Biometric feature based human authentication systems provide various advantages over the classical authentication systems. Out of numerous biometric features in a human body, the fingerprint is the most commonly used biometric feature for the authentication of a person. Typically, the fingerprint-based systems rely on minutiae points information and use it directly as a user template. Several studies

Face verification performance by human brain has been shown to be much better than most of the state-of-the-art approaches in computer vision. Performance improvement of automated face recognition (FR) systems that may equal or surpass the human intellect is the key goal of this research. We present our face verification system using facial mark (FM) combined with deep convolutional neural network

Augmented and virtual reality deployment is finding increasing use in novel applications. Some of these emerging and foreseen applications allow the users to access sensitive information and functionalities. Head Mounted Displays (HMD) are used to enable such applications and they typically include eye facing cameras to facilitate advanced user interaction. Such integrated cameras capture iris and

Generative adversarial networks (GANs) have been enjoying considerable success in recent years. However, mode collapse remains a major unsolved problem in training GANs and is one of the main obstacles hindering progress. In this paper, we present spectral regularization for GANs (SR-GANs), a new and robust method for combating the mode collapse problem in GANs. We first perform theoretical analysis

Periocular region is considered as an important biometric trait due to its ease of collectability and high acceptability in our society. Recent advancements in surveillance applications require infra-red (IR) sensing equipments to be deployed in order to capture the activities occurring in low-light conditions. This gives rise to the problem of matching periocular images in heterogeneous environments

We propose a novel framework for cross-modal zero-shot learning (ZSL) in the context of sketch-based image retrieval (SBIR). Conventionally, the SBIR schema mainly considers simultaneous mappings among the two image views and the semantic side information. Therefore, it is desirable to consider fine-grained classes mainly in the sketch domain using highly discriminative and semantically rich feature

A few-shot learning model generally consists of a feature extraction network and a classification module. In this paper, we propose an approach to improve few-shot image classification performance by increasing the representational capacity of the feature extraction network and improving the quality of the features extracted by it. The ability of the feature extraction network to extract highly discriminative

Capturing long-range dependencies has proven effective on video understanding tasks. However, previous works address this problem in a pixel pairs manner, which might be inaccurate since pixel pairs contain too limited semantic information. Besides, considerable computations and parameters will be introduced in those methods. Following the pattern of features aggregation in Graph Convolutional Networks

Existing efforts of saliency detection have achieved excellent performance in RGB images, thus to sufficiently exploit existing RGB saliency models and further do some extensions on them, we can transfer existing RGB saliency models to the similar research field, i.e. RGBD saliency detection, by introducing depth cues. Here, we construct a novel RGBD saliency model upon an existing RGB saliency model

Most existing approaches prune wrong matches via estimating an image transformation or solving a graph-based global matching optimization problem, which usually suffers from varying local transformations and outliers. Inspired by the insight that neighboring true matches usually hold consistent local topological structures across images, in this paper we propose a new approach to evaluate the confidence

In order to study and predict the freeway traffic safety and realize the traffic flow in the nonlinear big data environment, based on deep learning, the long-short-time memory (LSTM) model based on recurrent neural network is proposed. The traffic flow is predicted and the predicted value of traffic flow is compared with the actual value at different times. The mean absolute percentage error of LSTM

As the AI (artificial intelligence) develops, driverless vehicle technology is widely concerned, and the important problem that needs to be solved in driverless technology is the detection of pedestrians in the panoramic vision of the vehicle, so the pedestrian detection technology of panoramic vision is explored based on the deep learning. Recently, anchor-free and one-stage detectors have been introduced

The unsupervised person re-identification (re-ID) has become increasingly significant in the community because it is more scalable than the supervised method when dealing with the large-scale person re-ID. However, it is difficult to learn discriminative enough features from across-camera images without labelling information. To address this problem, we propose a joint patch and instance discrimination

There has been a continued interest in learning features that are generalizable across sensors and spectra for ocular biometrics. This is usually facilitated through a model that can learn features that are robust across pose, lighting conditions, spectra, and device sensor variations. In this paper, we propose an efficient deep learning-based feature extraction pipeline for learning the aforementioned

