Video Big Data Retrieval Over Media Cloud: A Context-Aware Online Learning Approach
TL;DR: This paper forms the personalized video big data retrieval problem as an interaction between the user and the system via a stochastic process, not just a similarity matching, accuracy (feedback) model of the retrieval; introduces users’ real-time context into the retrieval system; and proposes a general framework.
Abstract: Online video sharing (e.g., via YouTube or YouKu) has emerged as one of the most important services in the current Internet, where billions of videos on the cloud are awaiting exploration. Hence, a personalized video retrieval system is needed to help users find interesting videos from big data content. Two of the main challenges are to process the increasing amount of video big data and resolve the accompanying “cold start” issue efficiently. Another challenge is to satisfy the users’ need for personalized retrieval results, of which the accuracy is unknown. In this paper, we formulate the personalized video big data retrieval problem as an interaction between the user and the system via a stochastic process, not just a similarity matching, accuracy (feedback) model of the retrieval; introduce users’ real-time context into the retrieval system; and propose a general framework for this problem. By using a novel contextual multiarmed bandit-based algorithm to balance the accuracy and efficiency, we propose a context-based online big-data-oriented personalized video retrieval system. This system can support datasets that are dynamically increasing in size and has the property of cross-modal retrieval. Our approach provides accurate retrieval results with sublinear regret and linear storage complexity and significantly improves the learning speed. Furthermore, by learning for a cluster of similar contexts simultaneously, we can realize sublinear storage complexity with the same regret but slightly poorer performance on the “cold start” issue compared to the previous approach. We validate our theoretical results experimentally on a tremendously large dataset; the results demonstrate that the proposed algorithms outperform existing bandit-based online learning methods in terms of accuracy and efficiency and the adaptation from the bandit framework offers additional benefits.
Citations
More filters
28 Mar 2018
TL;DR: This paper proposes to use the linked users across social networking sites and e-commerce websites as a bridge to map users’ social networking features to another feature representation for product recommendation, and develops a feature-based matrix factorization approach which can leverage the learnt user embeddings for cold-start product recommendation.
Abstract: In recent years, the boundaries between ecommerce and social networking have become increasingly blurred. Many e-commerce websites support the mechanism of social login where users can sign on the websites using their social network identities such as their Facebook or Twitter accounts. Users can also post their newly purchased products on microblogs with links to the e-commerce product web pages. In this paper we propose a novel solution for cross-site coldstart product recommendation which aims to recommend products from e-commerce websites to users at social networking sites in “cold-start” situations, a problem which has rarely been explored before. A major challenge is how to leverage knowledge extracted from social networking sites for cross-site cold-start product We propose to use the linked users across social networking sites and e-commerce websites (users who have social networking accounts and have made purchases on e-commerce websites) as a bridge to map users’ social networking features to another feature representation for product recommendation. In specific, we propose learning both users’ and products’ feature representations (called user embeddings and product embeddings, respectively) from data collected from ecommerce websites using recurrent neural networks and then apply a modified gradient boosting trees method to transform users’ social networking features into user embeddings. We then develop a feature-based matrix factorization approach which can leverage the learnt user embeddings for cold-start product recommendation. Experimental results on a large dataset constructed from the largest Chinese microblogging service SINA WEIBO and the largest Chinese B2C e-commerce website JINGDONG have shown the effectiveness of our proposed framework.
83 citations
TL;DR: It was found that strategies for cut-based segmentation, color-based indexing, k-means based dimensionality reduction and data clustering have been the most frequent choices in recent papers.
Abstract: Content-based video retrieval and indexing have been associated with intelligent methods in many applications such as education, medicine and agriculture. However, an extensive and replicable review of the recent literature is missing. Moreover, relevant topics that can support video retrieval, such as dimensionality reduction, have not been surveyed. This work designs and conducts a systematic review to find papers able to answer the following research question: “what segmentation, feature extraction, dimensionality reduction and machine learning approaches have been applied for content-based video indexing and retrieval?”. By applying a research protocol proposed by us, 153 papers published from 2011 to 2018 were selected. As a result, it was found that strategies for cut-based segmentation, color-based indexing, k-means based dimensionality reduction and data clustering have been the most frequent choices in recent papers. All the information extracted from these papers can be found in a publicly available spreadsheet. This work also indicates additional findings and future research directions.
