Search

In the platform economy era, e‐commerce platforms function as distribution channels for sellers and offer online loans to sellers as financing providers. This study focuses on platform finance, where the platform sets a credit line or interest rate to offer either a limited or unlimited loan to capital‐constrained sellers. The sellers may have sufficient initial capital or be capital‐constrained but have access to limited or unlimited loans. We found that the optimal sellers' channel strategy, choosing either a single channel or online‐dominant or offline‐dominant dual channels, depends on the platform's credit line, consumers' channel preferences, and their switching behavior between online and offline channels. Given an unlimited (or limited) loan, the seller's dominated channel's quantity decreases (or increases) with her initial capital. The seller's and platform's preference for the unlimited loan or limited loan depends on the dominant channel and the seller's capital constraint. Loan offerings result in Pareto improvements for both participants, which reveals the value platform finance brings. We compare platform finance with bank finance and find that platform finance increases the sellers' threshold quantity without stockout in each channel and encourages the seller to place a higher quantity in both channels. We also examine the channel substitution effect on the sellers' quantity decisions. Findings provide insights for platforms and sellers to implement optimal financing and channel structures to increase their profits. [ABSTRACT FROM AUTHOR]

The transformer-based encoder-decoder framework is becoming popular in scene text recognition, largely because it naturally integrates recognition clues from both visual and semantic domains. However, recent studies show that the two kinds of clues are not always well registered and therefore, feature and character might be misaligned in difficult text (e.g., with a rare shape). As a result, constraints such as character position are introduced to alleviate this problem. Despite certain success, visual and semantic are still separately modeled and they are merely loosely associated. In this paper, we propose a novel module called multi-domain character distance perception (MDCDP) to establish a visually and semantically related position embedding. MDCDP uses the position embedding to query both visual and semantic features following the cross-attention mechanism. The two kinds of clues are fused into the position branch, generating a content-aware embedding that well perceives character spacing and orientation variants, character semantic affinities, and clues tying the two kinds of information. They are summarized as the multi-domain character distance. We develop CDistNet that stacks multiple MDCDPs to guide a gradually precise distance modeling. Thus, the feature-character alignment is well build even though various recognition difficulties are presented. We verify CDistNet on ten challenging public datasets and two series of augmented datasets created by ourselves. The experiments demonstrate that CDistNet performs highly competitively. It not only ranks top-tier in standard benchmarks, but also outperforms recent popular methods by obvious margins on real and augmented datasets presenting severe text deformation, poor linguistic support, and rare character layouts. In addition, the visualization shows that CDistNet achieves proper information utilization in both visual and semantic domains. Our code is available at https://github.com/simplify23/CDistNet. [ABSTRACT FROM AUTHOR]

Image super-resolution (SR) is a fundamental research task in low-level vision. Recently it has been applied to digital pathology to build transformations from low-resolution (LR) to super-resolved high-resolution (HR) images, which benefits pathological image sharing, storage, management, etc. However, existing studies on pathological image SR are mostly carried out on simulated dataset. It cannot fully reveal the challenge of real-world SR. Meanwhile, these studies rarely investigate SR models from a pathological-tailored perspective. This paper aims to promote studies on pathological image SR from the two aspects. Firstly, we construct PathImgSR, a dataset containing real-captured paired LR-HR pathological images by leveraging the progressively imaging property of pathological images. Second, we develop MASRGAN, a GAN-based mix-attention network to implement the SR. It devises a mix-attention block that is featured by modeling the channel and spatial attentions in parallel. Therefore it better captures the discriminative feature from pathological images spatially and channel-wisely. Furthermore, by formulating the learning processing in an adversarial learning manner, it also improves the subjective perception quality of the reconstructed HR image. Experiments on PathImgSR demonstrate that MASRGAN outperforms popular CNN-based and GAN-based SR methods in both quantitative metrics and visual subjective perception. [ABSTRACT FROM AUTHOR]

