Search

Unsupervised person re-identification (re-id) is an effective analysis for video surveillance in practice, which can train a pedestrian matching model without any annotations, and it is easy to deploy in unseen camera scenarios. The most challenging problem in unsupervised re-id task is the huge distribution-gap among different camera views, and the intrinsic correlations in unlabeled identities are also complicated to sufficiently explored. This paper proposes a Multi-order Cross-view Graph adversarial Network (MCGN) to bridge the cross-view distribution-gap, and mine the inherent discriminative information by multi-order triplet correlations. Specifically, MCGN firstly exploits graph representations by a cross-view graph convolutional network according to intra-view and inter-view graph structure, and then encodes each pedestrian image into a view-shared feature space, which is iteratively trained by a graph generative adversarial learning strategy to deeply bridge the distribution-gap. Finally, this paper proposes a multi-order discriminative learning module for composing reasonable triplet samples according to multi-order similarity correlations among unlabeled pedestrian images. Furthermore, sufficient experiments are conducted in two large scale person re-id datasets (Market-1501 and DukeMTMC-reID). The comparison to state-of-the-art methods and ablation study demonstrate the superiority of MCGN and the contribution of each module proposed in this paper.

Carbon nanotube (CNT) film has great potential in the application as a cold cathode in vacuum power electron devices. Pulse field emission of CNT film is investigated to achieve large current and current density. A maximum current of 16 mA is obtained from a 0.02-cm2 CNT film with a current density of 800 mA/cm2. The pulsewidth and area of CNT film have strong effects on field emission characteristics of CNT film, such as total current, current density, and current stability. The reason for this is discussed in detail. The results are useful for the design of the large current and current density CNT cold cathodes.