Search

Existing studies for gait recognition are dominated by in-the-lab scenarios. Since people live in real-world senses, gait recognition in the wild is a more practical problem that has recently attracted the attention of the community of multimedia and computer vision. Current methods that obtain state-of-the-art performance on in-the-lab benchmarks achieve much worse accuracy on the recently proposed in-the-wild datasets because these methods can hardly model the varied temporal dynamics of gait sequences in unconstrained scenes. Therefore, this paper presents a novel multi-hop temporal switch method to achieve effective temporal modeling of gait patterns in real-world scenes. Concretely, we design a novel gait recognition network, named Multi-hop Temporal Switch Network (MTSGait), to learn spatial features and multi-scale temporal features simultaneously. Different from existing methods that use 3D convolutions for temporal modeling, our MTSGait models the temporal dynamics of gait sequences by 2D convolutions. By this means, it achieves high efficiency with fewer model parameters and reduces the difficulty in optimization compared with 3D convolution-based models. Based on the specific design of the 2D convolution kernels, our method can eliminate the misalignment of features among adjacent frames. In addition, a new sampling strategy, i.e., non-cyclic continuous sampling, is proposed to make the model learn more robust temporal features. Finally, the proposed method achieves superior performance on two public gait in-the-wild datasets, i.e., GREW and Gait3D, compared with state-of-the-art methods., 10 pages, 6 figures; Accepted by ACM MM 2022

Background Accumulating evidence has revealed that aberrant microRNA (miRNA) expression can affect the development of chemotherapy drug resistance by modulating the expression of relevant target proteins. Emerging evidence has demonstrated that miR-133a participates in the tumorigenesis of various cancers. However, whether miR-133a is associated with cisplatin resistance in ovarian cancer remains unclear. Objective To investigate the role of miR-133a in the development of cisplatin resistance in ovarian cancer. Methods MiR-133a expression in cisplatin-resistant ovarian cancer cell lines was assessed by reverse-transcription quantitative PCR (RT–qPCR). A cell counting kit-8 (CCK-8) assay was used to evaluate the viability of tumour cells treated with cisplatin in the presence or absence of miR-133a. A luciferase reporter assay was used to analyse the binding of miR-133a with the 3′ untranslated region (3′UTR) of YES proto-oncogene 1 (YES1). The YES1 expression level was analysed using a dataset from the International Cancer Genome Consortium (ICGC) and assessed by RT–qPCR and western blotting in vitro. The roles and mechanisms of YES1 in cell functions were further probed via gain- and loss-of-function analysis. Results The expression of miR-133a was significantly decreased in cisplatin-resistant ovarian cancer cell lines (A2780-DDP and SKOV3-DDP), and the overexpression of the miR-133a mimic reduced cisplatin resistance in A2780-DDP and SKOV3-DDP cells. Treatment with the miR-133a inhibitor increased cisplatin sensitivity in normal A2780 and SKOV3 cells. MiR-133a binds the 3’UTR of YES1 and downregulates its expression. Bioinformatics analysis revealed that YES1 expression was upregulated in recurrent cisplatin-resistant ovarian cancer tissue, and in vitro experiments also verified its upregulation in cisplatin-resistant cell lines. Furthermore, we discovered that miR-133a downregulated the expression of YES1 and thus inhibited cell autophagy to reduce cisplatin resistance. Yes1 knockdown significantly suppressed the cisplatin resistance of ovarian cancer cells by inhibiting autophagy in vitro. Xenograft tumour implantation further demonstrated that Yes1 overexpression promoted ovarian tumour development and cisplatin resistance. Conclusions Our results suggest that the miR-133a/YES1 axis plays a critical role in cisplatin resistance in human ovarian cancer by regulating cell autophagy, which might serve as a promising therapeutic target for ovarian cancer chemotherapy treatment in the future.

In the age of information explosion, image classification is the key technology of dealing with and organizing a large number of image data. Currently, the classical image classification algorithms are mostly based on RGB images or grayscale images, and fail to make good use of the depth information about objects or scenes. The depth information in the images has a strong complementary effect, which can enhance the classification accuracy significantly. In this paper, we propose an image classification technology using principal component analysis based on multi-view depth characters. In detail, firstly, the depth image of the original image is estimated; secondly, depth characters are extracted from the RGB views and the depth view separately, and then the reducing dimension operation through the PCA is implemented. Eventually, the SVM is applied to image classification. The experimental results show that the method has good performance.