47 citations
TL;DR: This paper has provided thought for the application research of intelligent logistics system based on blockchain, and has positive reference value and guiding significance to the development of blockchain application research.
Abstract: Aiming at the current problems of security threats and privacy leak risks in the operation process of related data of intelligent logistics system, and the operation of system lacking of supervision and traceability, this paper proposes to use blockchain technology to resolve these problems. A scheme on applying blockchain in intelligent logistics system is proposed, including operation principle, consensus authentication mechanism, and data storage and access mechanism. By introducing and analyzing the related big data of intelligent logistics system, improving the scientific, rationality, and intelligence of the decision. The basic characteristic of blockchain is traceability. By constructing algorithm models, proposing the realization principles of consensus authentication mechanism. For different events, different “multi-authentication centers”, intelligent contracts, and blockchain systems are constructed, improving the efficiency and supervision of the operation of intelligent logistics system. By constructing the correlations between the fundamental data that corresponding to different blockchain, and the correlations between the fundamental data that corresponding to the same blockchain, making the related data easier to collect and analyze. By constructing the storage and access mechanism, ensuring the security and confidentiality of the operation data of intelligent logistics system. This paper has provided thought for the application research of intelligent logistics system based on blockchain, and has positive reference value and guiding significance to the development of blockchain application research.
42 citations
Cites background from "Video Big Data Retrieval Over Media..."
...[1] proposed a personalized video retrieval system to facilitate users to retrieve the required video from big data....
[...]
TL;DR: An end-to-end framework to directly and collectively model the relationships between category-instance, category-category, and instance-instance in the CI-graph is proposed and object semantics is adopted as a bridge to generate unified representations for both videos and categories.
Abstract: With the ever-growing video categories, Zero-Shot Learning (ZSL) in video classification has drawn considerable attention in recent years. To transfer the learned knowledge from seen categories to unseen categories, most existing methods resort to an implicit model that learns a projection between visual features and semantic category-representations. However, such methods ignore the explicit relationships among video instances and categories, which impede the direct information propagation in a Category-Instance graph (CI-graph) consisting of both instances and categories. In fact, exploring the structure of the CI-graph can capture the invariances of the ZSL task with good generality for unseen instances. Inspired by these observations, we propose an end-to-end framework to directly and collectively model the relationships between category-instance, category-category, and instance-instance in the CI-graph. Specifically, to construct node features of this graph, we adopt object semantics as a bridge to generate unified representations for both videos and categories. Motivated by the favorable performance of Graph Neural Networks (GNNs), we design a Category-Instance GNN (CI-GNN) to adaptively model the structure of the CI-graph and propagate information among categories and videos. With the task-driven message passing process, the learned model is able to transfer label information from categories towards unseen videos. Extensive experiments on four video datasets demonstrate the favorable performance of the proposed framework.
37 citations
TL;DR: A novel quantile contextual tree-based multiarmed bandits algorithm to support the large-scale recommendation with both quantifiable and unquantifiable data is proposed and theoretical analysis is given to prove a sublinear bound of the regret.
Abstract: With the rapid development of the Internet-of-Things (IoT) networks, millions of IoT services provided through wireless networks are waiting for people’s exploration. Such a large number of heterogeneous IoT services produce huge amounts of data in almost real time, known as big data , many of which cannot be measured or quantified. Hence, a recommended system that aims to deal with the unquantifiable big data is urgently needed. To solve the problem, we propose a novel quantile contextual tree-based multiarmed bandits algorithm to support the large-scale recommendation with both quantifiable and unquantifiable data. Furthermore, the high failure rate of communication has a serious influence on the recommendation accuracy of our system with the widely used D2D technology in today’s IoT network. To improve recommendation accuracy under the D2D communication, we take into account the feedback of historical service receivers and the historical successful delivery rate (SDP) of data transmission at the same time for the service recommendation system. We give theoretical analysis to prove a sublinear bound of the regret. Numerical experiments with tremendously large data sets show that we can balance the regret with the system time cost and guarantee a high SDP.
