Domain adaptation is an important technology for transferring source domain knowledge to new, unseen target domains. Recently, domain adaptation models are applied to learn domain invariant representations by minimizing distribution distance or adversarial training in the feature space. However, existing adversarial domain adaptation methods fail to preserve the data structure in the feature space

Recently, many efforts have been made to model spatial–temporal features from human skeleton for action recognition by using graph convolutional networks (GCN). Skeleton sequence can precisely represent human pose with a small number of joints while there is still a lot of redundancies across the skeleton sequence in the term of temporal dependency. In order to improve the effectiveness of spatial–temporal

The model pruning is one of the predominant model compression tasks to decrease the demands in computing power and memory footprint. However, most existing pruning methods have overly broad application areas, which defects in a sub-optimal solution specifically to solve certain specified difficult problems in the tasks of salient object detection. In this paper, we propose a novel solution, dubbed

Network convergence as well as recognition accuracy are essential issues when applying Convolutional Neural Networks (CNN) to human action recognition. Most deep learning methods neglect model convergence when striving to improve the abstraction capability, thus degrading the performances sharply when computing resources are limited. To mitigate this problem, we propose a structure named 2D Progressive

Generative adversarial networks (GANs) have been extensively studied in recent years and have been used to address several problems in the fields of image generation and computer vision. Despite significant advancements in computer vision, applying GANs to real-world problems such as 3D face generation remains a challenge. Owing to the proliferation of fake images generated by GANs, it is important

Estimating the 6D object pose based on a monocular RGB image is a challenging task in computer vision, which produces false positives under the influence of occlusion or cluttered environments. In addition, the prediction of translation is affected by changes of the image size. In this work, we present a novel two-stage method TGCPose6D for robust 6DoF object pose estimation which is composed of 2D

Behavior recognition is a well-known computer vision mobile technology. It has been used in many applications such as video surveillance, motion detection on devices, human-computer interaction and sports video, etc. However, most of the existing works ignored the depth and spatio-temporal information so that they resulted in over-fitting and inferior performance. Consequently, a novel framework for

In the field of detection, there is a wide gap between the performance of small objects and that of medium, large objects. Some studies show that this gap is due to the contradiction between the classification-based backbone and localization. Although the reduction in the feature map size is beneficial for the extraction of abstract features, it will cause the loss of detailed features in the localization

Visible-Infrared person re-IDentification (VI-reID) aims to automatically retrieve the pedestrian of interest exposed to sensors in different modalities, such as visible camera v.s. infrared sensor. It struggles to learn both modality-invariant and discriminant representations. Unfortunately, existing VI-reID work mainly focuses on tackling the modality difference, which fine-grained level discriminant

Image captioning is the task of generating captions of images in natural language. The training typically consists of two phases, first minimizing the XE (cross-entropy) loss, and then with RL (reinforcement learning) over CIDEr scores. Although there are many innovations in neural architectures, fewer works are proposed for the RL phase. Motivated by one recent state-of-the-art architecture X-Transformer

Data set of high quality is the cornerstone of the current data-driven machine learning models, and plays an important role in promoting the development of various application areas. At present, image analysis and processing techniques have intensively involved into the tasks of inheriting and protecting culture resources. However, currently there are few effective image data sets about the traditional

Object detection is a crucial task in computer vision systems with a wide range of applications in autonomous driving, medical imaging, retail, security, face recognition, robotics, and others. Nowadays, neural networks-based models are used to localize and classify instances of objects of particular classes. When real-time inference is not required, ensembles of models help to achieve better results

Image composition aims to composite a material region into a target image. Using this technique, more images could be interactive, as there are millions of images created daily in modern life. However, it is difficult for the majority of traditional composition methods to retrieve relatively realistic semantically valid material images. Also, even if the minority of traditional composition methods

The increasing availability of extensive digitized fine art collections opens up new research directions. In particular, correctly identifying the artistic style or art movement of paintings is crucial for large artistic database indexing, painter authentication, and mobile recognition of painters. Even though the implementation of CNN on artwork classification improved the performance dramatically

Predicting future actions is a key in visual understanding, surveillance, and human behavior analysis. Current methods for video-based prediction are primarily using single-view data, while in the real world multiple cameras and produced videos are readily available, which may potentially benefit the action prediction tasks. However, it may bring up a new challenge: subjects in the videos are more

Predicting pedestrian trajectory is useful in many applications, such as autonomous driving and unmanned vehicles. However, it is a challenging task because of the complexity of the interactions among pedestrians and the environment. Most existing works employ long short-term memory networks to learn pedestrian behaviors, but their prediction accuracy is not good, and their computing speed is relatively

How to effectively utilize and fuse deep features has become a critical point for salient object detection. Most existing methods usually adopt the convolutional features based on U-shape structures and fuse multi-scale convolutional features without fully considering the different characteristics between high-level features and low-level features. Furthermore, existing salient object detection methods

