Mechanical Behaviour of Aluminium-Timber Composite Connections with Screws and Toothed Plates

This paper presents an investigation of the load-slip behaviour of aluminium-timber composite connections. Toothed plates with bolts are often used for connecting timber structural members with steel structural members. In this paper, toothed plates (C2-50/M10G, C2-50/M12G or C11-50/M12) have been used as reinforcement in aluminium-timber screwed connections for the first time. The push-out test specimens consisted of laminated veneer lumber slabs, aluminium alloy beams, and hexagon head wood screws (10 mm × 80 mm and 12 mm × 80 mm). Of the specimens, 12 additionally had toothed plates as reinforcement, while 8 had no reinforcement. The load carrying-capacity, the mode of failure and the load-slip response of the strengthened and non-strengthened screwed connections were investigated. The use of toothed plate connectors was found to be effective in increasing the strength of aluminium-timber composite connections and ineffective in improving their stiffness. The examined stiffness and strength of the connections can be used in the design and numerical modelling of aluminium-timber composite beams with reinforced screwed connections.

Cascade Network with Deformable Composite Backbone for Formula Detection in Scanned Document Images

This paper presents a novel architecture for detecting mathematical formulas in document images, which is an important step for reliable information extraction in several domains. Recently, Cascade Mask R-CNN networks have been introduced to solve object detection in computer vision. In this paper, we suggest a couple of modifications to the existing Cascade Mask R-CNN architecture: First, the proposed network uses deformable convolutions instead of conventional convolutions in the backbone network to spot areas of interest better. Second, it uses a dual backbone of ResNeXt-101, having composite connections at the parallel stages. Finally, our proposed network is end-to-end trainable. We evaluate the proposed approach on the ICDAR-2017 POD and Marmot datasets. The proposed approach demonstrates state-of-the-art performance on ICDAR-2017 POD at a higher IoU threshold with an f1-score of 0.917, reducing the relative error by 7.8%. Moreover, we accomplished correct detection accuracy of 81.3% on embedded formulas on the Marmot dataset, which results in a relative error reduction of 30%.

Cascade Network with Deformable Composite Backbone for Formula Detection in Scanned Document Images

This paper presents a novel architecture for detecting mathematical formulas in document images, which is an important step for reliable information extraction in several domains. Recently, Cascade Mask R-CNN networks have been introduced to solve object detection in computer vision. In this paper, we suggest a couple of modifications to the existing Cascade Mask R-CNN architecture: First, the proposed network uses deformable convolutions instead of conventional convolutions in the backbone network to spot areas of interest better. Second, it uses a dual backbone of ResNeXt-101, having composite connections at the parallel stages. Finally, our proposed network is end-to-end trainable. We evaluate the proposed approach on the ICDAR-2017 POD and Marmot datasets. The proposed approach demonstrates state-of-the-art performance on ICDAR-2017 POD at a higher IoU threshold with an f1-score of 0.917, reducing the relative error by 7.8%. Moreover, we accomplished correct detection accuracy of 81.3% on embedded formulas on the Marmot dataset, which results in a relative error reduction of 30%.

Performance of composite connections strengthened with CFRP laminate

A three-dimensional non-linear finite element model is developed to predict the moment-rotational response of partial depth endplate composite connections strengthened with external Carbon Fiber Reinforced Polymer (CFRP) laminates. A parametric study is then performed to evaluate the influence of length, width and thickness of CFRP laminates on the composite connection performance. In addition, the feasibility of decreasing the reinforcement bar ratios in the presence of the CFRP laminate is investigated. The numerical analysis reveals that the flexural resistance of the retrofitted CFRP strengthened composite connection increases by up to around 20% and the rotation capacity decreases by approximately 60%. Also, the results indicate that applying CFRP laminate to the tension face of the composite slab can reduce the amount of rebar needed for the bending capacity of steel-concrete composite beam-to-column connections.

CBNet: A Novel Composite Backbone Network Architecture for Object Detection

In existing CNN based detectors, the backbone network is a very important component for basic feature1 extraction, and the performance of the detectors highly depends on it. In this paper, we aim to achieve better detection performance by building a more powerful backbone from existing ones like ResNet and ResNeXt. Specifically, we propose a novel strategy for assembling multiple identical backbones by composite connections between the adjacent backbones, to form a more powerful backbone named Composite Backbone Network (CBNet). In this way, CBNet iteratively feeds the output features of the previous backbone, namely high-level features, as part of input features to the succeeding backbone, in a stage-by-stage fashion, and finally the feature maps of the last backbone (named Lead Backbone) are used for object detection. We show that CBNet can be very easily integrated into most state-of-the-art detectors and significantly improve their performances. For example, it boosts the mAP of FPN, Mask R-CNN and Cascade R-CNN on the COCO dataset by about 1.5 to 3.0 points. Moreover, experimental results show that the instance segmentation results can be improved as well. Specifically, by simply integrating the proposed CBNet into the baseline detector Cascade Mask R-CNN, we achieve a new state-of-the-art result on COCO dataset (mAP of 53.3) with a single model, which demonstrates great effectiveness of the proposed CBNet architecture. Code will be made available at https://github.com/PKUbahuangliuhe/CBNet.