Search

Blind image quality assessment (BIQA) for authentic distortions is still a great challenge, even in today’s deep learning era. It has been widely acknowledged that local and global features are both indispensable for IQA, which play complementary roles. While combining local and global features is straightforward in traditional handcrafted feature-based IQA metrics, it is not an easy task in the deep learning framework. This is mainly due to the fact that deep neural networks typically require input images with a fixed size. Current metrics either resize the image or use local patches as input, which are problematic in that they cannot integrate local and global aspects as well as their interactions to achieve comprehensive quality evaluation. Motivated by the above facts, this paper presents a new BIQA metric for authentic distortions by aggregating local and global deep features in a Vision-Transformer framework. In the proposed metric, selective local regions and global content are simultaneously input for complementary feature extraction, and the Vision-Transformer is employed to build the relationship between different local patches and image quality. Self-attention mechanism is further adopted to explore the interaction between local and global deep features, producing the final image quality score. Extensive experiments on five authentically distorted IQA databases demonstrate that the proposed metric outperforms the state-of-the-arts in terms of both prediction performance and generalization ability.

Image quality assessment (IQA) for authentic distortions in the wild is challenging. Though current IQA metrics have achieved decent performance for synthetic distortions, they still cannot be satisfactorily applied to realistic distortions because of the generalization problem. Improving generalization ability is an urgent task to make IQA algorithms serviceable in real-world applications, while relevant research is still rare. Fundamentally, image quality is determined by both distortion degree and intelligibility. However, current IQA metrics mostly focus on the distortion aspect and do not fully investigate the intelligibility, which is crucial for achieving robust quality estimation. Motivated by this, this paper presents a new framework for building highly generalizable image quality model by integrating the intelligibility. We first analyze the relation between intelligibility and image quality. Then we propose a bilateral network to integrate the above two aspects of image quality. During the fusion process, feature selection strategy is further devised to avoid negative transfer. The framework not only catches the conventional distortion features but also integrates intelligibility features properly, based on which a highly generalizable no-reference image quality model is achieved. Extensive experiments are conducted based on five intelligibility tasks, and the results demonstrate that the proposed approach outperforms the state-of-the-art metrics, and the intelligibility task consistently improves metric performance and generalization ability.

With the development of mobile Internet and the prevalence of sharing economy, spatial crowdsourcing (SC) is becoming more and more popular and attracts attention from both academia and industry. A fundamental issue in SC is assigning tasks to suitable workers to obtain different global objectives. Existing works often assume that the tasks in SC are micro and can be completed by any single worker. However, there also exist macro tasks which need a group of workers with different kinds of skills to complete collaboratively. Although there have been a few works on macro task assignment, they neglect the dynamics of SC and assume that the information of the tasks and workers can be known in advance. This is not practical as in reality tasks and workers appear dynamically and task assignment should be performed in real time according to partial information. In this paper, we study the multi-skill aware task assignment problem in real-time SC, whose offline version is proven to be NP-hard. To solve the problem effectively, we first propose the Online-Exact algorithm, which always computes the optimal assignment for the newly appearing tasks or workers. Because of Online-Exact’s high time complexity which may limit its feasibility in real time, we propose the Online-Greedy algorithm, which iteratively tries to assign workers who can cover more skills with less cost to a task until the task can be completed. We finally demonstrate the effectiveness and efficiency of our solutions via experiments conducted on both synthetic and real datasets.

With the emergence of many crowdsourcing platforms, crowdsourcing has gained much attention. Spatial crowdsourcing is a rapidly developing extension of the traditional crowdsourcing, and its goal is to organize workers to perform spatial tasks. Route recommendation is an important concern in spatial crowdsourcing. In this paper, we define a novel problem called the Online Delivery Route Recommendation (OnlineDRR) problem, in which the income of a single worker is maximized under online scenarios. It is proved that no deterministic online algorithm for this problem has a constant competitive ratio. We propose an algorithm to balance three influence factors on a worker’s choice in terms of which task to undertake next. In order to overcome its drawbacks resulting from the dynamic nature of tasks, we devise an extended version which attaches gradually increased importance to the destination of the worker over time. Extensive experiments are conducted on both synthetic and real-world datasets and the results prove the algorithms proposed in this paper are effective and efficient.

Availability of big data is crucial for modern machine learning applications and services. Federated learning is an emerging paradigm to unite different data owners for machine learning on massive data sets without worrying about data privacy. Yet data owners may still be reluctant to contribute unless their data sets are fairly valuated and paid. In this work, we adapt Shapley value, a widely used data valuation metric to valuating data providers in federated learning. Prior data valuation schemes for machine learning incur high computation cost because they require training of extra models on all data set combinations. For efficient data valuation, we approximately construct all the models necessary for data valuation using the gradients in training a single model, rather than train an exponential number of models from scratch. On this basis, we devise three methods for efficient contribution index estimation. Evaluations show that our methods accurately approximate the contribution index while notably accelerating its calculation.

