State-of-the-art object detection approaches are often composed of two stages, namely, proposing a number of regions on an image and classifying each of them into one class. Both stages share a network backbone which builds visual features in a bottom-up manner. In this paper, we advocate the importance of equipping two-stage detectors with top-down signals, in order to which provides high-level contextual

Four-dimensional computed tomography (4D-CT) has been widely used in preoperative evaluation and radiotherapy planning of lung tumors. To reduce the damage to healthy tissue, the scan time and the number of CT slices are limited, which leads to the reduction of CT image resolution in the superior-inferior direction. To improve the resolution of the 4D-CT image, we propose a super-resolution (SR) algorithm

Neuro-fuzzy models have been applied in various domains, in which the issue of long time-consumption for optimizing parameters and less innovation in fuzzy method for feature extraction remains to be solved. Here, we present a novel cycle reinforce hierarchical model (CRHM) for effective and efficient recognition. The innovative strategies of CRHM consist of the hierarchical structure, the groups of

Object recognition from live video streams comes with numerous challenges such as the variation in illumination conditions and poses. Convolutional neural networks (CNNs) have been widely used to perform intelligent visual object recognition. Yet, CNNs still suffer from severe accuracy degradation, particularly on illumination-variant datasets. To address this problem, we propose a new CNN method based

One of the most important problems in regression-based error model is modeling the complex representation error caused by various corruptions and environment changes in images. For example, in robust face recognition, images are often affected by varying types and levels of corruptions, such as random pixel corruptions, block occlusions, or disguises. However, existing works are not robust enough to

Deep learning techniques have shown their superior performance in dermatologist clinical inspection. Nevertheless, melanoma diagnosis is still a challenging task due to the difficulty of incorporating the useful dermatologist clinical knowledge into the learning process. In this paper, we propose a novel knowledge-aware deep framework that incorporates some clinical knowledge into collaborative learning

Spatial information is often used to enhance the robustness of traditional fuzzy c-means (FCM) clustering algorithms. Although some recently emerged improvements are remarkable, the computational complexity of these algorithms is high, which may lead to lack of practicability. To address this problem, an efficient variant named the fuzzy clustering algorithm with variable multi-pixel fitting spatial

Most video analytics applications rely on object detectors to localize objects in frames. However, when real-time is a requirement, running the detector at all the frames is usually not possible. This is somewhat circumvented by instantiating visual object trackers between detector calls, but this does not scale with the number of objects. To tackle this problem, we present SiamMT, a new deep learning

Most existing approaches for single image super-resolution (SISR) resort to quality low-high resolution (LR-HR) pairs and available degradation kernels to train networks for a specific task in hand in a fully supervised manner. Labeled data used for training are, however, usually limited in terms of the quantity and the diversity degradation kernels. The learned SR networks with one degradation kernel

We present a novel learning-based approach to graph representations of road networks employing state-of-the-art graph convolutional neural networks. Our approach is applied to realistic road networks of 17 cities from Open Street Map. While edge features are crucial to generate descriptive graph representations of road networks, graph convolutional networks usually rely on node features only. We show

The bimodal ultrasound, namely B-mode ultrasound (BUS) and elastography ultrasound (EUS), provide complementary information to improve the diagnostic accuracy of breast cancers. However, in clinical practice, it is easier to acquire the labeled BUS images than the paired bimodal ultrasound data with shared labels due to the lack of EUS devices, especially in many rural hospitals. Thus, the single-modal

Deep neural network models owe their representational power and high performance in classification tasks to the high number of learnable parameters. Running deep neural network models in limited resource environments is a problematic task. Models employing conditional computing aim to reduce the computational burden while retaining model performance on par with more complex neural network models. In

Human action recognition in visual data is one of the most fundamental challenges in computer vision. Existing approaches for this primary goal have been based on video data, often incorporating both color and dynamic flow information. Nevertheless, the majority of the visual data constitute still images, and for this reason, being able to recognize actions in still image is an ultimate objective of

Video based visual question answering (V-VQA) remains challenging at the intersection of vision and language. In this paper, we propose a novel architecture, namely Generalized Pyramid Co-attention with Learnable Aggregation Net (GPC) to address two central problems: 1) how to deploy co-attention to V-VQA task considering the complex and diverse content of videos; and 2) how to aggregate the frame-level