This study aimed to explore the research trends of percutaneous endoscopic lumbar discectomy in treating lumbar disc herniation using bibliometrics over the past ten years.Methods: Relevant publications on the clinical application of percutaneous endoscopic lumbar discectomy in lumbar disc herniation were searched in the Web of Science Core Collection. Subsequently, the characteristics of all these articles were collected. Visualizing data of annual publications, journals, cited journals, authors, cited authors, countries, institutions, keywords, and cited references was performed by using CiteSpace (6.1.R6).Results: A total of 642 publications were extracted between 2013 and 2022. The number of publications peaked in the year 2020. The most prolific journal was World Neurosurgery (81), and Spine (597) as the cited journal was the most popular one. China (393) was the most prolific country, followed by South Korea (100). The institution with the most productivity was Tongji University (35). Yue Zhou (20) was the most prolific author, and Sebastian Ruetten (310) was the most cited author. The keyword "interlaminar" was top of research developments with the highest citation burst (8.69). "Lumbar disc herniation", "surgical technique", and "complication" were popular keywords. The surgical procedures and complications of percutaneous endoscopic lumbar discectomy have been the hot topics of recent research.Conclusion: This study summarized the current situation and development trends of percutaneous endoscopic lumbar discectomy clinical research in the form of visualization, and these findings may help researchers explore new directions in the future. [ABSTRACT FROM AUTHOR]

Backgrounds: Traditional Chinese medicine and Western medicine combination (TCM-WMC) increased the complexity of compounds ingested. Objective: To develop a method for screening hepatotoxic compounds in TCM-WMC based on chemical structures using artificial intelligence (AI) methods. Methods: Drug-induced liver injury (DILI) data was collected from the public databases and published literatures. The total dataset formed by DILI data was randomly divided into training set and test set at a ratio of 3:1 approximately. Machine learning models of SGD (Stochastic Gradient Descent), kNN (k-Nearest Neighbor), SVM (Support Vector Machine), NB (Naive Bayes), DT (Decision Tree), RF (Random Forest), ANN (Artificial Neural Network), AdaBoost, LR (Logistic Regression) and one deep learning model (deep belief network, DBN) were adopted to construct models for screening hepatotoxic compounds. Result: Dataset of 2035 hepatotoxic compounds was collected in this research, in which 1505 compounds were as training set and 530 compounds were as test set. Results showed that RF obtained 0.838 of classification accuracy (CA), 0.827 of F1-score, 0.832 of Precision, 0.838 of Recall, 0.814 of area under the curve (AUC) on the training set and 0.767 of CA, 0.731 of F1, 0.739 of Precision, 0.767 of Recall, 0.739 of AUC on the test set, which was better than other eight machine learning methods. The DBN obtained 82.2% accuracy on the test set, which was higher than any other machine learning models on the test set. Conclusion: The DILI AI models were expected to effectively screen hepatotoxic compounds in TCM-WMC. [ABSTRACT FROM AUTHOR]

Backgrounds: Traditional Chinese medicine and Western medicine combination (TCM-WMC) increased the complexity of compounds ingested. Objective: To develop a method for screening hepatotoxic compounds in TCM-WMC based on chemical structures using artificial intelligence (AI) methods. Methods: Drug-induced liver injury (DILI) data was collected from the public databases and published literatures. The total dataset formed by DILI data was randomly divided into training set and test set at a ratio of 3:1 approximately. Machine learning models of SGD (Stochastic Gradient Descent), kNN (k-Nearest Neighbor), SVM (Support Vector Machine), NB (Naive Bayes), DT (Decision Tree), RF (Random Forest), ANN (Artificial Neural Network), AdaBoost, LR (Logistic Regression) and one deep learning model (deep belief network, DBN) were adopted to construct models for screening hepatotoxic compounds. Result: Dataset of 2035 hepatotoxic compounds was collected in this research, in which 1505 compounds were as training set and 530 compounds were as test set. Results showed that RF obtained 0.838 of classification accuracy (CA), 0.827 of F1-score, 0.832 of Precision, 0.838 of Recall, 0.814 of area under the curve (AUC) on the training set and 0.767 of CA, 0.731 of F1, 0.739 of Precision, 0.767 of Recall, 0.739 of AUC on the test set, which was better than other eight machine learning methods. The DBN obtained 82.2% accuracy on the test set, which was higher than any other machine learning models on the test set. Conclusion: The DILI AI models were expected to effectively screen hepatotoxic compounds in TCM-WMC. [ABSTRACT FROM AUTHOR]

