Search
Now showing items 1-10 of 43
Intra-Camera Supervised Person Re-Identification
(Springer, 2021-05)
Existing person re-identification (re-id) methods mostly exploit a large set of cross-camera identity labelled training data. This requires a tedious data collection and annotation process, leading to poor scalability in ...
Multi-perspective cross-class domain adaptation for open logo detection
(Elsevier, 2021-03-01)
Existing logo detection methods mostly rely on supervised learning with a large quantity of labelled training data in limited classes. This restricts their scalability to a large number of logo classes subject to limited ...
Characteristic Regularisation for Super-Resolving Face Images
(IEEE, 2020-05)
Existing facial image super-resolution (SR) methods focus mostly on improving "artificially down-sampled" lowresolution (LR) imagery. Such SR models, although strong at handling artificial LR images, often suffer from ...
Unsupervised Deep Learning via Affinity Diffusion
(Association for the Advancement of Artificial Intelligence, 2020)
Convolutional neural networks (CNNs) have achieved unprecedented success in a variety of computer vision tasks. However, they usually rely on supervised model learning with the need for massive labelled training data, ...
Decentralised Learning from Independent Multi-Domain Labels for Person Re-Identification
(Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved., 2021)
Tracklet Self-Supervised Learning for Unsupervised Person Re-Identification
(Association for the Advancement of Artificial Intelligence, 2020)
Existing unsupervised person re-identification (re-id) methods mainly focus on cross-domain adaptation or one-shot learning. Although they are more scalable than the supervised learning counterparts, relying on a relevant ...
Learning hybrid ranking representation for person re-identification
(Elsevier, 2021-08-01)
Contemporary person re-identification (re-id) methods mostly compute independentlya feature representation of each person image in the query set and the gallery set. This strategy fails to consider any ranking context ...
Semi-Supervised Learning under Class Distribution Mismatch
(Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved., 2020)
Semi-supervised learning (SSL) aims to avoid the need for collecting prohibitively expensive labelled training data. Whilst
demonstrating impressive performance boost, existing SSL
methods artificially assume that small ...