together: Multi & Interdisciplinary Research Scheme which brings expertise from both Informatics and Geography to work on developing new machine learning approaches linked with (new) remote sensing data sources. Our focus will be to develop algorithms to separate dammed reservoirs from the millions of other water bodies on Earth. Pilot studies that we have carried out in the Volta and Limpopo basins indicate that dammed reservoirs tend to have a triangular or elongate triangular shape, whereas natural reservoirs tend to be round. The goal of this RA is thus to employ machine learning techniques, e.g. deep neural networks, to detect and recognize dammed reservoirs in remote sensing imagery. By identifying water bodies spectrally in earth observation imagery and then analysing their shape we hope to extend our database of large and medium sized dams to the many millions of small dams important for smallholder irrigation.
The selected RA will be mainly responsible to develop computer vision algorithms for the detection of dammed reservoirs in satellite images. Work will be carried out within the Department of Informatics, King’s College London. The RA will be working with Dr. Miaojing Shi (miaojing.shi@kcl.ac.uk Informatics), Dr. Arnout Van Soesbergen and Dr. Mark Mulligan (Geography).
The candidate should ideally have a master degree in Computer Science, or Electrical Engineering; solid mathematical background and programming skills; preferably, prior experience in computer vision, machine learning and deep learning.