Diabetic retinopathy, the most serious ocular complication of diabetes, imposes a serious economic burden on society. Automatic and objective assessment of vessel changes can effectively manage diabetic retinopathy and prevent blindness. Optical coherence tomography angiography (OCTA) metrics have been confirmed to be used to assess vessel changes. The accuracy and reliability of OCTA metrics are restricted by vessel segmentation methods. In this study, a multi-branch retinal vessel segmentation method is proposed, which is comparable to the segmentation results obtained from the manual segmentation, effectively extracting vessels in low contrast areas and improving the integrity of the extracted vessels. OCTA metrics based on the proposed segmentation method were validated to be reliable for further analysis of the relationship between OCTA metrics and diabetes and the severity of diabetic retinopathy. Changes in vessel morphology are influenced by systemic risk factors. However, there is a lack of analysis of the relationship between OCTA metrics and systemic risk factors. We conducted a cross-sectional study that included 362 eyes of 221 diabetic patients and 1,151 eyes of 587 healthy people. Eight systemic risk factors were confirmed to be closely related to diabetes. After controlling these systemic risk factors, significant OCTA metrics (such as vessel complexity index, vessel diameter index, and mean thickness of retinal nerve fiber layer centered in the macular) were found to be related to diabetic retinopathy and severe diabetic retinopathy. This study provides evidence to support the potential value of OCTA metrics as biomarkers of diabetic retinopathy. [ABSTRACT FROM AUTHOR]

Background: Osteoporosis (OP) is a systemic bone disease characterized by decreased bone mass, destruction of the bone tissue microstructure, increased bone brittleness and an increased risk of fracture. OP has a high incidence rate and long disease course and is associated with serious complications. Yigu decoction (YGD) is a compound prescription in traditional Chinese medicine that is used to treat OP. However, its mechanism in OP is not clear. This study used a tandem mass tag (TMT)quantitative proteomics method to explore the potential bone-protective mechanism of YGD in an osteoporotic rat model. Materials and methods: A rat model of OP was established by ovariectomy. Eighteen 12-week-old specific-pathogen-free female Wistar rats weighing 220 ± 10 g were selected. The eighteen rats were randomly divided into 3 groups (n = 6 in each group): the normal, model and YGD groups. The right femurs from each group were subjected to quantitative biological analysis. TMT quantitative proteomics was used to analyze the proteins extracted from the bone tissue of rats in the model and YGD groups, and the differentially expressed proteins after intervention with YGD were identified as biologically relevant proteins of interest. Functional annotation correlation analysis was also performed to explore the biological function and mechanism of YGD. Result: Compared with the model group, the YGD group showed significant upregulation of 26 proteins (FC > 1.2, P < 0.05) and significant downregulation of 39 proteins (FC < 0.833, P < 0.05). Four important targets involved in OP and 5 important signaling pathways involved in bone metabolism were identified. Conclusions: YGD can significantly increase the bone mineral density (BMD) of osteoporotic rats and may play a therapeutic role by regulating target proteins involved in multiple signaling pathways. Therefore, these results improve the understanding of the OP mechanism and provide an experimental basis for the clinical application of YGD in OP treatment. [ABSTRACT FROM AUTHOR]

For the study of various retinal diseases, an accurate quantitative analysis of the retinal layer is essential for assessing the severity of the disease and diagnosing the progression of the disease. Optical coherence tomography (OCT) images can clearly show each layer of the retinal structure and detect subtle early lesions, thus providing a gold standard for the diagnosis of retinal diseases. In this article, we propose a coarse-to-fine retinal layer boundary segmentation method based on the embedded residual recurrent network (ERR-Net) and the graph search (GS). Considering the integrity of information transmission and the dependence of features, we first design a novel end-to-end residual recurrent network to roughly segment the retinal layer boundaries. The proposed ERR-Net not only solves the gradient problem brought by the depth but also fully captures the global spatial structure of the image. Second, we employ a GS algorithm for boundary continuous to make the layer boundary segmentation results more accurate. Finally, we evaluate the effectiveness of the proposed method on three publicly available datasets and compare it with the state-of-the-art methods on each dataset. The quantitative results and visual effects show that the proposed method outperforms the state-of-the-art approaches in the segmentation of retinal layer boundaries in OCT images. Moreover, the results also show that the proposed method has good algorithm stability on three datasets with different sizes, characteristics, and segmentation difficulties. [ABSTRACT FROM AUTHOR]