19 citations
Cites background or methods from "Video Big Data Retrieval Over Media..."
...a great similarity with the QUCB and adaptive cover tree (ACT) algorithms proposed in [6] and [8], respectively....
[...]
...According to the figure, both ACT and QSMO receive high recommendation accuracy....
[...]
...To show the result more directly, we show the influence of context cluster and the accuracy gain over ACT and HCT in Figs....
[...]
...3) ACT [8]: ACT further considers the context of users than HCT, which can make a better balance between...
[...]
...1) The average running time cost for QSMO is 0.0504 s, it is just a bit of slower compared with the previous context-aware algorithm ACT, which has an average time cost of 0.0464 s....
[...]
References
More filters
TL;DR: This work shows that the optimal logarithmic regret is also achievable uniformly over time, with simple and efficient policies, and for all reward distributions with bounded support.
Abstract: Reinforcement learning policies face the exploration versus exploitation dilemma, i.e. the search for a balance between exploring the environment to find profitable actions while taking the empirically best action as often as possible. A popular measure of a policy's success in addressing this dilemma is the regret, that is the loss due to the fact that the globally optimal policy is not followed all the times. One of the simplest examples of the exploration/exploitation dilemma is the multi-armed bandit problem. Lai and Robbins were the first ones to show that the regret for this problem has to grow at least logarithmically in the number of plays. Since then, policies which asymptotically achieve this regret have been devised by Lai and Robbins and many others. In this work we show that the optimal logarithmic regret is also achievable uniformly over time, with simple and efficient policies, and for all reward distributions with bounded support.
6,361 citations
"Video Big Data Retrieval Over Media..." refers background in this paper
...MAB is one of the simplest and best-performing online learning algorithms [5], [9] due to its finite-time optimality guarantee when facing the exploration-exploitation dilemma....
[...]
...Therefore, the retrieval system faces the dilemma of exploration versus exploitation: the system must search for a balance between exploration of the most informative videos with highly uncertain performance and exploitation of the most positive videos with the highest estimated performance [5], [31]....
[...]
...The sum of these two terms accounts for the upper confidence bound of μv,c [5], where the second term is the maximum size of the node....
[...]
26 Apr 2010
TL;DR: This work model personalized recommendation of news articles as a contextual bandit problem, a principled approach in which a learning algorithm sequentially selects articles to serve users based on contextual information about the users and articles, while simultaneously adapting its article-selection strategy based on user-click feedback to maximize total user clicks.
Abstract: Personalized web services strive to adapt their services (advertisements, news articles, etc.) to individual users by making use of both content and user information. Despite a few recent advances, this problem remains challenging for at least two reasons. First, web service is featured with dynamically changing pools of content, rendering traditional collaborative filtering methods inapplicable. Second, the scale of most web services of practical interest calls for solutions that are both fast in learning and computation.In this work, we model personalized recommendation of news articles as a contextual bandit problem, a principled approach in which a learning algorithm sequentially selects articles to serve users based on contextual information about the users and articles, while simultaneously adapting its article-selection strategy based on user-click feedback to maximize total user clicks.The contributions of this work are three-fold. First, we propose a new, general contextual bandit algorithm that is computationally efficient and well motivated from learning theory. Second, we argue that any bandit algorithm can be reliably evaluated offline using previously recorded random traffic. Finally, using this offline evaluation method, we successfully applied our new algorithm to a Yahoo! Front Page Today Module dataset containing over 33 million events. Results showed a 12.5% click lift compared to a standard context-free bandit algorithm, and the advantage becomes even greater when data gets more scarce.