In order to solve the damage caused by the concrete structure, which leads to the reduction of the life of infrastructure, endangers the safety of pedestrians, and has a serious impact on the social economy, building crack detection model of FCN (Fully Convolutional Networks), R-CNN (Regions with CNN feature) and RFCN (Richer Fully Convolutional Networks) has been proposed based on the convolutional

Deep learning-based methods have pushed the limits of the state-of-the-art in face analysis. However, despite their success, these models have raised concerns regarding their bias towards certain demographics. This bias is inflicted both by limited diversity across demographics in the training set, as well as the design of the algorithms. In this work, we investigate the demographic bias of deep learning

Pyramid Convolutional Attention Network is proposed to efficiently capture long-range dependency and fuse features from different levels for benefitting semantic segmentation problems. In this paper, we focus on how to extract more representative features for segmentation object recognition and design a decoder to recover details in a more efficient way. Inspired by atrous sampling and attention mechanism

Current Visual Question Answering (VQA) systems can answer intelligent questions about ‘known’ visual content. However, their performance drops significantly when questions about visually and linguistically ‘unknown’ concepts are presented during inference (‘Open-world’ scenario). A practical VQA system should be able to deal with novel concepts in real world settings. To address this problem, we propose

Online multi-object tracking (MOT) is a fundamental problem in video analysis and multimedia applications. The major challenge in the popular tracking-by-detection framework is knowing how to associate candidate detections results with existing tracklets. In this, we propose a non-local attention association approach and apply it to a unified online MOT framework that integrates the merits of single

Domain adaptation has become a resounding success in learning a domain agnostic model that performs well on target dataset by leveraging source dataset which has related data distribution. Most of existing works aim at learning domain-invariant features across different domains, but they ignore the discriminability of learned features although it is import to improve the model's performance. This paper

To study the conservation of architectural heritage, computer algorithms are used to process the artificial field measurements and reference data maps. A 3D virtual model of traditional architecture is constructed for the direct learning and feature extraction from image data through deep learning. A set of tools and processes for pixel-level image processing labeling are proposed, and a label quality

Evacuation behavior is an important factor which must be considered in the design of public structures. With the continuous complexity of structure, more and more factors should be considered in evacuation. The traditional design based on experience may have some limitations in practice. Based on the deep neural network model, the evacuation design simulation for subway station buildings is implemented

An area of biometrics that has recently attracted much attention is gender and age classification. Its applications can be found not only in the fields of security and surveillance, but also in the context of marketing and demographic information gathering. In addition, extracting this information from a biometric sample can help to decrease the time to identify the exact individual. In this paper

The automatic characterization of pedestrians in surveillance footage is a tough challenge, particularly when the data is extremely diverse with cluttered backgrounds, and subjects are captured from varying distances, under multiple poses, with partial occlusion. Having observed that the state-of-the-art performance is still unsatisfactory, this paper provides a novel solution to the problem, with

In recent years, Autonomous Driving Systems (ADS) become more and more popular and reliable. Road markings are important for drivers and advanced driver assistance systems by better understanding the road environment. While the detection of road markings may suffer a lot from various illuminations, weather conditions and angles of view, most traditional road marking detection methods use fixed threshold

Face landmarking, defined as the detection of fiducial points on faces, has received a lot of attention over the last two decades within the computer vision community. While research literature documents major advances using state-of-art deep convolutional neural networks, earlier cascaded regression tree-based approaches remain a relevant alternative for low-cost, low-power embedded systems. Yet,

The periocular region is used for authentication in the recent days under unconstrained acquisition in biometrics. This work presents two new feature extraction techniques to achieve robust and blur invariant biometric verification using periocular images captured using smartphones - (1) Deep Sparse Features (DSF) and (2) Deep Sparse Time Frequency Features (DeSTiFF). Both the approaches are based

Facial recognition for surveillance applications still remains challenging in uncontrolled environments, especially with the appearances of masks/veils and different ethnicities effects. Multimodal facial biometrics recognition becomes one of the major studies to overcome such scenarios. However, to cooperate with multimodal facial biometrics, many existing deep learning networks rely on feature concatenation