In the online innovation market, the fund-raising performance of the start-up project is a concerning issue for creators, investors and platforms. Unfortunately, existing studies always focus on modeling the fund-raising process after the publishment of a project but the predicting of a project attraction in the market before setting up is largely unexploited. Usually, this prediction is always with

Temporal feature extraction is an essential technique in video-based action recognition. Key points have been utilized in skeleton-based action recognition methods but they require costly key point annotation. In this paper, we propose a novel temporal feature extraction module, named Key Point Shifts Embedding Module (KPSEM), to adaptively extract channel-wise key point shifts across video frames

Many embedded feature selection methods ignore the correlation among the important features. To reduce correlation, some models introduce constraints to impose sparsity on features, some try to exploit the similarity and group features without changing the objective function. In this paper, we propose diverse feature selection (DFS), which simultaneously performs feature clustering and selection. Given

The emergence of geometric deep learning as a novel framework to deal with graph-based representations has faded away traditional approaches in favor of completely new methodologies. In this paper, we propose a new framework able to combine the advances on deep metric learning with traditional approximations of the graph edit distance. Hence, we propose an efficient graph distance based on the novel

kNN is a widely used machine learning algorithm in many different domains because of its fairly good performance in actual cases and its simplicity. This study aims to enhance the performance of kNN for imbalanced datasets, a topic that has been relatively ignored in kNN research. The proposed kNN algorithm, called normalized class coherence change-based k-nearest neighbor (NCC-NN) algorithm, determines

In this paper, a progressive global perception and local polishing (PCPLP) network is proposed to automatically segment the COVID-19-caused pneumonia infections in computed tomography (CT) images. The proposed PCPLP follows an encoder-decoder architecture. Particularly, the encoder is implemented as a computationally efficient fully convolutional network (FCN). In this study, a multi-scale multi-level

Watershed clustering utilizes the concept of watershed algorithm to process clustering or cluster analysis. The most attractive characteristic of this method is the capability to determine automatically the number of clusters from the data sets. However, in terms of the literature, the purposes of the original watershed clustering algorithm and the improved version are the detection of the clusters

In this paper we extend the setting of the online prediction with expert advice to function-valued forecasts. At each step of the online game several experts predict a function, and the learner has to efficiently aggregate these functional forecasts into a single forecast. We adapt basic mixable (and exponentially concave) loss functions to compare functional predictions and prove that these adaptations

Research on Coronavirus Disease 2019 (COVID-19) detection methods has increased in the last months as more accurate automated toolkits are required. Recent studies show that CT scan images contain useful information to detect the COVID-19 disease. However, the scarcity of large and well balanced datasets limits the possibility of using detection approaches in real diagnostic contexts as they are unable

Head-mounted device-based human-computer interaction often requires egocentric recognition of hand gestures and fingertips detection. In this paper, a unified approach of egocentric hand gesture recognition and fingertip detection is introduced. The proposed algorithm uses a single convolutional neural network to predict the probabilities of finger class and positions of fingertips in one forward propagation

Multi-view subspace clustering algorithms have recently been developed to process multi-view dataset clustering by accurately depicting the essential characteristics of multi-view data. Most existing methods focus on conduct self-representation property using a consistent representation and a set of specific representations with well-designed regularization to learn the common and specific knowledge

The search cost of neural architecture search (NAS) has been largely reduced by differentiable architecture search and weight-sharing methods. Such methods optimize a super-network with all possible edges and operations, and determine the optimal sub-network by discretization, i.e., pruning off operations/edges of small weights. However, the discretization process performed on either operations or

Graph embedding is an effective method for deriving low-dimensional representations of graph data. The power of graph deep learning methods to characterize electroencephalogram (EEG) graph embedding is still in question. We designed a novel graph variational auto-encoder (GVAE) method to extract nodal features of brain functional connections. A new decoder model for the GVAEs network is proposed, which

The current ML approaches do not fully focus to answer a still unresolved and topical challenge, namely the prediction of priorities of COVID-19 vaccine administration. Thus, our task includes some additional methodological challenges mainly related to avoiding unwanted bias while handling categorical and ordinal data with a highly imbalanced nature. Hence, the main contribution of this study is to