2,467 citations
"Video Big Data Retrieval Over Media..." refers background or methods in this paper
...in [51]: at each time slot, we repeatedly and randomly select a searching event until the output vt belongs to the corresponding searching result....
[...]
...Techniques for reducing the dimension may be useful (we used the method in [51] in our experiments)....
[...]
...For all aforementioned features, we adopt the methods that are described in [51] to reduce the dimensionality of the items....
[...]
Book•
12 Dec 2012TL;DR: In this article, the authors focus on regret analysis in the context of multi-armed bandit problems, where regret is defined as the balance between staying with the option that gave highest payoff in the past and exploring new options that might give higher payoffs in the future.
Abstract: A multi-armed bandit problem - or, simply, a bandit problem - is a sequential allocation problem defined by a set of actions. At each time step, a unit resource is allocated to an action and some observable payoff is obtained. The goal is to maximize the total payoff obtained in a sequence of allocations. The name bandit refers to the colloquial term for a slot machine (a "one-armed bandit" in American slang). In a casino, a sequential allocation problem is obtained when the player is facing many slot machines at once (a "multi-armed bandit"), and must repeatedly choose where to insert the next coin. Multi-armed bandit problems are the most basic examples of sequential decision problems with an exploration-exploitation trade-off. This is the balance between staying with the option that gave highest payoffs in the past and exploring new options that might give higher payoffs in the future. Although the study of bandit problems dates back to the 1930s, exploration-exploitation trade-offs arise in several modern applications, such as ad placement, website optimization, and packet routing. Mathematically, a multi-armed bandit is defined by the payoff process associated with each option. In this book, the focus is on two extreme cases in which the analysis of regret is particularly simple and elegant: independent and identically distributed payoffs and adversarial payoffs. Besides the basic setting of finitely many actions, it also analyzes some of the most important variants and extensions, such as the contextual bandit model. This monograph is an ideal reference for students and researchers with an interest in bandit problems.
2,427 citations
TL;DR: A relevance feedback based interactive retrieval approach that effectively takes into account the subjectivity of human perception of visual content and the gap between high-level concepts and low-level features in CBIR.
Abstract: Content-based image retrieval (CBIR) has become one of the most active research areas in the past few years. Many visual feature representations have been explored and many systems built. While these research efforts establish the basis of CBIR, the usefulness of the proposed approaches is limited. Specifically, these efforts have relatively ignored two distinct characteristics of CBIR systems: (1) the gap between high-level concepts and low-level features, and (2) the subjectivity of human perception of visual content. This paper proposes a relevance feedback based interactive retrieval approach, which effectively takes into account the above two characteristics in CBIR. During the retrieval process, the user's high-level query and perception subjectivity are captured by dynamically updated weights based on the user's feedback. The experimental results over more than 70000 images show that the proposed approach greatly reduces the user's effort of composing a query, and captures the user's information need more precisely.
1,933 citations
"Video Big Data Retrieval Over Media..." refers background or methods in this paper
...Y. Rui et al. introduce this method into content-based image retrieval (CBIR) [4]....
[...]
...level concepts and user perception subjectivity [4], [30]....
[...]
...introduce this method into content-based image retrieval (CBIR) [4]....
[...]
...Many RF schemes have been proposed for CBIR [30], [33]–[36]; however, content-based video retrieval has not received sufficient attention, and few RF methods that can be applied to video retrieval exist....
[...]
26 Sep 2010
TL;DR: The video recommendation system in use at YouTube, the world's most popular online video community, is discussed, with details on the experimentation and evaluation framework used to test and tune new algorithms.
Abstract: We discuss the video recommendation system in use at YouTube, the world's most popular online video community. The system recommends personalized sets of videos to users based on their activity on the site. We discuss some of the unique challenges that the system faces and how we address them. In addition, we provide details on the experimentation and evaluation framework used to test and tune new algorithms. We also present some of the findings from these experiments.
1,069 citations