Search

Contour based scene text detection methods have rapidly developed recently, but still suffer from inaccurate front-end contour initialization, multi-stage error accumulation, or deficient local information aggregation. To tackle these limitations, we propose a novel arbitrary-shaped scene text detection framework named CT-Net by progressive contour regression with contour transformers. Specifically, we first employ a contour initialization module that generates coarse text contours without any post-processing. Then, we adopt contour refinement modules to adaptively refine text contours in an iterative manner, which are beneficial for context information capturing and progressive global contour deformation. Besides, we propose an adaptive training strategy to enable the contour transformers to learn more potential deformation paths, and introduce a re-score mechanism that can effectively suppress false positives. Extensive experiments are conducted on four challenging datasets, which demonstrate the accuracy and efficiency of our CT-Net over state-of-the-art methods. Particularly, CT-Net achieves F-measure of 86.1 at 11.2 frames per second (FPS) and F-measure of 87.8 at 10.1 FPS for CTW1500 and Total-Text datasets, respectively.

Triphenylamine (TPA) has often been used as a building block to construct functional organic materials yet is rarely employed in oxygen reduction reaction (ORR) due to its strong electron-donating ability. This versatile segment bears a three-dimensional spatial structure whose effect has not been fully explored in catalytic systems. To this end, five symmetric cobalt porphyrins with carbazole and TPA derivatives have been synthesized and their ORR performance has been evaluated in acid medium. It was found that all compounds produced mainly hydrogen peroxide in oxygen reduction, with CP1attaching benzyl derivatives and XCP4possessing TPA-carbazole substituents at the meso-position of porphyrin, showing similar but more positive ORR potential as compared to the other analogues. Importantly, XCP4achieved the greatest response current and the largest electron transfer numbers and H2O2yields among the investigated molecules. Detailed electrochemical measurements suggested that the dipole-induced partial charges on the porphyrin in tandem with the more exposed molecular orbitals on TPA contributed to this enhancement, with the former attracting more protons to the affinity of reactive sites and the latter increasing the collision frequency between the electrocatalyst and H+in solution. This is the first attempt to integrate the intermolecular forces with more exposed molecular orbitals in altering the electrochemical process.

Abnormality detection is a challenging task due to the dependence on a specific context and the unconstrained variability of practical scenarios. In recent years, it has benefited from the powerful features learnt by deep neural networks, and handcrafted features specialized for abnormality detectors. However, these approaches with large complexity still have limitations in handling long-term sequential data (e.g., videos), and their learnt features do not thoroughly capture useful information. Recurrent Neural Networks (RNNs) have been shown to be capable of robustly dealing with temporal data in long-term sequences. In this paper, we propose a novel version of Gated Recurrent Unit (GRU), called Single-Tunnelled GRU for abnormality detection. Particularly, the Single-Tunnelled GRU discards the heavy-weighted reset gate from GRU cells that overlooks the importance of past content by only favouring current input to obtain an optimized single-gated-cell model. Moreover, we substitute the hyperbolic tangent activation in standard GRUs with sigmoid activation, as the former suffers from performance loss in deeper networks. Empirical results show that our proposed optimized-GRU model outperforms standard GRU and Long Short-Term Memory (LSTM) networks on most metrics for detection and generalization tasks on CUHK Avenue and UCSD datasets. The model is also computationally efficient with reduced training and testing time over standard RNNs. [ABSTRACT FROM AUTHOR]

Face alignment has made great progress in recent years and the cascade regression framework is one of the main contributors. However, the performance of this framework is unsatisfactory on heavily occluded faces or those far from the frontal pose. This is because regression is sensitive to hidden landmarks and unified initialisation can often lead to the method falling into local minima. The authors propose a new pipeline of salient-to-inner-to-all to progressively compute the locations of landmarks. Additionally, a feedback process is utilised to improve the robustness of regression. They bring out a pose-invariant shape retrieval method to generate the discriminative initialisation. Experiments are performed on two benchmarks, and the experimental results demonstrate that the proposed method has a considerable improvement on the cascade regression model, and achieves favourable results compared with the state-of-the-art deep learning-based methods.