When applying common object detection algorithms to detect small objects on high-resolution images, the down-sampling operation of the input images is inevitable due to the limitation of GPU memory. Accordingly, the details for characterizing small objects are lost. To resolve this contradiction, a small object detection method in a coarse-to-fine manner is presented. Specifically, some rough regions of interest (ROI) are firstly computed from low-resolution images. The prior knowledge of the positions of objects is used to guide the generation of ROIs. Then the features of small ROIs are recomputed from high-resolution images, and the features of large ROIs are obtained from the feature maps used to generate ROIs. The proposed method is validated on two datasets. One is a plant phenotyping dataset and the other is a public traffic sign dataset. Experimental results convincingly show the effectiveness of the proposed method.

There have been increasing demands for developing robotic system combining camera and inertial measurement unit in navigation task, due to their low-cost, lightweight and complementary properties. In this paper, we present a Visual Inertial Odometry (VIO) system which can utilize sparse depth to estimate 6D pose in GPS-denied and unstructured environments. The system is based on Multi-State Constraint Kalman Filter (MSCKF), which benefits from low computation load when compared to optimization-based method, especially on resource-constrained platform. Features are enhanced with depth information forming 3D landmark position measurements in space, which reduces uncertainty of position estimate. And we derivate measurement model to access compatibility with both 2D and 3D measurements. In experiments, we evaluate the performance of the system in different in-flight scenarios, both cluttered room and industry environment. The results suggest that the estimator is consistent, substantially improves the accuracy compared with original monocular-based MSKCF and achieves competitive accuracy with other research.

As a core subtask in anaphora resolution, anaphoricity determination has aroused the interest of researchers. However, in recent work, the influence caused by the deep semantic information and the context of the coreference elements have not been taken into account. In this paper, by combining the semantic feature of Uygur, we established a Convolutional Neural Network & Long Short-Term Memory (CNN_LSTM) model in determining the anaphoricity of Uygur pronoun. Firstly, the deep negative semantic feature representation is extracted via word2vec. Secondly, the shallow explicit feature representation of coreference elements is extracted by our system. Afterwards, two kinds of features are combined to recognize whether coreference element is referential or not. The results showed that the method we used can distinguish coreference element accurately, the ACC[Formula: see text] score is 90.18% and the ACC[Formula: see text] score is 89.93%, which are higher than ANN (Artificial Neural Network) and SVM (Support Vector Machine) respectively.

We describe matrix computations available in the cluster programming framework, Apache Spark. Out of the box, Spark provides abstractions and implementations for distributed matrices and optimization routines using these matrices. When translating single-node algorithms to run on a distributed cluster, we observe that often a simple idea is enough: separating matrix operations from vector operations and shipping the matrix operations to be ran on the cluster, while keeping vector operations local to the driver. In the case of the Singular Value Decomposition, by taking this idea to an extreme, we are able to exploit the computational power of a cluster, while running code written decades ago for a single core. Another example is our Spark port of the popular TFOCS optimization package, originally built for MATLAB, which allows for solving Linear programs as well as a variety of other convex programs. We conclude with a comprehensive set of benchmarks for hardware accelerated matrix computations from the JVM, which is interesting in its own right, as many cluster programming frameworks use the JVM. The contributions described in this paper are already merged into Apache Spark and available on Spark installations by default, and commercially supported by a slew of companies which provide further services.

Matrix factorization techniques such as the singular value decomposition (SVD) have had great success in recommender systems. We present a new perspective of SVD for constructing a latent space from the training data, which is justified by the theory of hypergraph model. We show that the vectors representing the items in the latent space can be grouped into (approximately) orthogonal clusters which correspond to the vertex clusters in the co-rating hypergraph, and the lengths of the vectors are indicators of the representativeness of the items. These properties are used for making top-$N$ recommendations in a two-phase algorithm. In this work, we provide a new explanation for the significantly better performance of the asymmetric SVD approaches and a novel algorithm for better diversity in top-N recommendations.