Twin support vector machine (TWSVM) is an efficient algorithm for binary classification. However, the lack of the structural risk minimization principle restrains the generalization of TWSVM and the guarantee of convex optimization constraints TWSVM to only use positive semi-definite kernels (PSD). In this paper, we propose a novel TWSVM for indefinite kernel called indefinite twin support vector machine

With the outbreak and wide spread of novel coronavirus (COVID-19), contactless fingerprint recognition has attracted more attention for personal recognition because it can provide significantly higher user convenience and hygiene than the traditional contact-based fingerprint recognition. However, it is still challenging to achieve a highly accurate recognition due to the low ridge-valley contrast

Time series forecasting involves collecting and analyzing past observations to develop a model to extrapolate such observations into the future. Forecasting of future events is important in many fields to support decision making as it contributes to reducing the future uncertainty. We propose explainable boosted linear regression (EBLR) algorithm for time series forecasting, which is an iterative method

In the field of robotics, due to the complexity of real environments, place recognition using the 3D LiDAR is always a challenging problem. The spatial relations of internal structures underlying the LiDAR data from different places are distinguishable, which can be used to describe the environment. In this paper, we utilize the spatial relations of internal structures and propose a two-level framework

Nowadays, multi-label learning is ubiquitous in practical applications, in which multi-label data is always confronted with the curse of high-dimensional features. Feature selection has been shown to effectively improve learning performance by selecting discriminative features. Conventional multi-label feature selection only focuses on associating input features with corresponding labels while neglecting

This paper reports a new method (simplified as AE-ELM-SynMin) to create the Synthetic Minority class samples for imbalanced classification based on AutoEncoder Extreme Learning Machine (AE-ELM). AE-ELM-SynMin first trains an AE-ELM which is a special ELM with the same input and output, i.e., the original minority class samples. Second, the crossover, mutation and filtration operations are conducted

The lack of interpretability is an inevitable problem when using neural network models in real applications. In this paper, an explainable neural network based on generalized additive models with structured interactions (GAMI-Net) is proposed to pursue a good balance between prediction accuracy and model interpretability. GAMI-Net is a disentangled feedforward network with multiple additive subnetworks;

In this paper, a knowledge base graph embedding module is constructed to extend the versatility of knowledge-based VQA (Visual Question Answering) models. The knowledge base graph embedding module constructed in this paper extracts core entities from images and text, and maps them as knowledge base entities, then extracts the sub-graphs closely related to the core entities, and converts the sub-graphs

Feature selection is able to select more discriminative features for classification and plays an important role in multi-label learning to alleviate the effect of the curse of dimensionality. Recently, the multi-label feature selection methods based on the sparse regression model have received increasing attentions. However, most of these methods directly project original data space to label space

One of the successful approaches in semi-supervised learning is based on the consistency regularization. Typically, a student model is trained to be consistent with teacher prediction for the inputs under different perturbations. To be successful, the prediction targets given by teacher should have good quality, otherwise the student can be misled by teacher. Unfortunately, existing methods do not

Forecasting models that are trained across sets of many time series, known as Global Forecasting Models (GFM), have shown recently promising results in forecasting competitions and real-world applications, outperforming many state-of-the-art univariate forecasting techniques. In most cases, GFMs are implemented using deep neural networks, and in particular Recurrent Neural Networks (RNN), which require

Accurate segmentation of corneal layers depicted on optical coherence tomography (OCT) images is very helpful for quantitatively assessing and diagnosing corneal diseases (e.g., keratoconus and dry eye). In this study, we presented a novel boundary-guided convolutional neural network (CNN) architecture (BG-CNN) to simultaneously extract different corneal layers and delineate their boundaries. The developed

Squeeze-and-Excitation (SE) blocks have demonstrated significant accuracy gains for state-of-the-art deep architectures by re-weighting channel-wise feature responses. The SE block is an architecture unit that integrates two operations: a squeeze operation that employs global average pooling to aggregate spatial convolutional features into a channel feature, and an excitation operation that learns

Recently, graph convolutional networks (GCNs) have been employed for graph matching problem. It can integrate graph node feature embedding, node-wise affinity learning and matching optimization together in a unified end-to-end model. However, first, the matching graphs feeding to existing graph matching networks are generally fixed and independent of graph matching task, which thus are not guaranteed

