Leveraging social media networks for classification

Social media has reshaped the way in which people interact with each other. The rapid development of participatory web and social networking sites like YouTube, Twitter, and Facebook, also brings about many data mining opportunities and novel challenges. In particular, we focus on classification tasks with user interaction information in a social network. Networks in social media are heterogeneous, consisting of various relations. Since the relation-type information may not be available in social media, most existing approaches treat these inhomogeneous connections homogeneously, leading to an unsatisfactory classification performance. In order to handle the network heterogeneity, we propose the concept of social dimension to represent actors?? latent affiliations, and develop a classification framework based on that. The proposed framework, SocioDim, first extracts social dimensions based on the network structure to accurately capture prominent interaction patterns between actors, then learns a discriminative classifier to select relevant social dimensions. SocioDim, by differentiating different types of network connections, outperforms existing representative methods of classification in social media, and offers a simple yet effective approach to integrating two types of seemingly orthogonal information: the network of actors and their attributes.     

Leveraging colour segmentation for upper-body detection

This paper presents an upper-body detection algorithm that extends classical shape-based detectors through the use of additional semantic colour segmentation cues. More precisely, candidate upper-body image patches produced by a base detector are soft-segmented using a multi-class probabilistic colour segmentation algorithm that leverages spatial as well as colour prior distributions for different semantic object regions (skin, hair, clothing, background). These multi-class soft segmentation maps are then classified as true or false upper-bodies. By further fusing the score of this latter classifier with the base detection score, the method shows a performance improvement on three different public datasets and using two different upper-body base detectors, demonstrating the complementarity of the contextual semantic colour segmentation and the base detector.     

Distributed middleware architectures for scalable media services

The fusion of Multimedia and Internet technology has introduced an ever-increasing demand for large-scale reliable media services. This exposes the scalability limitations of current middleware architectures, as they traditionally operate on either very large-server configurations or on tightly coupled distributed systems. On the other hand, the wide availability of high-speed networks and the widespread deployment of powerful personal computing units by end users, has emphasized the advantages of the peer-to-peer (P2P) computing model. In this paper, we evaluate a number of different middleware architectures that facilitate the timely and reliable delivery of media services in P2P networks. Our evaluated architectures exploit features including availability of high-performance links, replication and caching of popular items and finally state-of-the-art search techniques proposed in the context of structured and unstructured P2P overlay networks. Through detailed simulation we investigate the behavior of the suggested P2P architectures for video provision and examine the involved trade-offs. We show that under realistic assumptions, the evaluated architectures are resilient to multiple peer-failures, are scalable with respect to dropped requests when the number of messages in the network increases and provide good response times to the user requests.     

Multiresolution video object extraction fitted to scalable wavelet-based object coding

To enable content based functionalities in video processing algorithms, decomposition of scenes into semantic objects is necessary. A semi-automatic Markov random field based multiresolution algorithm is presented for video object extraction in a complex scene. In the first frame, spatial segmentation and user intervention determine objects of interest. The specified objects are subsequently tracked in successive frames and newly appeared objects/regions are also detected. The video object extraction algorithm includes discrete wavelet transform decomposition multiresolution Markov random field (MRF)-based spatial segmentation with emphasis on border smoothness at different resolutions, and an MRF-based backward region classification that determines the tracked objects in the scene. Finally, a motion constraint, embedded in the region classifier, determines the newly appeared objects/regions and completes the proposed algorithm towards an efficient video segmentation algorithm. The results are applicable for generic segmentation applications, however the proposed multiresolution video segmentation algorithm supports scalable object-based wavelet coding in particular. Moreover, compared to traditional object extraction algorithms, it produces smoother and more visually pleasing shape masks at different resolutions. The proposed effective multiresolution video object extraction method allows for larger motion, better noise tolerance and less computational complexity     

