A deep dense captioning framework with joint localization and contextual reasoning

Dense captioning aims to simultaneously localize and describe regions-of-interest(RoIs)in images in natural language.Specifically,we identify three key problems:1)dense and highly overlapping RoIs,making accurate localization of each target region challenging;2)some visually ambiguous target regions which are hard to recognize each of them just by appearance;3)an extremely deep image representation which is of central importance for visual recognition.To tackle these three challenges,we propose a novel end-to-end dense captioning framework consisting of a joint localization module,a contextual reasoning module and a deep convolutional neural network(CNN).We also evaluate five deep CNN structures to explore the benefits of each.Extensive experiments on visual genome(VG)dataset demonstrate the effectiveness of our approach,which compares favorably with the state-of-the-art methods.

Numerical Analysis of Local Joint Flexibility of K-joints with External Plates Under Axial Loads in Offshore Tubular Structures

The Local Joint Flexibility(_(LJF))of steel K-joints reinforced with external plates under axial loads is investigated in this paper.For this aim,firstly,a finite element(FE)model was produced and verified with the results of several experimental tests.In the next step,a set of 150 FE models was generated to assess the effect of the brace angle(θ),the stiffener plate size(ηandλ),and the joint geometry(γ,τ,ξ,andβ)on the_(LJF)factor(f_(LJF)).The results showed that using the external plates can decrease 81%of the f_(LJF).Moreover,the reinforcing effect of the reinforcing plate on the f_(LJF)is more remarkable in the joints with smallerβ.Also,the effect of theγon the f_(LJF)ratio can be ignored.Despite the important effect of the f_(LJF)on the behavior of tubular joints,there is not available any study or equation on the f_(LJF)in any reinforced K-joints under axial load.Consequently,using the present FE results,a design parametric equation is proposed.The equation can reasonably predict the f_(LJF)in the reinforced K-joints under axial load.