Lifelong machine learning can learn a sequence of consecutive robotic perception tasks via transferring previous experiences. However, 1) most existing lifelong learning based perception methods only take advantage of visual information for robotic tasks, while neglecting another important tactile sensing modality to capture discriminative material properties; 2) Meanwhile, they cannot explore the

In this paper, we propose a general framework in continual learning for generative models: Feature-oriented Continual Learning (FoCL). Unlike previous works that aim to solve the catastrophic forgetting problem by introducing regularization in the parameter space or image space, FoCL imposes regularization in the feature space. We show in our experiments that FoCL has faster adaptation to distributional

Recently, part-based deep models have achieved promising performance in person re-identification (Re-ID), yet these models ignore the inter-local relationship of the corresponding parts among pedestrian images and the intra-local relationship between adjacent parts in one pedestrian image. As a result, the feature representations are hard to learn the information from the same parts of other pedestrian

Diabetic retinopathy (DR) detection has attracted much attention recently, and the deep learning algorithms have gained traction in this area. At present, DR screening by deep learning algorithms is often based on single-view fundus images, which usually leads to an unsatisfactory accuracy of DR grading due to the incomplete lesion features. In this paper, we proposed a novel diabetic retinopathy detection

We explore a new video segmentation task, named portrait video segmentation (PVS), which aims to automatically segment the dominant person throughout a given portrait video. To achieve accurate and temporal-coherent segmentation results, a feature reconstruction based PVS method is developed under the meta-learning framework. Due to the dramatic pose variation and severe occlusion in portrait videos

Weakly-supervised object detection attempts to limit the amount of supervision by dispensing the need for bounding boxes, but still assumes image-level labels on the entire training set. In this work, we study the problem of training an object detector from one or few images with image-level labels and a larger set of completely unlabeled images. This is an extreme case of semi-supervised learning

As the Internet confronts the multimedia explosion, it becomes urgent to investigate personalized recommendation for alleviating information overload and improving users’ experience. Most personalized recommendation approaches pay their attention to collaborative filtering over users’ interactions, which suffers greatly from the highly sparse interactions. In image recommendation, visual correlations

In the Internet of Things enabled intelligent transportation systems, a huge amount of vehicle video data has been generated and real-time and accurate video analysis are very important and challenging work, especially in situations with complex street scenes. Therefore, we propose edge computing based video pre-processing to eliminate the redundant frames, so that we migrate the partial or all the

Monocular depth estimation has been gaining growing momentum in recent years. Despite significant advances of this task, due to the inherent difficulty of reliably capturing contextual cues from RGB images, it remains challenging to accurately predict depth in scenes with complicated and cluttered spatial arrangement of objects. Instead of naively utilizing the primary features in the single RGB image

Biometrics technology is one of the most important and effective solutions for personal authentication. In recent years, as one of the emerging biometrics technologies, dorsal hand vein (DHV) biometrics has received a lot of attention. In fact, DHV biometrics has been studied for more than 30 years, during which different problems related to DHV recognition have been addressed. In this paper, we conduct

Multi-label feature selection is an efficient technique to alleviate the high dimensionality for multi-label learning. Existing multi-label feature selection methods based on information theory either deal with labels individually or treat all label relationships as redundancy. However, two important and being ignored issues are the different effects of label relationships and the dynamic changes of

In many practical credit evaluation problems, a lot of manpower as well as financial and material resources are required to label samples. Therefore, in the process of labeling, only a small number of samples with category labels can be obtained to train classification models and a large number of customer samples is abandoned without category labels. To solve this problem, we introduce a semi-supervised

Human trajectory prediction is an important topic in several application domains, ranging from self-driving cars to environment design and planning, from socially-aware robots to intelligent tracking systems. This complex subject comes with different challenges, such as human-space interaction, human-human interaction, multimodality, and generalizability. Currently, these challenges, especially generalizability

Video object segmentation is one of the most practical computer vision tasks, especially in the unsupervised case, which has no manually labeled segmentation mask at the beginning of a video sequence. In this paper, we propose a new real-time unsupervised video object segmentation network. Based on the encoder-decoder framework, we present a Dynamic ASPP module and a RNN-Conv module. The former adds