High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection. Existing state-of-the-art frameworks first encode the input image a low-resolution representation through subnetwork that is formed by connecting high-to-low resolution convolutions <i>in series</i> (e.g., ResNet, VGGNet), then recover high-resolution from encoded representation. Instead, our proposed network, named High-Resolution...

Full-image dependencies provide useful contextual information to benefit visual understanding problems. In this work, we propose a Criss-Cross Network (CCNet) for obtaining such in more effective and efficient way. Concretely, each pixel, novel criss-cross attention module CCNet harvests the of all pixels on its path. By taking further recurrent operation, pixel can finally capture full-image from pixels. Overall, is with following merits: 1) GPU memory friendly. Compared non-local block,...

This paper presents an end-to-end trainable fast scene text detector, named TextBoxes, which detects with both high accuracy and efficiency in a single network forward pass, involving no post-process except for standard non-maximum suppression. TextBoxes outperforms competing methods terms of localization is much faster, taking only 0.09s per image implementation. Furthermore, combined recognizer, significantly state-of-the-art approaches on word spotting recognition tasks.

With the increasing popularity of practical vision systems and smart phones, text detection in natural scenes becomes a critical yet challenging task. Most existing methods have focused on detecting horizontal or near-horizontal texts. In this paper, we propose system which detects texts arbitrary orientations images. Our algorithm is equipped with two-level classification scheme two sets features specially designed for capturing both intrinsic characteristics To better evaluate our compare...

Abstract Accurate and rapid diagnosis of COVID-19 suspected cases plays a crucial role in timely quarantine medical treatment. Developing deep learning-based model for automatic detection on chest CT is helpful to counter the outbreak SARS-CoV-2. A weakly-supervised software system was developed using 3D volumes detect COVID-19. For each patient, lung region segmented pre-trained UNet; then fed into neural network predict probability infectious. 499 collected from Dec. 13, 2019, Jan. 23,...

The pervasiveness of location-acquisition technologies (GPS, GSM networks, etc.) enable people to conveniently log the location histories they visited with spatio-temporal data. increasing availability large amounts data pertaining an individual's trajectories has given rise a variety geographic information systems, and also brings us opportunities challenges automatically discover valuable knowledge from these trajectories. In this paper, we move towards direction aim geographically mine...

Accurate and rapid diagnosis of COVID-19 suspected cases plays a crucial role in timely quarantine medical treatment. Developing deep learning-based model for automatic on chest CT is helpful to counter the outbreak SARS-CoV-2. A weakly-supervised learning framework was developed using 3D volumes classification lesion localization. For each patient, lung region segmented pre-trained UNet; then fed into neural network predict probability infectious; lesions are localized by combining...

High-resolution representation learning plays an essential role in many vision problems, e.g., pose estimation and semantic segmentation. The high-resolution network (HRNet)~\cite{SunXLW19}, recently developed for human estimation, maintains representations through the whole process by connecting high-to-low resolution convolutions \emph{parallel} produces strong repeatedly conducting fusions across parallel convolutions. In this paper, we conduct a further study on introducing simple yet...

This paper studies the problem of learning image semantic segmentation networks only using image-level labels as supervision, which is important since it can significantly reduce human annotation efforts. Recent state-of-the-art methods on this first infer sparse and discriminative regions for each object class a deep classification network, then train network supervision. Inspired by traditional seeded region growing, we propose to starting from progressively increase pixel-level...

In this paper, we propose a novel approach for text detection in natural images. Both local and global cues are taken into account localizing lines coarse-to-fine procedure. First, Fully Convolutional Network (FCN) model is trained to predict the salient map of regions holistic manner. Then, line hypotheses estimated by combining character components. Finally, another FCN classifier used centroid each character, order remove false hypotheses. The framework general handling multiple...

The study of Cyber-Physical System (CPS) has been an active area research. Internet Data Center (IDC) is important emerging System. As the demand on services drastically increases in recent years, power used by IDCs skyrocketing. While most existing research focuses reducing consumptions IDCs, management problem for minimizing total electricity cost overlooked. This faced service providers, especially current multi-electricity market, where price may exhibit time and location diversities....

Of late, weakly supervised object detection is with great importance in recognition. Based on deep learning, detectors have achieved many promising results. However, compared fully detection, it more challenging to train network based a manner. Here we formulate as Multiple Instance Learning (MIL) problem, where instance classifiers (object detectors) are put into the hidden nodes. We propose novel online classifier refinement algorithm integrate MIL and procedure single network, end-to-end...

This paper presents an end-to-end trainable fast scene text detector, named TextBoxes, which detects with both high accuracy and efficiency in a single network forward pass, involving no post-process except for standard non-maximum suppression. TextBoxes outperforms competing methods terms of localization is much faster, taking only 0.09s per image implementation. Furthermore, combined recognizer, significantly state-of-the-art approaches on word spotting recognition tasks.

Contextual information is vital in visual understanding problems, such as semantic segmentation and object detection. We propose a criss-cross network (CCNet) for obtaining full-image contextual very effective efficient way. Concretely, each pixel, novel attention module harvests the of all pixels on its path. By taking further recurrent operation, pixel can finally capture dependencies. Besides, category consistent loss proposed to enforce produce more discriminative features. Overall,...

In this paper, we introduce a new skeleton pruning method based on contour partitioning. Any partition can be used, but the partitions obtained by discrete curve evolution (DCE) yield excellent results. The theoretical properties and experiments presented demonstrate that skeletons are in accord with human visual perception stable, even presence of significant noise shape variations, have same topology as original skeletons. particular, proven proposed approach never produces spurious...

Weakly Supervised Object Detection (WSOD), using only image-level annotations to train object detectors, is of growing importance in recognition. In this paper, we propose a novel deep network for WSOD. Unlike previous networks that transfer the detection problem an image classification Multiple Instance Learning (MIL), our strategy generates proposal clusters learn refined instance classifiers by iterative process. The proposals same cluster are spatially adjacent and associated with...

High level semantics embodied in scene texts are both rich and clear thus can serve as important cues for a wide range of vision applications, instance, image understanding, indexing, video search, geolocation, automatic navigation. In this paper, we present unified framework text detection recognition natural images. The contributions paper threefold: 1) accomplished concurrently using exactly the same features classification scheme; 2) contrast to methods literature, which mainly focus on...

Driven by the wide range of applications, scene text detection and recognition have become active research topics in computer vision. Though extensively studied, localizing reading uncontrolled environments remain extremely challenging, due to various interference factors. In this paper, we propose a novel multi-scale representation for recognition. This consists set detectable primitives, termed as strokelets, which capture essential substructures characters at different granularities....

Shape similarity and shape retrieval are very important topics in computer vision. The recent progress this domain has been mostly driven by designing smart descriptors for providing better measure between pairs of shapes. In paper, we provide a new perspective to problem considering the existing shapes as group, study their measures query graph structure. Our method is general can be built on top any measure. For given measure, learned through transduction. iteratively so that neighbors...

Though deep learning-based object detection methods have achieved promising results on the conventional datasets, it is still challenging to locate objects from low-quality images captured in adverse weather conditions. The existing either difficulties balancing tasks of image enhancement and detection, or often ignore latent information beneficial for detection. To alleviate this problem, we propose a novel Image-Adaptive YOLO (IA-YOLO) framework, where each can be adaptively enhanced...