Visual Question Answering(VQA), an important task to evaluate the cross-modal understanding capability of an Artificial Intelligence model, has been a hot research topic in both computer vision and natural language processing communities. Recently, graph-based models have received growing interest in VQA, for its potential of modeling the relationships between objects as well as its formidable interpretability. Nonetheless, those solutions mainly define the similarity between objects as their semantical relationships, while largely ignoring the critical point that the difference between objects can provide more information for establishing the relationship between nodes in the graph. To achieve this, we propose an object-difference based graph learner, which learns question-adaptive semantic relations by calculating inter-object difference under the guidance of questions. With the learned relationships, the input image can be represented as an object graph encoded with structural dependencies between objects. In addition, existing graph-based models leverage the pre-extracted object boxes by the object detection model as node features for convenience, but they are suffering from the redundancy problem. To reduce the redundant objects, we introduce a soft-attention mechanism to magnify the question-related objects. Moreover, we incorporate our object-difference based graph learner into the soft-attention based Graph Convolutional Networks to capture question-specific objects and their interactions for answer prediction. Our experimental results on the VQA 2.0 dataset demonstrate that our model gives significantly better performance than baseline methods. [ABSTRACT FROM AUTHOR]

Iatrogenic radial nerve injures are a common complication during the placement of external fixator pins at the lateral aspect of the humeral shaft. This study uses a three-dimensional measurement technique to locate a safe entry point for humeral pins when externally fixating the elbow. Methods: We fixed a guide wire to the radial nerve by a suture string, and used computed tomography (CT) to scan the upper limbs of cadaver specimens. Then, we measured the deviation angles of the radial nerve on the CT scans, and the distance from the radial nerve to the "elbow rotation center" (ERC). Result: The average distance from the radial nerve to the ERC was 87.3 ± 8.5 mm (range: 68–100 mm), 58.3 ± 11.3 mm (range: 32.12–82.84 mm), 106.3 ± 5.8 mm (range: 86.93–115.08 mm), and 113.9 ± 4.8 mm (range: 97.93–120.22 mm) at radial nerve deviation angles of 0°, –30°, 30°, and 45°, respectively. The average radial nerve deviation angle was –37.7° ± 7.7° and 123.9° ± 19.9° at 50 and 150 mm, respectively. Relative to 0°, the distance between the radial nerve and the ERC at radial nerve deviation angles of –30°, 30°, and 45° showed a significant difference (t = 18.20, p < 0.05; Z = 6.07, p < 0.001; Z = 6.40, p < 0.001, respectively). Conclusions: Pins inserted into the proximal humerus should be about 150 mm from the ERC with a radial nerve deviation angle of 30° anteriorly, and 50 mm from the ERC with a deviation angle of 30°–45° posteriorly. [ABSTRACT FROM AUTHOR]

In recent years, deep convolutional features have been applied to discriminative correlation filters-based methods, which have achieved impressive performance in tracking. Most of them utilize hierarchical features from a certain layer. However, this is not always sufficient to learn target appearance changes and to suppress the background interference in complicated interfering factors (e.g., deformation, fast motion, low resolution, and rotations). In this paper, we propose an adaptive multi-branch correlation filter tracking method, by constructing multi-branch models and using an adaptive selection strategy to improve the accuracy and robustness of visual tracking. Specially, the multi-branch models are introduced to tolerate temporal changes of the object, which can serve different circumstances. In addition, the adaptive selection strategy incorporates both foreground and background information to learn background suppression. To further improve the tracking performance, we propose a measurement method to handle tracking failures from unreliable samples. Extensive experiments on OTB-2013, OTB-2015, and VOT-2016 datasets show that the proposed tracker has comparable performance compared to state-of-the-art tracking methods. Especially, on the OTB-2015, our method significantly improves the baseline with a gain of 5.5% in overlap precision. [ABSTRACT FROM AUTHOR]

