Behavior recognition algorithm based on the improved R3D and LSTM network fusion

Because behavior recognition is based on video frame sequences,this paper proposes a behavior recognition algorithm that combines 3D residual convolutional neural network(R3D)and long short-term memory(LSTM).First,the residual module is extended to three dimensions,which can extract features in the time and space domain at the same time.Second,by changing the size of the pooling layer window the integrity of the time domain features is preserved,at the same time,in order to overcome the difficulty of network training and over-fitting problems,the batch normalization(BN)layer and the dropout layer are added.After that,because the global average pooling layer(GAP)is affected by the size of the feature map,the network cannot be further deepened,so the convolution layer and maxpool layer are added to the R3D network.Finally,because LSTM has the ability to memorize information and can extract more abstract timing features,the LSTM network is introduced into the R3D network.Experimental results show that the R3D+LSTM network achieves 91%recognition rate on the UCF-101 dataset.

3D Filtering by Block Matching and Convolutional Neural Network for Image Denoising

Block matching based 3D filtering methods have achieved great success in image denoising tasks. However the manually set filtering operation could not well describe a good model to transform noisy images to clean images. In this paper, we introduce convolutional neural network （CNN） for the 3D filtering step to learn a well fitted model for denoising. With a trainable model, prior knowledge is utilized for better mapping from noisy images to clean images. This block matching and CNN joint model （BMCNN） could denoise images with different sizes and different noise intensity well, especially images with high noise levels. The experimental results demonstrate that among all competing methods, this method achieves the highest peak signal to noise ratio （PSNR） when denoising images with high noise levels （σ 〉 40）, and the best visual quality when denoising images with all the tested noise levels.

Polymersome formation by solvent annealing-induced structural reengineering under 3D soft confinement

A solvent annealing-induced structural reengineering approach is exploited to fabricate polymersomes from block copolymers that are hard to form vesicles through the traditional solution self-assembly route.More specifically,polystyrene-b-poly(4-vinyl pyridine)(PS-b-P4VP)particles with sphere-within-sphere structure(SS particles)are prepared by three-dimensional(3D)soft-confined assembly through emulsion-solvent evaporation,followed by 3D soft-confined solvent annealing upon the SS particles in aqueous dispersions for structural engineering.A water-miscible solvent(e.g.,THF)is employed for annealing,which results in dramatic transitions of the assemblies,e.g.,from SS particles to polymersomes.This approach works for PS-b-P4VP in a wide range of block ratios.Moreover,this method enables effective encapsulation/loading of cargoes such as fluorescent dyes and metal nanoparticles,which offers a new route to prepare polymersomes that could be applied for cargo release,diagnostic imaging,and nanoreactor,etc.

Improving Wind Forecasts Using a Gale-Aware Deep Attention Network

Numerical weather prediction of wind speed requires statistical postprocessing of systematic errors to obtain reliable and accurate forecasts.However,use of postprocessing models is often undesirable for extreme weather events such as gales.Here,we propose a postprocessing algorithm based on a gale-aware deep attention network to simultaneously improve wind speed forecasts and gale area warnings.Specifically,the algorithm includes both a galeaware loss function that focuses the model on potential gale areas,and an observation station supervision strategy that alleviates the problem of missing extreme values caused by data gridding.The effectiveness of the proposed model was verified by using data from 235 wind speed observation stations.Experimental results show that our model can produce wind speed forecasts with a root-mean-square error of 1.1547 m s^(-1),and a Hanssen–Kuipers discriminant score of 0.517,performance that is superior to that of the other postprocessing algorithms considered.