Classification of Smoking and Calling using Deep Learning

Since 2014, very deep convolutional neural networks have been proposed and become the must-have weapon for champions in all kinds of competition. In this report, a pipeline is introduced to perform the classification of smoking and calling by modifying the pretrained inception V3. Brightness enhancing based on deep learning is implemented to improve the classification of this classification task along with other useful training tricks. Based on the quality and quantity results, it can be concluded that this pipeline with small biased samples is practical and useful with high accuracy.

AEGCN: An Autoencoder-Constrained Graph Convolutional Network

We propose a novel neural network architecture, called autoencoder-constrained graph convolutional network, to solve node classification task on graph domains. As suggested by its name, the core of this model is a convolutional network operating directly on graphs, whose hidden layers are constrained by an autoencoder. Comparing with vanilla graph convolutional networks, the autoencoder step is added to reduce the information loss brought by Laplacian smoothing. We consider applying our model on both homogeneous graphs and heterogeneous graphs. For homogeneous graphs, the autoencoder approximates the adjacency matrix of the input graph by taking hidden layer representations as encoder and another one-layer graph convolutional network as decoder. For heterogeneous graphs, since there are multiple adjacency matrices corresponding to different types of edges, the autoencoder approximates the feature matrix of the input graph instead, and changes the encoder to a particularly designed multi-channel pre-processing network with two layers. In both cases, the error occurred in the autoencoder approximation goes to the penalty term in the loss function. In extensive experiments on citation networks and other heterogeneous graphs, we demonstrate that adding autoencoder constraints significantly improves the performance of graph convolutional networks. We also notice that such technique can be applied on graph attention network to improve the performance as well. This reveals the wide applicability of the proposed autoencoder technique.

Recognizing Handwritten Mathematical Expressions as LaTex Sequences Using a Multiscale Robust Neural Network

In this paper, a robust multiscale neural network is proposed to recognize handwritten mathematical expressions and output LaTeX sequences, which can effectively and correctly focus on where each step of output should be concerned and has a positive effect on analyzing the two-dimensional structure of handwritten mathematical expressions and identifying different mathematical symbols in a long expression. With the addition of visualization, the model's recognition process is shown in detail. In addition, our model achieved 49.459% and 46.062% ExpRate on the public CROHME 2014 and CROHME 2016 datasets. The present model results suggest that the state-of-the-art model has better robustness, fewer errors, and higher accuracy.

Deep Multiphase Level Set for Scene Parsing

Recently, Fully Convolutional Network (FCN) seems to be the go-to architecture for image segmentation, including semantic scene parsing. However, it is difficult for a generic FCN to discriminate pixels around the object boundaries, thus FCN based methods may output parsing results with inaccurate boundaries. Meanwhile, level set based active contours are superior to the boundary estimation due to the sub-pixel accuracy that they achieve. However, they are quite sensitive to initial settings. To address these limitations, in this paper we propose a novel Deep Multiphase Level Set (DMLS) method for semantic scene parsing, which efficiently incorporates multiphase level sets into deep neural networks. The proposed method consists of three modules, i.e., recurrent FCNs, adaptive multiphase level set, and deeply supervised learning. More specifically, recurrent FCNs learn multi-level representations of input images with different contexts. Adaptive multiphase level set drives the discriminative contour for each semantic class, which makes use of the advantages of both global and local information. In each time-step of the recurrent FCNs, deeply supervised learning is incorporated for model training. Extensive experiments on three public benchmarks have shown that our proposed method achieves new state-of-the-art performances.

An Efficient Method of Detection and Recognition in Remote Sensing Image Based on multi-angle Region of Interests

Presently, deep learning technology has been widely used in the field of image recognition. However, it mainly aims at the recognition and detection of ordinary pictures and common scenes. As special images, remote sensing images have different shooting angles and shooting methods compared with ordinary ones, which makes remote sensing images play an irreplaceable role in some areas. In this paper, based on a deep convolution neural network for providing multi-level information of images and combines RPN (Region Proposal Network) for generating multi-angle ROIs (Region of Interest), a new model for object detection and recognition in remote sensing images is proposed. In the experiment, it achieves better results than traditional ways, which demonstrate that the model proposed here would have a huge potential application in remote sensing image recognition.

Robust Encoder-Decoder Learning Framework towards Offline Handwritten Mathematical Expression Recognition Based on Multi-Scale Deep Neural Network

Offline handwritten mathematical expression recognition is a challenging task, because handwritten mathematical expressions mainly have two problems in the process of recognition. On one hand, it is how to correctly recognize different mathematical symbols. On the other hand, it is how to correctly recognize the two-dimensional structure existing in mathematical expressions. Inspired by recent work in deep learning, a new neural network model that combines a Multi-Scale convolutional neural network (CNN) with an Attention recurrent neural network (RNN) is proposed to identify two-dimensional handwritten mathematical expressions as one-dimensional LaTeX sequences. As a result, the model proposed in the present work has achieved a WER error of 25.715% and ExpRate of 28.216%.

