|
|
Computer Vision and Machine Learning for Multimodal Big Data - Ref: EE/DRFCOM7P/68648
Project Description
In this big data era, massive datasets with multiple modalities such as image, video, audio and text are ubiquitous. How to analyse, mine and understand such large-scale, multimodal and noisy data is a challenging and interesting research topic. Recently, deep learning, especially deep convolutional neural networks, has shown outstanding performance on visual classification tasks such as object detection, scene classification and even action recognition. However, applying deep learning to general multimodal or cross-modal big data analytics and
interpretation is still in its infantry and many open questions remain unanswered. This research project aims to investigate recent advances in state-of-the-art computer vision and machine learning theories, and study deep learning architectures to create a breakthrough in the field of multimodal big data processing and analysis, including cross-modal search and retrieval, cross-modal hashing, multimodal recognition and fusion. Application areas can cover but are not limited to Human-Computer Interaction, Video Surveillance, Robotics and Social Media. Considering that current deep learning relies on huge amounts of fully-labelled data, which is not practical for general data analytics, semi-supervised or weakly-supervised learning strategies requiring only partial supervision or weak labelling will also be proposed.
Funding Notes:
This is a fully funded studentship with international tuition fees paid and an annual stipend around £15,000 for 3 years
Entry Requirements:
The ideal candidate should have completed a Master degree (or equivalent) in computer science, electrical engineering, physics, applied mathematics or other relevant fields. Outstanding students, who hold a bachelor’s degree, are also acceptable. We expect experience in computer vision, video analysis, and machine learning as well as good mathematical and programming skills (either C/C++ or MATLAB). The candidate is
expected to work in an international research group with 10 + Ph.D. students and Post-doc researchers under the supervision of Prof. Ling Shao and Dr. Jungong Han.
For applicants whose first language is not English, you will need to meet our minimum overall and component scores for research programmes. For applications to all Faculties this is the equivalent of an IELTS overall score of 6.5 with no component below 6.0.
Informal Enquiries:
Enquiries regarding this studentship should be made to pgr.admissions@northumbria.ac.uk
Further information about the content can be obtained from: Dr. Jungong Han (jungong.han@northumbria.ac.uk) and Prof. Ling Shao (ling.shao@northumbria.ac.uk)

How to Apply
For further details of how to apply, entry requirements and the application form, see https://www.northumbria.ac.uk/re ... grees/how-to-apply/
Please ensure you quote the advert reference above on your application form.
Deadline for applications: 30 November 2015 Interview date/s (if known): to be confirmed Start Date: 1 February 2016
References
L. Shao, L. Liu and M. Yu, “Kernelized Multiview Projection for Robust Action
Recognition”, International Journal of Computer Vision (IJCV), doi: 10.1007/s11263-015- 0861-6, 2015.
M. Yu, L. Liu and L. Shao, “Structure-Preserving Binary Representations for RGB-D Action Recognition”, IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), doi: 10.1109/TPAMI.2015.2491925, 2015.
F. Zhu and L. Shao, “Weakly-Supervised Cross-Domain Dictionary Learning for Visual Recognition”, International Journal of Computer Vision (IJCV), vol. 109, no. 1-2, pp. 42-59, Aug. 2014.
L. Shao, D. Wu and X. Li, “Learning Deep and Wide: A Spectral Method for Learning Deep Networks”, IEEE Transactions on Neural Networks and Learning Systems, vol. 25, no. 12, pp. 2303-2308, Dec. 2014.
L. Shao, L. Liu and X. Li, “Feature Learning for Image Classification via Multiobjective Genetic Programming”, IEEE Transactions on Neural Networks and Learning Systems, vol. 25, no. 7, pp. 1359-1371, Jul. 2014.
L. Liu, M. Yu and L. Shao, “Multiview Alignment Hashing for Efficient Image Search”, IEEE Transactions on Image Processing, vol. 24, no. 3, pp. 956-966, Mar. 2015.
J. Han, L. Shao, D. Xu and J. Shotton, “Enhanced Computer Vision with Microsoft Kinect Sensor: A Review”, IEEE Transactions on Cybernetics, vol. 43, no. 5, pp. 1317-1333, Oct. 2013.
L. Liu, M. Yu and L. Shao, “Projection Bank: From High-dimensional Data to Medium- length Binary Codes”, IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, Dec. 2015.
S. Jones and L. Shao, “Unsupervised Spectral Dual Assignment Clustering of Human Actions
in Context”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, USA, 2014.
D. Wu and L. Shao, “Leveraging Hierarchical Parametric Networks for Skeletal Joints Based Action Segmentation and Recognition”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, USA, 2014.
S. Jones and L. Shao, “A Multigraph Representation for Improved Unsupervised/Semi- supervised Learning of Human Actions”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, USA, 2014.
F. Zhu, Z. Jiang and L. Shao, “Submodular Object Recognition”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, USA, 2014.
F. Zhu, L. Shao and M. Yu, “Cross-Modality Submodular Dictionary Learning for Information Retrieval”, ACM International Conference on Information and Knowledge Management (CIKM), Shanghai, China, 2014.
L. Liu and L. Shao, “Learning Discriminative Representations from RGB-D Video Data”, International Joint Conference on Artificial Intelligence (IJCAI), Beijing, China, 2013.
|
|
发表于 2015-11-12 08:28:51