Search

As an important research direction in image and video processing, set-based video recognition requires speed and accuracy. However, the existing static modeling methods focus on computational speed but ignore accuracy, whereas the dynamic modeling methods are higher-accuracy but ignore the computational speed. Combining these two types of methods to obtain fast and accurate recognition results remains a challenging problem. Motivated by this, in this study, a novel Manifolds-based Low-Rank Dictionary Pair Learning (MbLRDPL) method was developed for a set-based video recognition/image set classification task. Specifically, each video or image set was first modeled as a covariance matrix or linear subspace, which can be seen as a point on a Riemannian manifold. Second, the proposed MbLRDPL learned discriminative class-specific synthesis and analysis dictionaries by clearly imposing the nuclear norm on the synthesis dictionaries. The experimental results show that our method achieved the best classification accuracy (100%, 72.16%, 95%) on three datasets with the fastest computing time, reducing the errors of state-of-the-art methods (JMLC, DML, CEBSR) by 0.96–75.69%.

CAPTCHA, or Completely Automated Public Turing Tests to Tell Computers and Humans Apart, is a common mechanism used to protect commercial accounts from malicious computer bots, and the most widely used scheme is text-based CAPTCHA. In recent years, newly emerged deep learning techniques have achieved high accuracy and speed in attacking text-based CAPTCHAs. However, most of the existing attacks have various disadvantages, the attack process made high complexity or manually collecting and labeling a large number of samples to train a deep learning recognition model is time-consuming and expensive. In this paper, we propose a transfer learning-based approach that greatly reduces the attack complexity and the cost of labeling samples, specifically, by pre-training the model with randomly generated samples and fine-tuning the pre-trained model with a small number of real-world samples. To evaluate our attack, we tested 25 online CAPTCHAs achieving success rates ranging from 36.3% to 96.9%. To further explore the effect of the training sample characteristics on the attack accuracy, we elaborately imitate some samples and apply a generative adversarial network to refine the samples, sequentially we use these two kinds of generated samples to pre-train the models, respectively. The experimental results demonstrate that the similarity between randomly generated samples and elaborately imitated samples has a negligible impact on the attack accuracy. Instead, transfer learning is the key factor; it reduces the cost of data preparation while preserving the model's attack accuracy.

To date, lanthanide-doped upconversion nanoparticles (UCNPs) have been widely reported as a promising CT contrast agent because they have high atomic numbers and big X-ray attenuation coefficient values. However, it is still a challenge to fabricate a simple multimodal imaging probe with improved image quality for early cancer diagnosis in clinical medicine. Herein, ultra-small, uniform and monodisperse β-NaGdF4:Yb,Er,X% Lu (X = 0, 1, 2.5, 4, 6, 7.5) UCNPs were prepared through a solvothermal method with high-level modulation of both the phase and morphology. Meanwhile, a remarkably enhanced red upconversion luminescence (UCL) in the β-NaGdF4:Yb,Er,X% Lu NPs was successfully realized via Lu3+ doping. It is found that as the content of Lu3+ increases from 0 to 7.5 mol%, the UCL intensity of the red emission first increases and then decreases, with the optimum doping content of Lu3+ ions of 2.5 mol%. The red UCL enhancement is ascribed to the change of the Yb–Er interionic distance controlling the Yb–Er energy transfer rate and the distortion of the local environment of Er3+ ions influencing the 4f–4f transition rates of Er3+ ions, which has been further confirmed by the experimental check of the crystallographic phase and by photoluminescence spectroscopy employing Eu3+ as the structural probe, respectively. More importantly, after being modified with the HS-PEG2000-NH2 ligand, the NH2-PEGylated-NaGdF4:Yb,Er,X% Lu NPs exhibited low cytotoxicity, high biocompatibility, and remarkably enhanced contrast performance in in vitro UCL and in vivo CT imaging. On the basis of our findings, the as-obtained functionalized UCNPs could be considered as a promising versatile dual-mode imaging probe for bioimaging, tumor diagnosis, and cancer therapy.