ChestNet: A Deep Neural Network for Classification of Thoracic Diseases on Chest Radiography

Computer-aided techniques may lead to more accurate and more acces-sible diagnosis of thorax diseases on chest radiography. Despite the success of deep learning-based solutions, this task remains a major challenge in smart healthcare, since it is intrinsically a weakly supervised learning problem. In this paper, we incorporate the attention mechanism into a deep convolutional neural network, and thus propose the ChestNet model to address effective diagnosis of thorax diseases on chest radiography. This model consists of two branches: a classification branch serves as a uniform feature extraction-classification network to free users from troublesome handcrafted feature extraction, and an attention branch exploits the correlation between class labels and the locations of patholog-ical abnormalities and allows the model to concentrate adaptively on the patholog-ically abnormal regions. We evaluated our model against three state-of-the-art deep learning models on the Chest X-ray 14 dataset using the official patient-wise split. The results indicate that our model outperforms other methods, which use no extra training data, in diagnosing 14 thorax diseases on chest radiography.

Non-rigid Object Tracking via Deep Multi-scale Spatial-Temporal Discriminative Saliency Maps

In this paper we propose an effective non-rigid object tracking method based on spatial-temporal consistent saliency detection. In contrast to most existing trackers that use a bounding box to specify the tracked target, the proposed method can extract the accurate regions of the target as tracking output, which achieves better description of the non-rigid objects while reduces background pollution to the target model. Furthermore, our model has several unique features. First, a tailored deep fully convolutional neural network (TFCN) is developed to model the local saliency prior for a given image region, which not only provides the pixel-wise outputs but also integrates the semantic information. Second, a multi-scale multi-region mechanism is proposed to generate local region saliency maps that effectively consider visual perceptions with different spatial layouts and scale variations. Subsequently, these saliency maps are fused via a weighted entropy method, resulting in a final discriminative saliency map. Finally, we present a non-rigid object tracking algorithm based on the proposed saliency detection method by utilizing a spatial-temporal consistent saliency map (STCSM) model to conduct target-background classification and using a simple fine-tuning scheme for online updating. Numerous experimental results demonstrate that the proposed algorithm achieves competitive performance in comparison with state-of-the-art methods for both saliency detection and visual tracking, especially outperforming other related trackers on the non-rigid object tracking datasets.

Video Person Re-identification by Temporal Residual Learning

In this paper, we propose a novel feature learning framework for video person re-identification (re-ID). The proposed framework largely aims to exploit the adequate temporal information of video sequences and tackle the poor spatial alignment of moving pedestrians. More specifically, for exploiting the temporal information, we design a temporal residual learning (TRL) module to simultaneously extract the generic and specific features of consecutive frames. The TRL module is equipped with two bi-directional LSTM (BiLSTM), which are respectively responsible to describe a moving person in different aspects, providing complementary information for better feature representations. To deal with the poor spatial alignment in video re-ID datasets, we propose a spatial-temporal transformer network (ST^2N) module. Transformation parameters in the ST^2N module are learned by leveraging the high-level semantic information of the current frame as well as the temporal context knowledge from other frames. The proposed ST^2N module with less learnable parameters allows effective person alignments under significant appearance changes. Extensive experimental results on the large-scale MARS, PRID2011, ILIDS-VID and SDU-VID datasets demonstrate that the proposed method achieves consistently superior performance and outperforms most of the very recent state-of-the-art methods.

Learning Uncertain Convolutional Features for Accurate Saliency Detection

Deep convolutional neural networks (CNNs) have delivered superior performance in many computer vision tasks. In this paper, we propose a novel deep fully convolutional network model for accurate salient object detection. The key contribution of this work is to learn deep uncertain convolutional features (UCF), which encourage the robustness and accuracy of saliency detection. We achieve this via introducing a reformulated dropout (R-dropout) after specific convolutional layers to construct an uncertain ensemble of internal feature units. In addition, we propose an effective hybrid upsampling method to reduce the checkerboard artifacts of deconvolution operators in our decoder network. The proposed methods can also be applied to other deep convolutional networks. Compared with existing saliency detection methods, the proposed UCF model is able to incorporate uncertainties for more accurate object boundary inference. Extensive experiments demonstrate that our proposed saliency model performs favorably against state-of-the-art approaches. The uncertain feature learning mechanism as well as the upsampling method can significantly improve performance on other pixel-wise vision tasks.