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

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

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

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,

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

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 illumination, weather conditions and angles of view, most traditional road marking detection methods use fixed threshold

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 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

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

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

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

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

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

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

Zero-shot learning (ZSL) has received increasing attention in recent years especially in areas of fine-grained object recognition, retrieval, and image captioning. The key to ZSL is to transfer knowledge from the seen to the unseen classes via auxiliary class attribute vectors. However, the popularly learned projection functions in previous works cannot generalize well since they assume the distribution

Convolutional neural networks (CNNs) have been the source of recent breakthroughs in many vision tasks. Feature pooling layers are being widely used in CNNs to reduce the spatial dimensions of the feature maps of the hidden layers. This gives CNNs the property of spatial invariance and also results in speed-up and reduces over-fitting. However, this also causes significant information loss. All existing

We propose visual variation learning to improve object recognition with convolutional neural networks (CNN). While a typical CNN regards visual variations as nuisances and marginalizes them from the data, we speculate that some variations are informative. We study the impact of visual variation as an auxiliary task, during training only, on classification and similarity embedding problems. To train

This work introduces a high-efficiency approach for face recognition applications based on features using a recent algorithm called Floor of Log (FoL). The advantage of this method is the reduction of storage and energy, maintaining accuracy. K-Nearest Neighbors and Support Vector Machine algorithm was applied to learn the better parameter of the FoL algorithm using cross-validation. Accuracy and the

In this paper, we address a problem of correcting upright orientation of a reconstructed object to search. We first reconstruct an input object appearing in an image sequence, and generate a query shape using multi-view object co-segmentation. In the next phase, we utilize the Convolutional Neural Network (CNN) architecture to determine category-specific upright orientation of the queried shape for

Object pose recovery has gained increasing attention in the computer vision field as it has become an important problem in rapidly evolving technological areas related to autonomous driving, robotics, and augmented reality. Existing review-related studies have addressed the problem at visual level in 2D, going through the methods which produce 2D bounding boxes of objects of interest in RGB images

While the problem of estimating shapes and diffuse reflectances of human faces from images has been extensively studied, there is relatively less work done on recovering the specular albedo. This paper presents a lightweight solution for inferring photorealistic facial reflectance and geometry. Our system processes video streams from two views of a subject, and outputs two reflectance maps for diffuse

In this paper, we explore illustrations in children's books as a new domain in unpaired image-to-image translation. We show that although the current state-of-the-art image-to-image translation models successfully transfer either the style or the content, they fail to transfer both at the same time. We propose a new generator network to address this issue and show that the resulting network strikes

Image alignment is a crucial step to generate a high quality panorama. The state-of-the-art approaches use local-adaptive transformations to deal with multi-view parallax, but still suffer from unreliable feature correspondences and high computational cost. In this paper, we propose a local-adaptive and outlier-tolerant image alignment method using RBF (radial basis function) approximation. To eliminate

Existing advanced saliency systems have been proposed using Convolutional Neural Networks (CNNs), the prior knowledge of objectness is crucial for saliency detection. However, we show that the use of objectness may also limit the power of CNNs on the images which do not contain a salient object. Besides, one previous study has shown applying a deeper CNN model may not improve the performance, the reason

Most of the deep convolutional neural networks (CNNs) based RGBD saliency models either regard the RGB and depth cues as the same status or trust the depth information excessively. However, they ignore that the low-quality depth map is an interference factor and the multi-level deep features originated from RGB images contain abundant appearance information. Therefore, we propose a novel RGBD saliency

This paper proposes a complementary regression network (CRN) that combines global and local regression methods to align faces. A global regression network (GRN) generates the coordinates of facial landmark points directly such that all facial feature points are fitted to the input face on the whole and a local regression network (LRN) generates the heatmap of facial landmark points such that each channel

This paper presents a Riemannian approach for free-space extraction and path planning using color catadioptric vision. The problem is formulated considering color catadioptric images as Riemannian manifolds and solved using the Riemannian Eikonal equation with an anisotropic fast marching numerical scheme. This formulation allows the integration of adapted color and spatial metrics in an incremental

The Convolutional Neural Networks(CNNs) with encoder-decoder architecture has shown powerful ability in semantic segmentation and it has also been applied in saliency detection. In most researches, the parameters of the backbone network which have been pre-trained on the ImageNet dataset will be retrained using the new training dataset to let CNNs adapt to the new task better. But the retraining will

In the person re-identification (re-ID) community, pedestrians often have great changes in appearance, and there are many similar persons, which incurs will degrades the accuracy. Re-ranking is an effective method to solve these problems, this paper proposes an expanded neighborhoods distance (END) to re-rank the re-ID results. We assume that if the two persons in different image are same, their initial

Light field imaging has recently become a promising technology for 3D rendering and displaying. However, capturing real-world light field images still faces many challenges in both the quantity and quality. In this paper, we develop a learning based technique to reconstruct light field from a single 2D RGB image. It includes three steps: unsupervised monocular depth estimation, view synthesis and depth-guided

Single-object tracking is a significant and challenging computer vision problem. Recently, discriminative correlation filters (DCF) have shown excellent performance. But there is a theoretical defects that the boundary effect, caused by the periodic assumption of training samples, greatly limit the tracking performance. Spatially regularized DCF (SRDCF) introduces a spatial regularization to penalize

Collective activity recognition is an important subtask of human action recognition, where the existing datasets are mostly limited. In this paper, we look into this issue and introduce the “Collective Sports (C-Sports)” dataset, which is a novel benchmark dataset for multi-task recognition of both collective activity and sports categories. Various state-of-the-art techniques are evaluated on this