The correlation between images is crucial for solving the image co-segmentation problem that is segmenting common and salient objects from a set of related images. This paper proposes a novel co-attention computation block to compute the visual correlation between images for improving the co-segmentation performance. Here ‘co-attention’ means that we obtain the co-attention features in encoded features

Multiple object tracking is an important but challenging computer vision problem. The complex motion of objects makes tracking difficult during long periods of object occlusion, and as a result occlusions frequently cause fragmented tracks with gaps. Previous works use linear interpolation to fill in such gaps, a technique which is only able to model simple motion. As a result, tracked bounding box

In RGBD saliency detection research field, RGB and depth cues are generally given the same status by RGBD saliency models. However, they ignore that both modalities are significantly different in inherent attribution so that effective features cannot be drawn from depth maps. In order to address this issue, this paper proposes a novel RGBD saliency model including two key components: the contrast-guided

Person Search (PS) has become a major field because of its need in community and in the field of research among researchers. This task aims to find a probe person from whole scene which shows great significance in video surveillance field to track lost people, re-identification, and verification of person. In last few years, deep learning has played unremarkable role for the solution of re-identification

Constructing high-quality panorama is a fundamental task in both computer vision and computer graphics communities, thus, leading to many image stitching approaches for panorama construction. However, panorama constructed by traditional image stitching has a limited angle of view and has an expensively computational cost. To defend the issues, in this paper, we proposed to use video sequence as input

The success of handheld video capturing devices has further fueled the need of improved video stabilization. The videos often contain many foreground facial features like eyes, nose etc. These foreground features can be considered as feature points and may be used to stabilize videos. This paper proposes an innovative and effective digital video stabilization technique, which utilizes foreground features

In this work, we focus on the Visual Question Answering (VQA) task, where a model must answer a question based on an image, and the VQA-Explanations task, where an explanation is produced to support the answer. We introduce an interpretable model capable of pointing out and consuming information from a novel Knowledge Base (KB) composed of real-world relationships between objects, along with labels

Person re-identification (re-ID) is highly complex in a diverse surveillance environment. The existing person re-ID methods are evaluated as a closed set problem with limited environmental variation. It is highly challenging to estimate the diverse poses of a dynamically crowded environment using the traditional unsupervised person re-ID methods. To resolve this issue of handling complex diverse poses

In recent years, accurate 3D detection plays an important role in a lot of applications. Autonomous driving, for instance, is one of typical representatives. This paper aims to design an accurate 3D detector that takes both Li-DAR point clouds and RGB images as inputs according to the fact that both LiDAR and camera have their own merits. A deep novel end-to-end two-stream learnable architecture, CrossFusion

In this work, we create two new video datasets for the task of temporal Cricket stroke extraction. The two datasets, namely, the Highlights dataset (with approx. 117K frames) and the Generic dataset (with approx. 1.93M frames), comprise of Cricket telecast videos collected from available online sources and down-sampled to 360×640 at 25FPS. These untrimmed videos have been manually annotated with temporal

Face aging is a task which referred to image synthesis, and the challenge comes from the training dataset, most existing face aging works require paired face images which is difficult to collect. Face images with various ages of the same person can be considered as unpaired images which come from different domains. The degree of aging effect can be influenced by age, gender, race and some other factors

Despite recent breakthroughs in the field, Visual Object Tracking remains an open and challenging task in Computer Vision. Modern applications require trackers to not only be accurate but also very fast, even on embedded systems. In this work, we use features from Convolutional Neural Networks to build histograms, which are more adept at handling appearance variations, in an end-to-end trainable architecture

Understanding the 3D space is crucial for autonomous vehicles for planning and navigation. Traditionally autonomous vehicles use LiDAR sensor to 3D map its environment. LiDAR sensor data are often noisy and sparse making it not fully reliable for real-time applications like autonomous driving, thus redundant such sensors are used for the purpose. The array of cameras in an autonomous vehicle purposed

The ability to sense the surrounding environment is an important developing technology in the field of automated vehicles. Lane line detection could determine a vehicle's travelable area. An embedded road boundary detection system based on deep learning was developed in this study. The system can detect structured and unstructured roads in a variety of situations. To obtain an image with clear lane