Due to stricter data management regulations such as General Data Protection Regulation (GDPR), traditional production mode of machine learning services is shifting to federated learning, a paradigm that allows multiple data providers to train a joint model collaboratively with their data kept locally. A key enabler for practical adoption of federated learning is how to allocate the profit earned by the joint model to each data provider. For fair profit allocation, a metric to quantity the contribution of each data provider to the joint model is essential. Shapley value is a classical concept in cooperative game theory which assigns a unique distribution (among the players) of a total surplus generated by the coalition of all players and has been used for data valuation in machine learning services. However, prior Shapley value based data valuation schemes either do not apply to federated learning or involve extra model training which leads to high cost. In this paper, given $n$ data providers with data sets $D_{1}, D_{2}$,..., $D_{n}$, a federated learning algorithm $A$ and a standard test set $T$, we propose the contribution index, a new Shapley value based metric fit for assessing the contribution of each data provider for the joint model trained by federated learning. The contribution index shares the same properties as Shapley value. However, direct calculation of the contribution index is time consuming, since a large number of joint models with different combinations of data sets are required to be trained and evaluated. To solve this problem, we propose two gradient based methods. The idea is to reconstruct approximately the models on different combinations of the data sets through the intermediate results of the training process of federated learning so as to avoid extra training. The first method reconstructs models by updating the initial global model in federated learning with the gradients in different rounds. Then it calculates the contribution index by the performance of these reconstructed models. The second method calculates contribution index in each round by updating the global model in the previous round with the gradients in the current round. Contribution indexes of multiple rounds are then added with elaborated weights to get the final result. We conduct extensive experiments on the MNIST data set in different settings. The results demonstrate that the proposed methods can approximate the exact contribution index effectively and achieve a time speed up of up to 2x-l00x compared with the exact calculation and other baselines extended from existing work.

On-demand taxi-calling platforms often ignore the social engagement of individual drivers. The lack of social incentives impairs the work enthusiasms of drivers and will affect the quality of service. In this paper, we propose to form teams among drivers to promote participation. A team consists of a leader and multiple members, which acts as the basis for various group-based incentives such as competition. We define the Recommendation-based Team Formation (RTF) problem to form as many teams as possible while accounting for the choices of drivers. The RTF problem is challenging. It needs both accurate recommendation and coordination among recommendations, since each driver can be in at most one team. To solve the RTF problem, we devise a Recommendation-Matrix-Based Framework (RMBF). It first estimates the acceptance probability of recommendations and then derives a recommendation matrix to maximize the number of formed teams from a global view. We conduct trace-driven simulations using real data covering over 64,000 drivers and deploy our solution on a large on-demand taxi-calling platform for online evaluations. Experimental results show that RMBF outperforms the greedy-based strategy by forming up to 20% and 12.4% teams in trace-driven simulations and online evaluations, and the drivers who form teams and are involved in the competition have more service time, number of finished orders and income.

With the rapid development of mobile Internet, spatial crowdsourcing is gaining more and more attention from both academia and industry. In spatial crowdsourcing, spatial tasks are sent to workers based on their locations. A wide kind of tasks in spatial crowdsourcing are specialty-aware, which are complex and need to be completed by workers with different skills collaboratively. Existing studies on specialty-aware spatial crowdsourcing assume that each worker has a unified charge when performing different tasks, no matter how many skills of her/him are used to complete the task, which is not fair and practical. In this paper, we study the problem of specialty-aware task assignment in spatial crowdsourcing, where each worker has fine-grained charge for each of their skills, and the goal is to maximize the total utility of the completed tasks based on tasks’ budget and requirements on particular skills. The problem is proven to be NP-hard. Thus, we propose two efficient heuristics to solve the problem. Experiments on both synthetic and real datasets demonstrate the effectiveness and efficiency of our solutions.

Online event-based social networks (EBSNs) and studies on global event-participant arrangement strategies for EBSNs are becoming popular recently. Existing works measure satisfaction of an arrangement by a linear combination of few factors, weights of which are predefined and fixed, and do not allow users to provide feedbacks on whether accepting the arrangement or not. Besides, most of them only consider offline scenarios, where full information of users is known in advance. However, on real-world EBSN platforms, users can dynamically log in the platform and register for events on a first come, first served basis. In other words, online scenarios of event-participant arrangement strategies should be considered. In this work, we study a new event-participant arrangement strategy for online scenarios, the Feedback-Aware Social Event-participant Arrangement (FASEA) problem, where satisfaction scores of an arrangement are learned adaptively and users can choose to accept or reject the arranged events. Particularly, we model the problem as a contextual combinatorial bandit setting and use efficient and effective algorithms to solve the problem. The effectiveness and efficiency of the solutions are evaluated with extensive experimental studies and our findings indicate that the state-of-the-art Thompson Sampling that is reported to work well under basic multi-armed bandit does not perform well under FASEA.