Weakly-supervised semantic segmentation with image-level labels has much significance as it facilitates related practical applications under lightweight manual annotations. Recent researches first infer the visual cues, referred as discriminative regions corresponding to each object category on images using deep convolutional classification networks. Then they expand visual cues to generate initial segmentation masks. Despite the remarkable progress, the segmentation performance still remains unsatisfactory due to the absence of complete visual cues. Using these low-quality visual cues as prior will have the limitation on improving segmentation performance. To overcome this problem, we propose a novel context propagation embedding network, i.e., the CPENet to generate high-quality visual cues, which focuses on learning semantic relationship between each region and its surrounding neighbors and selectively propagates discriminative information to non-discriminative, object related regions. Our methods can provide reliable initial segmentation masks for training subsequent segmentation network to generate final segmentation results. In addition, we refined convolutional block attention module (CBAM) [30] to hierarchically extract more category-aware features by capturing global context related information and further promote the propagation process. Experiments on benchmark demonstrate that our proposed method obtains superior performance over the state-of-the-arts. [ABSTRACT FROM AUTHOR]

Lumbar decompressive surgery is the gold standard treatment for lumbar spinal stenosis. Minimally invasive surgical techniques have been introduced with the aim of reducing the morbidity associated with open surgery. The purpose of the present study was to systematically search the literature and perform a meta-analysis of studies comparing the outcomes between biportal endoscopic technique and microscopic technique for lumbar canal stenosis decompression. A comprehensive search of the PubMed, Google Scholar, Web of Science, Embase and the Cochrane Library databases was performed to identify relevant articles up to 15th of December 2019. Eligible studies were retrieved, data were extracted by two authors independently and risks of bias were assessed. A total of six studies involving 438 patients were selected for review. The results of the pooled analysis indicated similar operative times [mean difference (MD), -3.41; 95% CI, -10.78-3.96; P<0.36], similar complications (MD, 0.70; 95% CI, 0.33-1.46; P=0.34), similar visual analogue scale scores for back and leg pain at the time of the final follow-up and similar Oswestry disability indexes (MD, -0.28; 95% CI, -1.25-0.69; P=0.58) for the two procedures. In conclusion, biportal endoscopic technique is a viable alternative to microscopic technique for lumbar canal stenosis decompression with similar operative time, clinical outcomes and complications. [ABSTRACT FROM AUTHOR]

Fine-grained object classification (FGOC) is a challenging research topic in multimedia computing with machine learning, which faces two pivotal conundrums: focusing attention on the discriminate part regions, and then processing recognition with the part-based features. Existing approaches generally adopt a unidirectional two-step structure, that first locate the discriminate parts and then recognize the part-based features. However, they neglect the truth that part localization and feature recognition can be reinforced in a bidirectional process. In this paper, we propose a novel bidirectional attention-recognition model (BARM) to actualize the bidirectional reinforcement for FGOC. The proposed BARM consists of one attention agent for discriminate part regions proposing and one recognition agent for feature extraction and recognition. Meanwhile, a feedback flow is creatively established to optimize the attention agent directly by recognition agent. Therefore, in BARM the attention agent and the recognition agent can reinforce each other in a bidirectional way and the overall framework can be trained end-to-end without neither object nor parts annotations. Moreover, a novel Multiple Random Erasing data augmentation is proposed, and it exhibits impressive pertinency and superiority for FGOC. Conducted on several extensive FGOC benchmarks, BARM outperforms the present state-of-the-art methods in classification accuracy. Furthermore, BARM exhibits a clear interpretability and keeps consistent with the human perception in visualization experiments. [ABSTRACT FROM AUTHOR]