Sockpuppet gang detection on social media sites

Users of social media sites can use more than one account. These identities have pseudo anonymous properties, and as such some users abuse multiple accounts to perform undesirable actions, such as posting false or misleading remarks comments that praise or defame the work of others. The detection of multiple user accounts that are controlled by an individual or organization is important. Herein, we define the problem as sockpuppet gang (SPG) detection. First, we analyze user sentiment orientation to topics based on emotional phrases extracted from their posted comments. Then we evaluate the similarity between sentiment orientations of user account pairs, and build a similar-orientation network (SON) where each vertex represents a user account on a social media site. In an SON, an edge exists only if the two user accounts have similar sentiment orientations to most topics. The boundary between detected SPGs may be indistinct, thus by analyzing account posting behavior features we propose a multiple random walk method to iteratively remeasure the weight of each edge. Finally, we adopt multiple community detection algorithms to detect SPGs in the network. User accounts in the same SPG are considered to be controlled by the same individual or organization. In our experiments on real world datasets, our method shows better performance than other contemporary methods.     

Event detection over twitter social media streams

In recent years, microblogs have become an important source for reporting real-world events. A real-world occurrence reported in microblogs is also called a social event. Social events may hold critical materials that describe the situations during a crisis. In real applications, such as crisis management and decision making, monitoring the critical events over social streams will enable watch officers to analyze a whole situation that is a composite event, and make the right decision based on the detailed contexts such as what is happening, where an event is happening, and who are involved. Although there has been significant research effort on detecting a target event in social networks based on a single source, in crisis, we often want to analyze the composite events contributed by different social users. So far, the problem of integrating ambiguous views from different users is not well investigated. To address this issue, we propose a novel framework to detect composite social events over streams, which fully exploits the information of social data over multiple dimensions. Specifically, we first propose a graphical model called location-time constrained topic (LTT) to capture the content, time, and location of social messages. Using LTT, a social message is represented as a probability distribution over a set of topics by inference, and the similarity between two messages is measured by the distance between their distributions. Then, the events are identified by conducting efficient similarity joins over social media streams. To accelerate the similarity join, we also propose a variable dimensional extendible hash over social streams. We have conducted extensive experiments to prove the high effectiveness and efficiency of the proposed approach.     

Leveraging social media to gain insights into service delivery: a study on Airbnb

Consumers increasingly rely on reviews and social media posts provided by others to get information about a service. Especially in the Sharing Economy, the quality of service delivery varies widely; no common quality standard can be expected. Because of the rapidly increasing number of reviews and tweets regarding a particular service, the available information becomes unmanageable for a single individual. However, this data contains valuable insights for platform operators to improve the service and educate individual providers. Therefore, an automated tool to summarize this flood of information is needed. Various approaches to aggregating and analyzing unstructured texts like reviews and tweets have already been proposed. In this research, we present a software toolkit that supports the sentiment analysis workflow informed by the current state-of-the-art. Our holistic toolkit embraces the entire process, from data collection and filtering to automated analysis to an interactive visualization of the results to guide researchers and practitioners in interpreting the results. We give an example of how the tool works by identifying positive and negative sentiments from reviews and tweets regarding Airbnb and delivering insights into the features of service delivery its users most value and most dislike. In doing so, we lay the foundation for learning why people participate in the Sharing Economy and for showing how to use the data. Beyond its application on the Sharing Economy, the proposed toolkit is a step toward providing the research community with an instrument for a holistic sentiment analysis of individual domains of interest.     

Leveraging social semantic components in executable environments for learning

Learning can benefit from the modern Web structure through the convergence of top‐down encyclopedic institutional knowledge and bottom‐up user‐generated annotations. A promising approach to such convergence consists in leveraging the social functionalities in 3.0 executable environments through the recommendation of tags with the mediation of lexical and semantic resources. This paper addresses such issues through the design and evaluation of a tag recommendation system in a Web 3.0 Web portal, ‘150 Digit’. Designed for schools, 150 Digit encourages students and teachers to interact with a set of four exhibitions on the historical and social aspects of the Italian unification process in a virtual environment. The website displays the exhibits and their related documents promoting the users' active participation through tagging, voting and commenting on the exhibits. Tags become a way for students to create and explore new relations among the site contents, orthogonal to the institutional viewpoint. In this paper, we illustrate the recommendation strategy incorporated in 150 Digit, which relies on a semantic middleware to mediate between the input expressed by the users through tags and the top‐down institutional classification provided by the curators of the exhibitions. Following this, we describe the evaluation process conducted in a real experimental setting and discuss the evaluation results and their implications for learning environments.     

