VLTinT: Visual-Linguistic Transformer-in-Transformer for Coherent Video Paragraph Captioning

End-to-End Dense Video Captioning with Masked Transformer

Dense video captioning aims to generate text descriptions for all events in an untrimmed video. This involves both detecting and describing events. Therefore, all previous methods on dense video captioning tackle this problem by building two models, i.e. an event proposal and a captioning model, for these two sub-problems. The models are either trained separately or in alternation. This prevent...

VXT: Visual XML Transformer

The ever growing amount of heterogeneous data exchanged through the Internet, combined with the popularity of XML, make structured document transformations an increasingly important application domain. Most of the existing solutions for expressing XML transformations are textual languages, such as XSLT or DOM combined with a general-purpose programming language. Several tools build on top of th...

Whegs Transformer

Transformer proteins

Proteins are generally believed to adopt a unique fold, defined by their amino acid sequence, under specific environmental conditions. These unique structures, in turn, endow proteins with one specific function. However, not all proteins obey the “1 amino acid sequence → 1 fold → 1 function” scheme. Moonlighting proteins that adopt one distinct threedimensional structure but can accomplish two ...

Transformer in Grid

The aim of this research article is to determine the way to install surge arresters close to a power transformer to provide protection against lightning overvoltage. Depending on the length of the cables used in the installation, the insulation levels in base insulators of surge arresters and bushings of transformers change according to the voltage they support. For validation purposes, the vol...