As a practical pursuit of quantified uniqueness, biometrics explores the parameters that make us who we are and provides the tools we need to secure the integrity of that identity. In our culture of constant connectivity, an increasing reliance on biometrically secured mobile devices is transforming them into a target for bad actors. While no system will ever prevent all forms of intrusion, even state

In this paper, we propose a Motion Saliency based multi-stream Multiplier ResNets (MSM-ResNets) for action recognition. The proposed MSM-ResNets model consists of three interactive streams: the appearance stream, motion stream and motion saliency stream. Similar to conventional two-stream CNNs models, the appearance stream and motion stream are responsible for capturing the appearance information and

In the last few years, squared fiducial markers have become a popular and efficient tool to solve monocular localization and tracking problems at a very low cost. Nevertheless, marker detection is affected by noise and blur: small camera movements may cause image blurriness that prevents marker detection. The contribution of this paper is two-fold. First, it proposes a novel approach for estimating

Recognizing artworks in a cultural site using images acquired from the user's point of view (First Person Vision) allows to build interesting applications for both the visitors and the site managers. However, current object detection algorithms working in fully supervised settings need to be trained with large quantities of labeled data, whose collection requires a lot of times and high costs in order

Clothing compatibility learning has gained increasing research attention due to the fact that a properly coordinated outfit can represent personality and improve an individual's appearance greatly. In this paper, we propose a Compatibility Matrix-Regularized Generative Adversarial Network (CMRGAN) for compatible item generation. In particular, we utilize a multi-modal embedding to transform the image

This paper presents an accurate non-iterative method for the Perspective-n-Point problem(PnP). Our main idea is to mitigate scale bias by multiplying an independent inverse average depth variable onto the object space error. The introduced variable is of order 2 in the objective function and the optimality conditions constitute a polynomial system with three third-order and one first-order unknowns

Recently, plenty of deep learning methods have been proposed to handle point clouds. Almost all of them input the entire point cloud and ignore the information redundancy lying in point clouds. This paper addresses this problem by extracting the Reeb graph from point clouds, which is a much more informative and compact representation of point clouds, and then filter the graph with deep graph convolution

Human-Robot Interaction (HRI) provides assisted services in different real-time applications. The robotic systems identify objects through digital visualization wherein a three-dimensional (3D) image is converged to a plane-based projection. The projection is analyzed using the co-ordinates and identification points for recognizing the object. In such a converging process, the misidentification of

Face frontalization aims to normalize profile faces to frontal ones for pose-invariant face recognition. Current works have achieved promising results in face frontalization by using deep learning techniques. However, training deep models of face frontalization usually needs paired training data which is undoubtedly costly and time-consuming to acquire. To address this issue, we propose a Pose Conditional

Driven by business intelligence applications for rating attraction of products in shops, a new problem — salient object grading is studied in this paper. In computer vision, plenty of salient object detection approaches have been proposed, while most existing studies detect objects in a binary manner: salient or not. This paper focuses on a new problem setting that requires detecting all salient objects

An enormous amount of sensing devices (scalar or multimedia) collect and generate information (in the form of events) over the Internet of Things (IoT). Present research on IoT mainly focus on the processing of scalar sensor data events and barely considers the challenges posed by multimedia based events. In this paper, we systematically review the existing solutions available for the Internet of Multimedia

Perception systems, to a large extent, rely on neural networks. Commonly, the training of neural networks uses a finite amount of data. The usual assumption is that an appropriate training dataset is available, which covers all relevant domains. This abstract will follow the example of different lighting conditions in autonomous driving scenarios. In real-world datasets, a single source domain, such

Existing stereo matching networks based on deep learning lack multi-level and multi-module attention and integration for feature information. Therefore, we propose an attention-guided aggregation stereo matching network to encode and integrate information multiple times. Specifically, we design a residual network based on the 2D channel attention block to adaptively calibrate weight response, improving

Although refinement is commonly used in visual tasks to improve pre-obtained results, it has not been studied for Multiple Object Tracking (MOT) tasks. This could be attributed to two reasons: i) it has not been explored what kinds of errors should — and could — be reduced in MOT refinement; ii) the refinement target, namely, the tracklets, are intertwined and interactive in a 3D spatio-temporal space

Video surveillance systems are popular and used in public places such as market places, shopping malls, hospitals, banks, streets, education institutions, city administrative offices, and smart cities to enhance the safety of public lives and assets. Most of the time, the timely and accurate detection of video anomalies is the main objective of security applications. The video anomalies such as anomalous

In the past few years, video-based person re-identification (Re-ID) have attracted growing research attention. The crucial problem for this task is how to learn robust video feature representation, which can weaken the influence of factors such as occlusion, illumination, and background etc. A great deal of previous works utilize spatio-temporal information to represent pedestrian video, but the correlations

Pedestrian detection in images is a topic that has been studied extensively, but existing detectors designed for perspective images do not perform as successfully on images taken with top-view fisheye cameras, mainly due to the orientation variation of people in such images. In our proposed approach, several perspective views are generated from a fisheye image and then concatenated to form a composite

