In this paper, for the first time, we investigate the problem of generating 3D shapes from professional 2D sketches via deep learning. We target sketches done by professional artists, as these sketches are likely to contain more details than the ones produced by novices, and thus the reconstruction from such sketches poses a higher demand on the level of detail in the reconstructed models. This is importantly different to previous work, where the training and testing was conducted on either synthetic sketches or sketches done by novices. Novices sketches often depict shapes that are physically unrealistic, while models trained with synthetic sketches could not cope with the level of abstraction and style found in real sketches. To address this problem, we collected the first large-scale dataset of professional sketches, where each sketch is paired with a reference 3D shape, with a total of 1,500 professional sketches collected across 500 3D shapes. The dataset is available at http://sketchx.ai/downloads/. We introduce two bespoke designs within a deep adversarial network to tackle the imprecision of human sketches and the unique figure/ground ambiguity problem inherent to sketch-based reconstruction. We show that existing 3D shapes generation methods designed for images fail to be naively applied to our problem, and demonstrate the effectiveness of our method both qualitatively and quantitatively.

Many researchers nowadays choose multi-omics techniques for myocardial infarction studies. However, there’s yet to be a review article integrating myocardial infarction multi-omics. Hence, this study adopts the popular bibliometrics. Based on its principles, we use software like R Studio, Vosviewer, Citespace, and SciMAT to analyze literature data of myocardial infarction omics research (1991–2022) from Web of Science. By extracting key information and calculating weights, we conduct analyses from 4 aspects: Collaboration Network Analysis, Co-word Analysis, Citing and Cited Journal Analysis, and Co-citation and Clustering Analysis, aiming to understand the field’s cooperation, research topic evolution, and knowledge flow. The results show that myocardial infarction omics research is still in its early stage with limited international cooperation. In terms of knowledge flow, there’s no significant difference within the discipline, but non-biomedical disciplines have joined, indicating an interdisciplinary integration trend. In the overall research field, genomics remains the main topic with many breakthroughs identifying susceptibility sites. Meanwhile, other omics fields like lipidomics and proteomics are also progressing, clarifying the pathogenesis. The cooperation details in this article enable researchers to connect with others, facilitating their research. The evolution trend of subject terms helps them set goals and directions, quickly grasp the development context, and read relevant literature. Journal analysis offers submission suggestions, and the analysis of research base and frontier provides references for the research’s future development.

The widespread adoption of encryption technologies has greatly increased the complexity of network traffic classification, as plaintext features such as DNS are increasingly unavailable. Traditional payload-based approaches fail under strong encryption, while statistical and deep learning methods relying on single-level information often struggle to capture comprehensive traffic patterns. To address these challenges, we propose Cross-Level Encrypted Traffic (CLET), a novel classification model that integrates session-level and packet-level representations to capture comprehensive patterns in encrypted traffic. At the session level, CLET constructs an 87-dimensional attribute set encompassing certificate characteristics, temporal behaviors, and spatial distributions, providing a robust global view of each flow. At the packet level, CLET introduces a compact 13-dimensional attribute set processed by a hybrid CNN-Transformer network with dual attention mechanisms, learning fine-grained temporal and spatial dependencies while avoiding redundant information. By jointly leveraging global and local representations, CLET mitigates information loss and enhances feature discriminability. Experiments on the LFETT2021 and ISCX-VPN datasets show that CLET outperforms state-of-the-art baselines, demonstrating the effectiveness of cross-level learning for encrypted traffic classification.