Inner-imaging 3D attention module for residual network

3D imaging and modeling of the middle and inner ear

The bones of the middle ear are the smallest bones in the body and are among the most complicated functionally. They are located within the temporal bone – rendering them difficult to access and study. An accurate 3D model can offer an excellent illustration of the complex spatial relationships between the ossicles and the nerves and muscles with which they intertwine. The overall objective was...

RRA: Recurrent Residual Attention for Sequence Learning

In this paper, we propose a recurrent neural network (RNN) with residual attention (RRA) to learn long-range dependencies from sequential data. We propose to add residual connections across timesteps to RNN, which explicitly enhances the interaction between current state and hidden states that are several timesteps apart. This also allows training errors to be directly back-propagated through r...

Confocal Imaging of 3D Network Structures

Recurrent Residual Module for Fast Inference in Videos

Deep convolutional neural networks (CNNs) have made impressive progress in many video recognition tasks such as video pose estimation and video object detection. However, CNN inference on video is computationally expensive due to processing dense frames individually. In this work, we propose a framework called Recurrent Residual Module (RRM) to accelerate the CNN inference for video recognition...

Augmented laminography, a correlative 3D imaging method for revealing the inner structure of compressed fossils

Non-destructive imaging techniques can be extremely useful tools for the investigation and the assessment of palaeontological objects, as mechanical preparation of rare and valuable fossils is precluded in most cases. However, palaeontologists are often faced with the problem of choosing a method among a wide range of available techniques. In this case study, we employ x-ray computed tomography...