No abstract

Prevailing video frame interpolation techniques rely heavily on optical flow estimation and require additional model complexity and computational cost; it is also susceptible to error propagation in challenging scenarios with large motion and heavy occlusion. To alleviate the limitation, we propose a simple but effective deep neural network for video frame interpolation, which is end-to-end trainable and is free from a motion estimation network component. Our algorithm employs a special feature reshaping operation, referred to as PixelShuffle, with a channel attention, which replaces the optical flow computation module. The main idea behind the design is to distribute the information in a feature map into multiple channels and extract motion information by attending the channels for pixel-level frame synthesis. The model given by this principle turns out to be effective in the presence of challenging motion and occlusion. We construct a comprehensive evaluation benchmark and demonstrate that the proposed approach achieves outstanding performance compared to the existing models with a component for optical flow computation.

No abstract

Microorganisms such as protozoa and bacteria play very important roles in many practical domains, like agriculture, industry and medicine. To explore functions of different categories of microorganisms is a fundamental work in biological studies, which can assist biologists and related scientists to get to know more properties, habits and characteristics of these tiny but obbligato living beings. However, taxonomy of microorganisms (microorganism classification) is traditionally investigated through morphological, chemical or physical analysis, which is time and money consuming. In order to overcome this, since the 1970s innovative content-based microscopic image analysis (CBMIA) approaches are introduced to microbiological fields. CBMIA methods classify microorganisms into different categories using multiple artificial intelligence approaches, such as machine vision, pattern recognition and machine learning algorithms. Furthermore, because CBMIA approaches are semior full-automatic computer-based methods, they are very efficient and labour cost saving, supporting a technical feasibility for microorganism classification in our current big data age. In this article, we review the development history of microorganism classification using CBMIA approaches with two crossed pipelines. In the first pipeline, all related works are grouped by their corresponding microorganism application domains. By this pipeline, it is easy for microbiologists to have an insight into each special application domain and find their interested applied CBMIA techniques. In the second pipeline, the related works in each application domain are reviewed by time periods. Using this pipeline, computer scientists can see the dynamic of technological development clearly and keep up with the future devel-

Microorganisms play a great role in ecosystem, wastewater treatment, monitoring of environmental changes, and decomposition of waste materials. However, some of them are harmful to humans and animals such as tuberculosis bacteria and plasmodium. In such course, it is important to identify, track, analyze, consider the beneficial side and get rid of the negative effects of microorganisms using fast, accurate, and reliable methods. In recent decades, image analysis techniques have been used to address the drawbacks of manual traditional approaches in the identification and analysis of microorganisms. As image segmentation being an important step (technique) in the detection, tracking, monitoring, feature extraction, modeling, and analysis of microorganisms, different methods have been deployed, from classical approaches to current deep neural networks upon different challenges on microorganism images. This survey comprehensively analyses the various studies focused on developing microorganism image segmentation methods in the last 30 years (since 1989). In this survey, segmentation methods are categorized into classical and machine learning methods. Furthermore, these methods are subcategorized into threshold-based, regionbased, and edge-based which belong to classical methods, supervised and unsupervised machine leaningbased methods which belong to machine learning category. A growth trend of different methods and most frequently used methods in each category are meticulously analyzed. A clear explanation of the suitability of these methods for different segmentation challenges encountered on microscopic microorganism images is also enlightened. INDEX TERMSMicroorganism segmentation, content-based microscopic image analysis, feature extraction, microscopic images, classical methods, machine learning.

Partial label learning aims to learn from training examples each associated with a set of candidate labels, among which only one label is valid for the training example. The common strategy to induce predictive model is trying to disambiguate the candidate label set, such as disambiguation by identifying the ground-truth label iteratively or disambiguation by treating each candidate label equally. Nonetheless, these strategies ignore considering the generalized label distribution corresponding to each instance since the generalized label distribution is not explicitly available in the training set. In this paper, a new partial label learning strategy named PL-LE is proposed to learn from partial label examples via label enhancement. Specifically, the generalized label distributions are recovered by leveraging the topological information of the feature space. After that, a multi-class predictive model is learned by fitting a regularized multi-output regressor with the generalized label distributions. Extensive experiments show that PL-LE performs favorably against state-ofthe-art partial label learning approaches.

Label distribution is more general than both single-label annotation and multi-label annotation. It covers a certain number of labels, representing the degree to which each label describes the instance. The learning process on the instances labeled by label distributions is called label distribution learning (LDL). Unfortunately, many training sets only contain simple logical labels rather than label distributions due to the difficulty of obtaining the label distributions directly.  To solve the problem, one way is to recover the label distributions from the logical labels in the training set via leveraging the topological information of the feature space and the correlation among the labels. Such process of recovering label distributions from logical labels is defined as label enhancement (LE), which reinforces the supervision information in the training sets. This paper proposes a novel LE algorithm called Graph Laplacian Label Enhancement (GLLE). Experimental results on one artificial dataset and fourteen real-world datasets show clear advantages of GLLE over several existing LE algorithms.

Recently, neural networks with deep architecture have been widely applied to acoustic scene classification. Both Convolutional Neural Networks (CNNs) and Long Short-Term Memory Networks (LSTMs) have shown improvements over fully connected Deep Neural Networks (DNNs). Motivated by the fact that CNNs, LSTMs and DNNs are complimentary in their modeling capability, we apply the CLDNNs (Convolutional, Long Short-Term Memory, Deep Neural Networks) framework to short-duration acoustic scene classification in a unified architecture. The CLDNNs take advantage of frequency modeling with CNNs, temporal modeling with LSTM, and discriminative training with DNNs. Based on the CLDNN architecture, several novel attention-based mechanisms are proposed and applied on the LSTM layer to predict the importance of each time step. We evaluate the proposed method on the truncated version of the 2016 TUT acoustic scenes dataset which consists of recordings from 15 different scenes. By using CLDNNs with bidirectional LSTM, we achieve higher performance compared to the conventional neural network architectures. Moreover, by combining the attention-weighted output with LSTM final time step output, significant improvement can be further achieved.