In view of the difficulty in training the algorithm of image oil painting style migration and reconstruction based on the generative adversarial network, and the loss gradient of generator and discriminator disappears, this paper proposes an improved generative adversarial network based on gradient penalty, and constructs the total variance loss function to carry out the research of image oil painting

Generalized zero-shot classification is predicting the labels of the test images coming from seen or unseen classes. The task is difficult because of the bias problem, that is, unseen samples are easily to be misclassified to seen classes. Many methods have handled the problem by training a generative adversarial network (GAN) to generate fake samples. However, the GAN model trained with seen samples

In order to study the application effect and function of industrial visual perception technology in smart city, the image processing and quality evaluation system was constructed by using convolutional neural network (CNN) and Internet of things (IoT) technology. The system was simulated, and then the quality performance of image and video obtained by using industrial visual perception technology was

Vehicle re-identification is an important part of intelligent transportation. Although much work has been done on this subject in recent years, vehicle re-identification is still a challenging task due to its obvious illumination change, high similarity between inter-class and great changes under different views. As discriminatory local areas and vehicle view information is the key to improving the

Human-robot interaction (HRI) is a multidisciplinary area that consists of several technologies that are used to create various smart city applications. The knowledge gain and analysis of the smart city environment improves response time. This paper introduces the dependable information processing (DIP) method for handling multi-attribute environmental information in a smart city application. Information

Deep learning-based object detection solutions emerged from computer vision has captivated full attention in recent years. The growing UAV market trends and interest in potential applications such as surveillance, visual navigation, object detection, and sensors-based obstacle avoidance planning have been holding good promises in the area of deep learning. Object detection algorithms implemented in

With the widespread use of mobile devices, iris recognition systems encounter more challenges, such as the vulnerability of Presentation Attack Detection (PAD). Recent works pointed out the contact lens attacks, especially images captured under the uncontrolled environment, as a hard task for iris PAD. In this paper, we propose a novel framework for detecting iris presentation attacks that especially

Multimodal image fusion aims to generate a fused image from different signals that captured by multimodal sensors. Although the images obtained by multimodal sensors have different appearances, the information included in these images might be redundant and noisy. In the previous studies, the fusion rule and their properties that guiding how to merge the features from multiple images is relatively

Vehicle model recognition (VMR) is a typical fine-grained classification task in computer vision. To improve the representation power of classical CNN networks for this special task, we focus on enhancing the subtle difference of features and their spatial encoding based on the attention mechanism, and then propose a novel architectural unit, which we term the “convolutional attention model” (CAM)

The limited capacity to recognize micro-expressions with subtle and rapid motion changes is a long-standing problem that presents a unique challenge for expression recognition systems and even for humans. The problem regarding micro-expression is less covered by research when compared to macro-expression. Nevertheless, micro-expression recognition (MER) is imperative to exploit the full potential of

In this paper, we propose an infrared and visible image fusion framework based on the consensus problem. Most current infrared and visible image fusion models aim to transfer only one characteristic of each source domain to the final fusion result. This mechanism limits the performances of fusion algorithms under different conditions. We present a general fusion framework based to solve the global

Recent advances in deep learning have shown excellent performance in various scene understanding tasks. However, in some complex environments or under challenging conditions, it is necessary to employ multiple modalities that provide complementary information on the same scene. A variety of studies have demonstrated that deep multimodal fusion for semantic image segmentation achieves significant performance

The application of computer vision (CV) in healthcare applications is familiar with the wireless and communication technology. CV methods are incorporated in the healthcare for providing programmed interactions towards patient monitoring. The requirements of systems are the analysis and detection of the images' visualization of patients. In this paper, a multi-modal visualization analysis (MMVA) method

Today, with the rapid development of science and technology, the era of big data has been proposed and triggered reforms in all walks of life. Face recognition is a biometric recognition method with the characteristics of non-contact, non mandatory, friendly and harmonious, which has a good application prospect in the fields of national security and social security. With the deepening of the research

Although many studies have investigated markerless motion capture, the technology has not been applied to real sports or concerts. In this paper, we propose a markerless motion capture method with spatiotemporal accuracy and smoothness from multiple cameras in wide-space and multi-person environments. The proposed method predicts each person's 3D pose and determines the bounding box of multi-camera

Crowd counting is an important surveillance application and receives significant attention from the computer vision community. Most of the current methods treat crowd counting by density map estimation and use the Fully Convolution Network (FCN) for prediction. The mainstream framework is to predict density maps and use the sum up the density maps to get the number of people. In such methods, the main

The detection of objects with multi-orientations and multi-scales in aerial images is receiving increasing attention because of numerous useful applications in computer vision, image understanding, satellite remote sensing and surveillance. However, such detection can be exceedingly challenging because of a birds eye view, multi-scale rotating objects with large aspect ratios, dense distributions and