As binary code is storage efficient and fast to compute, it has become a trend to compact real-valued data to binary codes for the nearest neighbors (NN) search in a large-scale database. However, the use of binary code for the NN search leads to low retrieval accuracy. To increase the discriminability of the binary codes of existing hash functions, in this paper, we propose a framework of double-bit quantization and index hashing for an effective NN search. The main contributions of our framework are: first, a novel double-bit quantization (DBQ) is designed to assign more bits to each dimension for higher retrieval accuracy; second, a double-bit index hashing (DBIH) is presented to efficiently index binary codes generated by DBQ; and third, a weighted distance measurement for DBQ binary codes is put forward to re-rank the search results from DBIH. The empirical results on three benchmark databases demonstrate the superiority of our framework over existing approaches in terms of both retrieval accuracy and query efficiency. Specifically, we observe an absolute improvement on precision of 10%–25% in most cases and the query speed increases over 30 times compared to traditional binary embedding methods and linear scan, respectively. [ABSTRACT FROM AUTHOR]

This paper describes methods for automatically associating faces detected from multimedia documents with their names presented in the surrounding metadata. We consider the task in the image matching (IM) framework, where external Web facial images are automatically retrieved as the gallery face set of the names in advance, and a detected face is assigned to one of the names, or none of them, according to the association score between the two kinds of faces and constraints. Several important issues are investigated within the IM framework. In collecting Web facial images, beyond the basic scheme that use a celebrity name purely as the query to crawl facial images, a context-assisted image search method is proposed to enhance the relevance and discriminability of the retrieved faces. In constraint formulation, we propose an assigning-thresholding (AT) pipeline to uniformly ensure that the name-face correspondence is strictly one-to-one, and set low confidence associations as null assignments. In association score computation, we propose methods that jointly consider IM with the well-established graph-based association (GA) method at different stages, aiming at producing more accurate scores to benefit the association. Based on these efforts, an Accu-IM method performing the association as accurate as possible and a Fast-IM method performing the association in real-time are respective proposed. Extensive experiments on datasets of captioned News images and Web videos both demonstrate the advantages of the proposed efforts individually and jointly, which consistently provide improvement gains under different settings when compared with state-of-the-art methods. [ABSTRACT FROM AUTHOR]

In recent years, block compressed sampling (BCS) has emerged as a considerable attractive sampling technology for image acquisition. However, the general BCS approaches ignore the information distribution in the same image sub-block, and may lead to unfair allocation of sampling resources. In this paper, we propose a novel compressed sampling scheme by employing the idea of adaptive partition. In the proposed scheme, images are adaptively partitioned based on their saliency information through clustering, and pixels with similar saliency are gathered in the same sub-blocks. Sampling rates for those blocks, in turn, are computed on the basis of their saliency values, respectively. Therefore the sampling resources are allocated with fairer and more equitable sharing by all sub-blocks. Experimental results show that the proposed scheme has better visual effect and obtains higher image reconstruction accuracy than existing ones. [ABSTRACT FROM AUTHOR]

How to read Uyghur text from biomedical graphic images is a challenge problem due to the complex layout and cursive writing of Uyghur. In this paper, we propose a system that extracts text from Uyghur biomedical images, and matches the text in a specific lexicon for semantic analysis. The proposed system possesses following distinctive properties: first, it is an integrated system which firstly detects and crops the Uyghur text lines using a single fully convolutional neural network, and then keywords in the lexicon are matched by a well-designed matching network. Second, to train the matching network effectively an online sampling method is applied, which generates synthetic data continually. Finally, we propose a GPU acceleration scheme for matching network to match a complete Uyghur text line directly rather than a single window. Experimental results on benchmark dataset show our method achieves a good performance of F-measure 74.5%. Besides, our system keeps high efficiency with 0.5s running time for each image due to the GPU acceleration scheme. [ABSTRACT FROM AUTHOR]