The prevalence of mobile Internet techniques and Online-To-Offline (O2O) business models has led the emergence of various spatial crowdsourcing (SC) platforms in our daily life. A core issue of SC is to assign real-time tasks to suitable crowd workers. Existing approaches usually focus on the matching of two types of objects, tasks and workers, or assume the static offline scenarios, where the spatio-temporal information of all the tasks and workers is known in advance. Recently, some new emerging O2O applications incur new challenges: SC platforms need to assign three types of objects, tasks, workers and workplaces, and support dynamic real-time online scenarios, where the existing solutions cannot handle. In this paper, based on the aforementioned challenges, we formally define a novel dynamic online task assignment problem, called the trichromatic online matching in real-time spatial crowdsourcing (TOM) problem, which is proven to be NP-hard. Thus, we first devise an efficient greedy online algorithm. However, the greedy algorithm can be trapped into local optimal solutions easily. We then present a threshold-based randomized algorithm that not only guarantees a tighter competitive ratio but also includes an adaptive optimization technique, which can quickly learn the optimal threshold for the randomized algorithm. Finally, we verify the effectiveness and efficiency of the proposed methods through extensive experiments on real and synthetic datasets.

These days, Online To Offline (O2O) platforms have been developing rapidly because of the popularization of smart phones and Mobile Internet. Spatial crowdsourcing, a burgeoning area in O2O market, is gaining more and more attention. It is a typical spatial crowdsourcing scenario in which an employer publishes a task and some workers will help him or her to accomplish it. However, most of previous work only considers the spatial information of workers and tasks, but ignores the individual variations among workers. In this paper, we raise a new problem called Software Development Team Formation (SDTF) problem, which aims to find a team of workers whose ability satisfies the requirement of the task. After showing the problem is NP-hard, we propose three greedy algorithms to approximately solve the problem. Besides, extensive experiments are conducted on synthetic and real datasets, which verify the effectiveness and efficiency of our algorithms.

With the rapid development of Mobile Internet and Online To Offline (O2O) marketing model, various spatial crowdsourcing platforms, such as Gigwalk and Gmission, are getting popular. Most existing studies assume that spatial crowdsourced tasks are simple and trivial. However, many real crowdsourced tasks are complex and need to be collaboratively finished by a team of crowd workers with different skills. Therefore, an important issue of spatial crowdsourcing platforms is to recommend some suitable teams of crowd workers to satisfy the requirements of skills in a task. In this paper, to address the issue, we first propose a more practical problem, called \(\underline{Top}\)-\(\underline{k} \; \underline{T}eam \;\underline{R}ecommendation \;in \;spatial \;crowdsourcing\) (TopkTR) problem. We prove that the TopkTR problem is NP-hard and design a two-level-based framework, which includes an approximation algorithm with provable approximation ratio and an exact algorithm with pruning techniques to address it. Finally, we verify the effectiveness and efficiency of the proposed methods through extensive experiments on real and synthetic datasets.

Twitter has become an important platform for reporting breaking news and instant events. However, it is almost impossible to detect events on Twitter manually due to the large volume of data and the noise in them. Though automatic event detection has been studied a lot, most works can only detect events in a fixed time window. In this paper, we propose an efficient system that can detect events in adjustable time windows. We detect terms with unusual frequency and group them into events. We further modify a segment tree data structure to support adjustable time window based event detection, which can efficiently aggregate statistics of terms of varied-sized time windows and is both space and time saving. We finally validate the effectiveness and efficiency of our proposed techniques through extensive experiments on real datasets.

With the rapid development of mobile internet and online to offline marketing model, various spatial crowdsourcing platforms, such as Gigwalk and Gmission, are getting popular. Most existing studies assume that spatial crowdsourced tasks are simple and trivial. However, many real crowdsourced tasks are complex and need to be collaboratively finished by a team of crowd workers with different skills. Therefore, an important issue of spatial crowdsourcing platforms is to recommend some suitable teams of crowd workers to satisfy the requirements of skills in a task. In this paper, to address the issue, we first propose a more practical problem, called Top-k team recommendation in spatial crowdsourcing (TopkTR) problem. We prove that the TopkTR problem is NP-hard and designs a two-level-based framework, which includes an approximation algorithm with provable approximation ratio and an exact algorithm with pruning techniques to address it. In addition, we study a variant of the TopkTR problem, called TopkTRL, where a team leader is appointed among each recommended team of crowd workers in order to coordinate different crowd workers conveniently, and the aforementioned framework can be extended to address this variant. Finally, we verify the effectiveness and efficiency of the proposed methods through extensive experiments on real and synthetic datasets.