Research on human parsing methods has attracted increasing attention in a wide range of applications. However, dataset imbalance is still a challenging problem in this task, which directly affects the performance of human parsing. There are different types of dataset imbalance problems. For example, the numbers of samples for various labels in a dataset may differ, the scales of objects identified

Deep learning has been applied to fashion landmark detection in recent years, and great progress has been made. However, the detection of hard keypoints, such as those which are occluded or invisible, remains challenging and must be addressed. To tackle this problem, in the feature exaction level a novel Multi-Depth Dilated (MDD) block which is composed of different numbers of dilated convolutions

Recently, Siamese networks based trackers have shown excellent performance in accuracy and speed. However, previous studies treat all training samples equally and use the general feature space without adapting to the specific video during tracking. These trackers ignore the class data imbalance during training and the feature space difference between the generic domain and the current tracking target

Convolutional Neural Network models have reached extremely high performance on the Face Recognition task. Mostly used datasets, such as VGGFace2, focus on gender, pose, and age variations, in the attempt of balancing them to empower models to better generalize to unseen data. Nevertheless, image resolution variability is not usually discussed, which may lead to a resizing of 256 pixels. While specific

Recent works have demonstrated convolutional neural networks are vulnerable to adversarial examples, i.e., inputs to machine learning models that an attacker has intentionally designed to cause the models to make a mistake. To improve the adversarial robustness of neural networks, adversarial training has been proposed to train networks by injecting adversarial examples into the training data. However

This paper presents a new method for skin region segmentation based on a zero-sum game theory model which exploits the opposite classifications of an image region by different skin detectors. In fact, these regions are considered conflict areas between two players (skin and non-skin) and skin detectors are considered strategies. An appropriate utility function is then defined. The computation of the

Due to the high cost of data annotation in supervised person re-identification (re-ID) methods, unsupervised methods become more attractive in the real world. Recently, the hierarchical clustering serves as a promising unsupervised method. One key factor of hierarchical clustering is the distance measurement strategy. Ideally, a good distance measurement should consider both inter-cluster and intra-cluster

Monocular depth estimation plays a crucial role in understanding 3D scene geometry and is a challenging computer vision task. Recently, deep convolutional neural networks have been applied to solve this problem. However, existing methods either directly exploiting RGB pixels which can introduce much noise into the depth map or utilizing over smoothed internal representation features which can cause

Small object detection is a challenging problem in computer vision. It has been widely applied in defense military, transportation, industry, etc. To facilitate in-depth understanding of small object detection, we comprehensively review the existing small object detection methods based on deep learning from five aspects, including multi-scale feature learning, data augmentation, training strategy,

Single-stage object detectors have been widely applied in many computer vision applications due to their simpleness and high efficiency. However, the low correlation between the classification score and localization accuracy in detection results severely hurts the average precision of the detection model. To solve this problem, an IoU-aware single-stage object detector is proposed in this paper. Specifically

Image search can be tackled using deep features from pre-trained Convolutional Neural Networks (CNN). The feature map from the last convolutional layer of a CNN encodes descriptive information from which a discriminative global descriptor can be obtained. We propose a new representation of co-occurrences from deep convolutional features to extract additional relevant information from this last convolutional

This paper proposes a digital video intrusion detection method based on Narrow Band Internet of Things (NB-IoT), and establishes a digital video intrusion detection system based on NB-IoT network and SVM intelligent classification algorithm. Firstly, the image is preprocessed by gradation processing and threshold transformation to extract the HOG feature extraction of human intrusion behavior in digital

A novel similarity-covariant feature detector that extracts points whose neighborhoods, when treated as a 3D intensity surface, have a saddle-like intensity profile is presented. The saddle condition is verified efficiently by intensity comparisons on two concentric rings that must have exactly two dark-to-bright and two bright-to-dark transitions satisfying certain geometric constraints. Saddle is

We propose a novel convolutional neural network approach to address the fine-grained recognition problem of multi-view dynamic facial action unit detection. We leverage recent gains in large-scale object recognition by formulating the task of predicting the presence or absence of a specific action unit in a still image of a human face as holistic classification. We then explore the design space of