Results 1 -
4 of
4
Unsupervised Learning of Generative Topic Saliency For Person Re-identification
, 2014
"... Existing approaches to person re-identification (re-id) are dominated by supervised learning based methods which focus on learning optimal similarity distance metrics. However, supervised learning based models require a large number of manually labelled pairs of person images across every pair of ca ..."
Abstract
-
Cited by 3 (1 self)
- Add to MetaCart
Existing approaches to person re-identification (re-id) are dominated by supervised learning based methods which focus on learning optimal similarity distance metrics. However, supervised learning based models require a large number of manually labelled pairs of person images across every pair of camera views. This thus limits their ability to scale to large camera networks. To overcome this problem, this paper proposes a novel unsupervised re-id modelling approach by exploring generative probabilistic topic mod-elling. Given abundant unlabelled data, our topic model learns to simultaneously both (1) discover localised person foreground appearance saliency (salient image patches) that are more informative for re-id matching, and (2) remove busy background clutters surround-ing a person. Extensive experiments are carried out to demonstrate that the proposed model outperforms existing unsupervised learning re-id methods with significantly sim-plified model complexity. In the meantime, it still retains comparable re-id accuracy when compared to the state-of-the-art supervised re-id methods but without any need for pair-wise labelled training data.
Investigating Open-World Person Re-identification Using a Drone
"... Abstract. Person re-identification is now one of the most topical and intensively studied problems in computer vision due to its challenging na-ture and its critical role in underpinning many multi-camera surveillance tasks. A fundamental assumption in almost all existing re-identification research ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
(Show Context)
Abstract. Person re-identification is now one of the most topical and intensively studied problems in computer vision due to its challenging na-ture and its critical role in underpinning many multi-camera surveillance tasks. A fundamental assumption in almost all existing re-identification research is that cameras are in fixed emplacements, allowing the explicit modelling of camera and inter-camera properties in order to improve re-identification. In this paper, we present an introductory study push-ing re-identification in a different direction: re-identification on a mobile platform, such as a drone. We formalise some variants of the standard formulation for re-identification that are more relevant for mobile re-identification. We introduce the first dataset for mobile re-identification, and we use this to elucidate the unique challenges of mobile re-identification. Finally, we re-evaluate some conventional wisdom about re-id models in the light of these challenges and suggest future avenues for research in this area. 1
LAYNE, HOSPEDALES, GONG: RE-ID: HUNTING ATTRIBUTES IN THE WILD 1 Re-id: Hunting Attributes in the Wild
"... Person re-identification is a crucial capability underpinning many applications of public-space video surveillance. Recent studies have shown the value of learning seman-tic attributes as a discriminative representation for re-identification. However, existing attribute representations do not genera ..."
Abstract
- Add to MetaCart
Person re-identification is a crucial capability underpinning many applications of public-space video surveillance. Recent studies have shown the value of learning seman-tic attributes as a discriminative representation for re-identification. However, existing attribute representations do not generalise across camera deployments. Thus, this strat-egy currently requires the prohibitive effort of annotating a vector of person attributes for each individual in a large training set – for each given deployment/dataset. In this paper we take a different approach and automatically discover a semantic attribute on-tology, and learn an effective associated representation by crawling large volumes of internet data. In addition to eliminating the necessity for per-dataset annotation, by train-ing on a much larger and more diverse array of examples this representation is more view-invariant and generalisable than attributes trained at conventional small scales. We show that these automatically discovered attributes provide a valuable representation that significantly improves re-identification performance on a variety of challenging datasets. 1