Leveraging social networks to fight spam

Social networks are useful for judging the trustworthiness of outsiders. An automated antispam tool exploits the properties of social networks to distinguish between unsolicited commercial e-mail - spam - and messages associated with people the user knows.     

A scalable and reliable paradigm for media on demand

The authors describe a system for solving some of the conventional problems associated with traditional streaming protocols by using forward error correction codes to let multiple clients recover from different packet losses using the same redundant data     

On network CoProcessors for scalable, predictable media services

This paper presents the embedded realization and experimental evaluation of a media stream scheduler on network interface (NI) CoProcessor boards. When using media frames as scheduling units, the scheduler is able to operate in real-time on streams traversing the CoProcessor, resulting in its ability to stream video to remote clients at real-time rates. This paper presents a detailed evaluation of the effects of placing application or kernel-level functionality, like packet scheduling on NIs, rather than the host machines to which they are attached. The main benefits of such placement are: 1) that traffic is eliminated from the host bus and memory subsystem, thereby allowing increased host CPU utilization for other tasks, and 2) that NI-based scheduling is immune to host-CPU loading, unlike host-based media schedulers that are easily affected even by transient load conditions. An outcome of this work is a proposed cluster architecture for building scalable media servers by distributing schedulers and media stream producers across the multiple NIs used by a single server and by clustering a number of such servers using commodity network hardware and software.     

Context augmentation for object detection

Current two-stage object detectors, which mainly consist of a region proposal stage and a proposal recognition stage, may produce unreliable results for objects appearing with little information such as small and occluded objects. This is caused by poor region proposals and inaccurate proposal recognition. To address this problem, we propose a context augmentation algorithm that fully utilizes contextual information to generate high-quality region proposals and detection results. First, Region proposals are produced by two steps: 1) generate a coarse set of region proposals, some of which are reliable and some of which are ambiguous, and 2) the ambiguous region proposals are re-estimated using appearance and geometry information with respect to the reliable region proposals from step 1). Second, similar types of pair-wise relations between region proposals are used to produce global feature information associated with the region proposals in order to enhance recognition results. In practice, our method effectively improves the quality of region proposals as well as recognition results. Empirical studies show that the proposed context augmentation yields substantial and consistent improvements over baseline Faster R-CNN. Moreover, there is around 1.3% mAP improvement over Mask R-CNN on COCO dataset.

     

基于改进Transformer的社交媒体谣言检测

随着互联网的快速发展,社交媒体日益广泛而深刻地融入人们日常生活的各个方面。社交媒体逐渐成为人们彼此之间用来分享意见、见解、经验和观点的工具和平台,是人们获取分享信息、表达交流观点的主要途径。社交媒体在互联网的沃土上蓬勃发展,爆发出令人眩目的能量。由于社交媒体的开放性,用户规模庞大且来源复杂众多,容易产生各种各样的谣言虚假信息。社交媒体谣言左右着网民对事件的认识、动摇着社会的稳定。因此,如何准确高效地检测谣言成为当下亟待解决的问题。现有基于Transformer的社交媒体谣言检测模型忽略了文本位置信息。为有效提取文本位置信息,充分利用文本潜在信息,提出了一种基于改进Transformer的社交媒体谣言检测模型。该模型从相对位置和绝对位置两方面对传统Transformer进行改进：一方面采用可学习的相对位置编码捕捉文本的方向信息和距离信息;另一方面采用绝对位置编码将不同位置词语映射到不同特征空间。实验结果表明,与其他基准模型相比,所提模型在Twitter15、Twitter16和Weibo3种数据集上的准确率分别提高了0.9%、0.6%和1.4%。实验结果验证了所提的位置编码改进有效,基于...     

