Deep-Learning-Based Segmentation of Keyhole in In-Situ X-ray Imaging of Laser Powder Bed Fusion.

In laser powder bed fusion processes, keyholes are the gaseous cavities formed where laser interacts with metal, and their morphologies play an important role in defect formation and the final product quality. The in-situ X-ray imaging technique can monitor the keyhole dynamics from the side and capture keyhole shapes in the X-ray image stream. Keyhole shapes in X-ray images are then often labeled by humans for analysis, which increasingly involves attempting to correlate keyhole shapes with defects using machine learning.

Vicinity Vision Transformer.

Vision transformers have shown great success on numerous computer vision tasks. However, their central component, softmax attention, prohibits vision transformers from scaling up to high-resolution images, due to both the computational complexity and memory footprint being quadratic. Linear attention was introduced in natural language processing (NLP) which reorders the self-attention mechanism to mitigate a similar issue, but directly applying existing linear attention to vision may not lead to satisfactory results.

Synergetic removal of oppositely charged dyes by co-precipitation and amphoteric self-floating capturer: Mechanism investigation by molecular simulation.

The adsorption performances of adsorbents to dyes are hard to maintain in a wide pH range because most of the reactions are pH-dependent, developing a cost-effective strategy to break the pH-limitation is significant. In this study, an amphoteric self-floating adsorbent (Am-SA) was synthesized by hollow silica microsphere surface modification, which was useful to capture anionic acid orange 7 (AO7) and cationic crystal violet (CV) dyes, but the adsorption performances were also greatly affected by pH. Fortunately, a co-precipitation phenomenon was noticed when the AO7 and CV solutions were mixed with a 1:1 molecule ratio.

Blind Motion Deblurring Super-Resolution: When Dynamic Spatio-Temporal Learning Meets Static Image Understanding.

Single-image super-resolution (SR) and multi-frame SR are two ways to super resolve low-resolution images. Single-Image SR generally handles each image independently, but ignores the temporal information implied in continuing frames. Multi-frame SR is able to model the temporal dependency via capturing motion information.

RNase L facilitates the repair of DNA double-strand breaks through the nonhomologous end-joining pathway.

RNA molecules have been found to play important roles in DNA double-strand break (DSB) repair, but the exact underlying mechanism remains unclear. Here, we aimed to clarify the function of RNase L, an important ribonuclease in the immune system of vertebrates, in DSB repair. Knockdown of RNase L reduces cell survival after induction of DSBs by ionizing radiation or camptothecin and causes a significant decrease in DSB repair, as evidenced by an increase in the extent of phosphorylation of histone H2AX on Ser139 (γH2AX) and γH2AX nuclear foci formation.

Adversarial Spatio-Temporal Learning for Video Deblurring.

Camera shake or target movement often leads to undesired blur effects in videos captured by a hand-held camera. Despite significant efforts having been devoted to video-deblur research, two major challenges remain: 1) how to model the spatio-temporal characteristics across both the spatial domain (i.e.

Identification of lncRNA MEG3 Binding Protein Using MS2-Tagged RNA Affinity Purification and Mass Spectrometry.

Long noncoding RNAs (lncRNAs) are nonprotein coding transcripts longer than 200 nucleotides. Recently in mammals, thousands of long noncoding RNAs have been identified and studied as key molecular players in different biological processes with protein complexes. As a long noncoding RNA, maternally expressed gene 3 (MEG3) plays an important role in many cellular processes.