Now showing items 21-30 of 63
Unsupervised Person Re-identification by Deep Learning Tracklet Association
© 2018, Springer Nature Switzerland AG. Most existing person re-identification (re-id) methods rely on supervised model learning on per-camera-pair manually labelled pairwise training data. This leads to poor scalability ...
Unsupervised learning of generative topic saliency for person re-identification
© 2014. The copyright of this document resides with its authors. Existing approaches to person re-identification (re-id) are dominated by supervised learning based methods which focus on learning optimal similarity distance ...
Fine-grained sketch-based image retrieval by matching deformable part models
© 2014. The copyright of this document resides with its authors. An important characteristic of sketches, compared with text, rests with their ability to intrinsically capture object appearance and structure. Nonetheless, ...
Re-id: Hunting Attributes in the Wild.
(BMVA Press, 2014)