Fast and scalable conflict detection for packet classifiers

Packet filters provide rules for classifying packets based on header fields. High speed packet classification has received much study. However, the twin problems of fast updates and fast conflict detection have not received much attention. A conflict occurs when two classifiers overlap, potentially creating ambiguity for packets that match both filters. For example, if Rule 1 specifies that all packets going to CNN be rate controlled and Rule 2 specifies that all packets coming from Walmart be given high priority, the rules conflict for traffic from Walmart to CNN. There has been prior work on efficient conflict detection for two-dimensional classifiers. However, the best known algorithm for conflict detection for general classifiers is the naive O(N²) algorithm of comparing each pair of rules for a conflict. In this paper, we describe an efficient and scalable conflict detection algorithm for the general case that is significantly faster. For example, for a database of 20 000 rules, our algorithm is 40 times faster than the naive implementation. Even without considering conflicts, our algorithm also provides a packet classifier with fast updates and fast lookups that can be used for stateful packet filtering.     

基于网络社交媒体的子话题检测技术综述

在当前多种平台崛起的互联网背景下,与传统媒体相比,网络社交媒体中的数据具有传递速度快、用户参与度高、内容覆盖全等特点,其中存在着人们关注并发布评论的众多话题,而一个话题的相关信息中可能存在更深层次、更细粒度的子话题,针对该问题进行基于网络社交媒体的子话题检测技术的研究,这是一个新兴且不断发展的研究领域。通过社交媒体获取话题及子话题信息并参与讨论,这一方式正全方位、深层次改变着人们的生活,但是该领域技术还不成熟,且相关研究在国内尚处于起步阶段。首先,简述网络社交媒体中子话题检测的发展背景和基本概念;其次,将子话题检测技术分为七大类,对每类方法均加以介绍、对比和总结;然后,将子话题检测方式分为在线检测和离线检测两种方式,并将这两种方式进行对比,列举通用技术及两种方式下的常用技术;最后,概括了该领域当前不足及未来发展趋势。     

Pyramid context learning for object detection

Contextual information in complex scenarios is critical for accurate object detection. Existing state-of-the-art detectors have greatly improved detection performance with the use of contexts around objects. However, these detectors consider the local and global contexts separately, which limits the improvement in detection accuracy. In this paper, we propose a pyramid context learning module (PCL) for object detection, which makes full use of the feature context at different levels. Specifically, two operators, named aggregation and distribution, are designed to assemble and synthesize contextual information at different levels. In addition, a channel context learning operator is also used to capture the channel context. PCL is a universal module, so it can be easily integrated into most of the detection frameworks. To evaluate our PCL, we apply it into some popular detectors, e.g., SSD, Faster R-CNN and RetinaNet, and conduct extensive experiments on PASCAL VOC and MS COCO datasets. Experimental results show that PCL can produce competitive performance gains and significantly improve the baselines.

     

一种运动目标检测优化算法

提出了一种用于图像序列中检测运动目标的优化算法。针对用于室内目标检测的差分法存在着“虚影”噪声,以及用于室外目标检测的背景估计法在对短序列进行检测时,其结果中存在“残像”噪声的问题,揭示并利用两次差分之间的相关性实现了对“虚影”的检测并将其消除,将其引入背景估计法,以消除后者存在的“残像”噪声。实验表明,该方法在目标检测中不仅消除了“虚影”和“残像”噪声,而且检测结果的完整性显著提高。     

Oscillation analysis for salient object detection

Salient object detection from an image is important for many multimedia applications. Existing methods provide good solutions to saliency detection; however, their results often emphasize the high-contrast edges, instead of regions/objects. In this paper, we present a method for salient object detection based on oscillation analysis. Our study shows that salient objects and their backgrounds have different amplitudes of oscillation between the local minima and maxima. Based on this observation, our method analyzes the oscillation in an image by estimating its local minima and maxima and computes the saliency map according to the oscillation magnitude contrast. Our method detects the local minima and maxima and performs extreme interpolation to smoothly propagate these information to the whole image. In this way, the oscillation information is smoothly assigned to regions, retaining well-defined salient boundaries as there are large variations near the salient boundaries (edges between objects and their backgrounds). As a result, our saliency map highlights salient regions/objects instead of high-contrast boundaries. We experiment with our method on two large public data set. Our results demonstrate the effectiveness of our method. We further apply our salient object detection method to automatic salient object segmentation, which again shows the success.