Search

Image captioning is one of the hot research topics in the field of computer vision.It is a cross-media data analysis task that combines computer vision and natural language processing.It describes the image by understanding the content of the image and generating captions that are both semantically and grammatically correct.Existing image captioning methods mostly use the encoder-decoder model.This kind of methods mostly ignore the relative position relationship between visual objects when extracting the visual object features in image,and the relative position relationship between objects is very important for generating accurate captioning.Based on this,this paper proposes a spatial encoding and multi-layer joint encoding enhanced transformer for image captioning.In order to make better use of the position information contained in the image,this paper proposes a spatial encoding mechanism for visual objects,which converts the independent spatial relationship of each visual object into the relative spatial relationship between visual objects to help the model to recognize the relative spatial relationship between each visual object.At the same time,in the encoder part of visual objects,the top encoding feature retains more semantic information that fits the image but loses part of the visual information of the image.Taking this into account,this paper proposes a multi-level joint encoding mechanism to improve the semantic information contained in the top encoding layer by integrating the image feature information contained in each shallow encoding layer,so as to obtain richer semantic features that fit the image.This paper evaluates the proposed image captioning method by multiple evaluation indicators(BLEU,METEOR,ROUGE-L,CIDEr,etc.) on the MSCOCO dataset.The ablation experiment proves that the spatial encoding mechanism and the multi-level joint encoding mechanism proposed in this paper can be helpful in generating more accurate and effective image captions.Comparative experimental results show that the proposed method in can produce accurate and effective image caption and is superior to most of the latest methods.

The existing emotion recognition researches generally use neural network and attention mechanism to learn emotional features,which have relatively single feature representation.Moreover,neuroscience studies have shown that EEG signals of different frequencies and channels have different responses to emotion.Therefore,this paper proposes a method of fusing frequency and electrode channel convolutional attention for EEG emotion recognition.Specifically,EEG signals are firstly decomposed into different frequency bands and the corresponding frame-level features are extracted.Then the pre-activated residual network is employed to learn deep emotion-relevant features.At the same time,the frequency and electrode channel convolutional attention module is integrated into each pre-activated residual unit of residual network to model the frequency and channel information of EEG signals,thus generating final representation of EEG features.Experiments on DEAP and DREAMER datasets show that the proposed method helps to enhance the importing of emotion-salient information in EEG signals when compared with single-layer attention mechanism,and generates better recognition performance.

C40H42Mo5N8O23P2, triclinic, P1̄ (no. 2), a = 10.9867(2) Å, b = 15.4753(3) Å, c = 15.5666(3) Å, α = 85.583(2)°, β = 81.294(2)°, γ = 84.844(2)°, V = 2600.18(9) Å3, Z = 2, Rgt(F) = 0.0208, wRref(F2) = 0.0485, T = 293(2) K.

Background Uncontrolled proliferation of pulmonary artery smooth muscle cells (PASMCs) contributes to the pathogenesis of pulmonary arterial hypertension (PAH). In this work, we defined the precise part of circ_0068481 in PASMC proliferation and migration induced by hypoxia. We hypothesized that circ_0068481 enhanced hypoxia-induced PASMC proliferation, invasion, and migration through the microRNA (miR)-361-3p/Krüppel-like factor 5 (KLF5) pathway. Methods Human PASMCs (hPASMCs) were exposed to hypoxic (3% O2) conditions. Circ_0068481, miR-361-3p, and KLF5 levels were gauged by qRT-PCR and western blot. Cell viability, proliferation, invasion, and migration were detected by XTT, EdU incorporation, transwell, and wound-healing assays, respectively. Dual-luciferase reporter, RNA immunoprecipitation, and RNA pull-down assays were performed to confirm the direct relationship between miR-361-3p and circ_0068481 or KLF5. Results Circ_0068481 expression was increased in the serum of PAH patients and hypoxia-induced hPASMCs. Downregulation of circ_0068481 attenuated hypoxia-induced promotion in hPASMC proliferation, invasion, and migration. Circ_0068481 directly targeted miR-361-3p, and miR-361-3p downregulation reversed the inhibitory effects of circ_0068481 silencing on hypoxia-induced hPASMC proliferation, invasion, and migration. KLF5 was a direct miR-361-3p target, and miR-361-3p upregulation mitigated hypoxia-induced hPASMC proliferation, invasion, and migration by inhibiting KLF5 expression. Moreover, circ_0068481-induced KLF5 expression by binding to miR-361-3p in hypoxic hPASMCs. Conclusions Circ_0068481 knockdown ameliorated hypoxia-induced hPASMC proliferation, invasion, and migration at least in part through the miR-361-3p/KLF5 axis. [ABSTRACT FROM AUTHOR]