25 September 2024 in IEEE Transactions on Neural Networks and Learning Systems
Siamese-network-based trackers convert the general object tracking as a similarity matching task between a template and a search region. Using convolutional feature cross correlation (Xcorr) for similarity matching, a large number of Siamese trackers are proposed and achieved great success. However, due to the predefined size of the target feature, these trackers suffer from either retaining much background information or losing important foreground information. Moreover, the global matching between the target and search region also largely neglects the part-level structural information and the contextual information of the target. To tackle the aforementioned obstacles, in this article, we propose a simple context-aware Siamese graph attention network, which establishes part-to-part correspondence between the Siamese branches with a complete bipartite graph. The object information from the template is propagated to the search region via a graph attention mechanism. With such a design, a target-aware template input is enabled to replace the prefixed template region, which can adaptively fit the size and aspect ratio variations in different objects. Based on it, we further construct a context-aware feature matching mechanism to embed both the target and the contextual information in the search region. Experiments on challenging benchmarks including GOT-10k, TrackingNet, LaSOT, VOT2020, and OTB-100 demonstrate that the proposed SiamGAT* outperforms many state-of-the-art trackers and achieves leading performance. Code is available at: https://git.io/SiamGAT.
9 December 2021 in Human Mutation
Approximately 10% of von Willebrand factor (VWF) gene variants are suspected to disrupt messenger RNA (mRNA) processing, the number of which might be underestimated due to the lack of transcript assays. In the present study, we provided a detailed strategy to evaluate the effects of nine putative splice site variants (PSSVs) of VWF on mRNA processing as well as protein properties and establish their genotype-phenotype relationships. Eight of nine PSSVs affected VWF splicing: c.322A>T, c.1534-13_1551delinsCA, and c.8116-2del caused exon skipping; c.221-2A>C, c.323+1G>T, and c.2547-13T>A resulted in the activation of cryptic splice sites; c.2684A>G led to exon skipping and activation of a cryptic splice site; c.2968-14A>G created a new splice site. The remaining c.5171-9del was likely benign. The efficiency of nonsense-mediated mRNA decay (NMD) was much higher in platelets compared to leukocytes, impairing the identification of aberrant transcripts in 4 of 8 PSSVs. The nonsense variant c.322A>T partially impaired mRNA processing, leaking a small amount of correct transcripts with c.322T (p.Arg108*), while the missense variant c.2684A>G totally disrupted normal splicing of VWF, rather than produced mutant protein with the substitution of Gln895Arg. The results of this study would certainly add novel insights into the molecular events behind von Willebrand disease.
1 January 2026 in IEEE Transactions on Image Processing