Zero-shot Image Classification
(2017)
Thesis
Long, Y. (2017). Zero-shot Image Classification. (Thesis). University of Sheffield. Retrieved from https://durham-repository.worktribe.com/output/1642055
Dr Yang Long's Outputs (6)
From Zero-shot Learning to Conventional Supervised Classification: Unseen Visual Data Synthesis (2017)
Presentation / Conference Contribution
Long, Y., Liu, L., Shao, L., Shen, F., Ding, G., & Han, J. (2017, December). From Zero-shot Learning to Conventional Supervised Classification: Unseen Visual Data Synthesis. Presented at Computer Vision and Pattern Recognition IEEE
Learning to recognise unseen classes by a few similes (2017)
Presentation / Conference Contribution
Long, Y., & Shao, L. (2017, December). Learning to recognise unseen classes by a few similes. Presented at Proceedings of the 25th ACM international conference on Multimedia ACM
Towards fine-grained open zero-shot learning: Inferring unseen visual features from attributes (2017)
Presentation / Conference Contribution
Long, Y., Liu, L., & Shao, L. (2017, December). Towards fine-grained open zero-shot learning: Inferring unseen visual features from attributes. Presented at 2017 IEEE Winter Conference on Applications of Computer Vision (WACV) IEEE
Describing unseen classes by exemplars: Zero-shot learning using grouped simile ensemble (2017)
Presentation / Conference Contribution
Long, Y., & Shao, L. (2017, December). Describing unseen classes by exemplars: Zero-shot learning using grouped simile ensemble. Presented at 2017 IEEE winter conference on applications of computer vision (WACV) IEEE
Zero-Shot Learning Using Synthesised Unseen Visual Data with Diffusion Regularisation (2017)
Journal Article
Long, Y., Liu, L., Shen, F., Shao, L., & Li, X. (2018). Zero-Shot Learning Using Synthesised Unseen Visual Data with Diffusion Regularisation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(10), 2498-2512. https://doi.org/10.1109/tpami.2017.2762295Sufficient training examples are the fundamental requirement for most of the learning tasks. However, collecting well-labelled training examples is costly. Inspired by Zero-shot Learning (ZSL) that can make use of visual attributes or natural languag... Read More about Zero-Shot Learning Using Synthesised Unseen Visual Data with Diffusion Regularisation.