Search

In recent years,as one of the important issues in natural language processing,the human-machine dialogue system has received more and more attention.Methods of deep learning based on big data are widely used in dialogue systems.In this paper,the background of human-machine dialogue system is firstly introduced,then dialogue system based on multiple-round interaction is taken as an example.This paper emphasizes on task-oriented and non-task-oriented dialogue systems,elaborates the main types and current research progress.After that,this paper provides an overview of some main methods of evaluating the dialogue system.Finally,based on the current research status,the prospect of some future research directions on human-machine dialogue system are discussed. [ABSTRACT FROM AUTHOR]

At present, deep learning has been widely applied in object detection, such as vehicle detection. In this paper, the deep learning EfficientDet model was analyzed, and its advantages in vehicle detection were confirmed. A phased adaptive training model was constructed to avoid local optimum in training process, then it was used to detect vehicles from both short and long distance. The detection results showed that compared with detection methods based on Cascade R-CNN and CenterNet, the proposed model was superior in terms of computational complexity, time con sumption and detection accuracy. Meanwhile, further analysis figured out the optimal detection distance and angle.Finally, an example is given to verify that the proposed method can be applied to a large range of vehicle detection. [ABSTRACT FROM AUTHOR]

Visual Odometry（VO）,which is an important part of visual simultaneous localization and mapping technology, is mainly used for robot pose estimation and local map building through time series images captured by camera sensors.Known as the front end, VO has been widely used in many fields and achieved fruitful practical results, and it is of great significance for unmanned driving, autonomous drones, virtual reality, and augmented reality, etc.In this paper, we summarize the recent research results on the novel visual odometry technology based on introduction of various algorithms in the framework module of classical VO.According to their technical means, the novel methods are divided into two categories, including VO integrated with multiple sensors（take VIO as an example）,and VO based on deep learning.The former improves the accuracy of VO by complementing the advantages of various sensors, while the latter is combined with deep learning network.Finally, the existing algorithms of visual odometry are compared, and the future development trend is forecasted based on the challenges faced by VO. [ABSTRACT FROM AUTHOR]

Research on object detection has developed rapidly in recent years with the progress of deep learning. However,the deep learning based object detection systems rely heavily on large scale labeled training data, which are rarely available in our realistic scene, so few-shot object detection get researchers' great concern.In this paper, we present a survey of few-shot object detection, and introduce the mainstream approaches and their characteristics, merits as well as limits.Finally, we provide the possible direction for further few-shot object detection research. [ABSTRACT FROM AUTHOR]

Fine-grained image classification is a fundamental and important task in field of computer vision.The purpose of the task is to distinguish between object categories that have subtle inter-class differences (e.g.,birds,flowers,or animals of different sub-categories).Different from traditional image classification tasks that can employ a large number of common people for image annotations,fine-grained image classification usually requires expert-level knowledge.In addition to the common classification challenges of pose,lighting,and viewing changes,fine-grained datasets have larger inter-class similarity and intra-class variability.Therefore,it puts a high demand on the models to capture the subtle visual differences between classes and common intra-class characteristics.Furthermore,owing to the difficulty in obtaining samples of different categories,fine-grained datasets suffer from long-tail distribution problem.In summary,fine-grained data distribution has the characteristics of small,non-uniform,and indistinguishable inter-class differences,which also poses a huge challenge to the powerful deep learning algorithms.In this paper,we first introduce the formulation and challenges of fine-grained visual categorization tasks,and then illustrate two mainstream methods about local features and global features,as well as their advantages and disadvantages.Finally,we compare the performance of related works on common used datasets,and we make the required summarization and forecast. [ABSTRACT FROM AUTHOR]

Heterogeneous face synthesis aims at generating visually realistic and identity-preserving portraits of different modality, such as sketches, caricatures, etc. Heterogeneous face synthesis is of great significance for both public security and digital entertainment, and has attracted numerous attention. Recently, inspired by the dramatic progress in generative adversarial networks (GANs) and their great successes in image-to-image translation tasks, researchers have proposed a number of new heterogeneous face synthesis methods based on GANs. In this paper, we briefly introduce the development of heterogeneous face synthesis, and detailed recent progresses in terms of developments of applications, architectures of GANs, performance evaluation approaches, datasets, and qualitative analysis. Finally, we summarize the challenges and some prospects of heterogeneous face synthesis. [ABSTRACT FROM AUTHOR]