Uyghur text localization in complex background images is a significant research for Uyghur image content analysis. In this paper, we propose a robust Uyghur text localization method in complex background images and provide a CPU-GPU heterogeneous parallelization scheme. Firstly, a multi-color-channel enhanced maximally stable extremal region is used to extract components in images, which is robust to blur and low contrast. Secondly, a two-stage component classification system is used to filter out non-text components. Finally, a component connected graph algorithm is proposed to construct text lines. Experiments on the proposed dataset demonstrate that our algorithm compares favorably with the state-of-the-art algorithms when handling Uyghur texts. Besides, the heterogeneous parallel implementation achieves 12.5 times speedup. [ABSTRACT FROM AUTHOR]

Uyghur text detection is crucial to a variety of real-world applications, while little researches put their attention on it. In this paper, we develop an effective and efficient region-based convolutional neural network for Uyghur text detection in complex background images. The characteristics of the network include: (1) Three region proposal networks are used to improve the recall, which simultaneously utilize feature maps from different convolutional layers. (2) The overall architecture of our network is in the form of fully convolutional network, and global average pooling is applied to replace the fully connected layers in the classification and bounding box regression layers. (3) To fully utilize the baseline information, Uyghur text lines are detected directly by the network in an end-to-end fashion. Experiment results on benchmark dataset show that our method achieves an F-measure of 0.83 and detection time of 0.6 s for each image in a single K20c GPU, which is much faster than the state-of-the-art methods while keeps competitive accuracy. [ABSTRACT FROM AUTHOR]

The Internet has extended the physical boundary of people's social circles to manage an inordinate number of online friends. It is recognized that only a fraction of these online friends are also known with each other in offline circumstances, i.e., the offline friends. An important type of offline friend, onsite offline friend, is defined and addressed in this paper. We explores the possibility of utilizing users’ online photo sharing-related behaviors and network topologies to analyze and distinguish between online and onsite offline friendships. Different from traditional social science studies which rely on survey-based data, we employ users’ tagged people on the shared Instagram photos as the ground-truth for onsite offline friends. This enables a large-scale and objective analysis and experimental evaluation, which compares between different factors and identifies the features that are key to onsite offline friend identification. [ABSTRACT FROM PUBLISHER]

The proliferation of mobile devices is producing a new wave of mobile visual search applications that enable users to sense their surroundings with smart phones. As the particular challenges of mobile visual search, achieving high recognition bitrate becomes the consistent target of existed related works. In this paper, we explore to holistically exploit the deep learning-based hashing methods for more robust and instant mobile visual search. Firstly, we present a comprehensive survey of the existed deep learning based hashing methods, which showcases their remarkable power of automatic learning highly robust and compact binary code representation for visual search. Furthermore, in order to implement the deep learning hashing on computation and memory constrained mobile device, we investigate the deep learning optimization works to accelerate the computation and reduce the model size. Finally, we demonstrate a case study of deep learning hashing based mobile visual search system. The evaluations show that the proposed system can significantly improve 70% accuracy in MAP than traditional methods, and only needs less than one second computation time on the ordinary mobile phone. Finally, with the comprehensive study, we discuss the open issues and future research directions of deep learning hashing for mobile visual search. [ABSTRACT FROM AUTHOR]

Broadcast news video has been playing an increasingly important role in our daily life. However, how to effectively segment a broadcast news video into meaningful semantic story units is still a challenge issue. In this paper, we propose a novel unified video structure parsing approach, named multiple style exploration-based news story segmentation (MSE-NSS), to segment broadcast news videos into semantic story units. In MSE-NSS, we first investigate the appropriate methods to explore multiple kinds of style information inherent in broadcast news videos, including temporal style inferred from caption texts, boundary style represented by a wealth of multi-modal visual-audio features, and structural style known as the spanning duration of story units. Then the above multiple style information is integrated together and the task of story unit segmentation is accomplished through the following three steps: temporal style-based pre-location, boundary style-based description, and boundary-structural style-based segmentation, where the segmentation process is composed of a SVM-based detector and a dynamic programming-based refiner that considers the boundary style and the structural style collectively. Parallel to this, a news-oriented broadcast management system-NOBMs is implemented on top of the proposed MSE-NSS. Encouraging experimental results on a large broadcast news video dataset demonstrate the effectiveness of the proposed MSE-NSS, as well as its superiority over traditional story unit segmentation methods. [ABSTRACT FROM AUTHOR]