Human pose estimation has been greatly advanced in recent years. However, even the best-performing models are not shift equivariant. In particular, a small change in input images often results in drastic alterations in output, which are problematic especially in video applications. The prevalence of top-down approaches, which typically rely on a (non-equivariant) object detector in the first stage, exac-erbates this issue. In this paper, we first demonstrate that the biased keypoint representation and the non-equivariant network components are the two main obstacles to shift equivariant pose estimation. To address the limitation, we propose an unbiased decoding method, and redesign the necessary network components (e.g., APS-ResBlock, SSP). Extensive experiments show that our method not only produces much more stable results with shifting input, but also achieves better metrics with the ability of tolerating in-accurate detector output from the first stage. To our knowledge, this is the first work to address the problem of shift equivariance in the field of pose estimation. Our method could be easily applied to existing CNN-based pose estimation networks.

Social e-commerce uses social media as a new prevalent platform for online shopping. In this paper, we address the problem of cross-platform recommendation for social e-commerce, i.e., recommending products to users when they are shopping through social media. To the best of our knowledge, this is a new and important problem for all e-commerce companies (e.g. Amazon, Alibaba), but has never been studied before. Existing cross-platform and social related recommendation methods cannot be applied directly to this problem since they do not co-consider the social information and the cross-platform characteristics together. To study this problem, we collect two real-world datasets from social e-commerce services. We first investigate the heterogeneous shopping behaviors between traditional e-commerce app and social media. Based on these observations from data, we propose CROSS (Cross-platform Recommendation for Online Shopping in Social Media), a recommendation framework utilizing not only user-item interaction data on both platforms, but also social relation data on social media. The framework is general and we propose two variants, CROSS-MF and CROSS-NCF. Extensive experiments on two real-world social e-commerce datasets demonstrate that our proposed CROSS significantly outperforms existing state-of-the-art methods.

Intrinsic image decomposition is a fundamental problem for many computer vision applications. While recent deep learning based methods have achieved very promising results on the synthetic densely labeled datasets, the results on the real-world dataset are still far from human level performance. This is mostly because collecting dense supervision on a real-world dataset is impossible. Only a sparse set of pairwise judgement from human is often used. It's very difficult for models to learn in such settings. In this paper, we investigate the possibilities of only using reflectance images for supervision during training. In this way, the demand for labeled data is greatly reduced. In order to achieve this goal, we take a deep investigation into the reflectance images. We find that reflectance images are actually comprised of two components: the flat surfaces with low frequency information, and the boundaries with high frequency details. Then, we propose to disentangle the learning process of the two components of the reflectance images. We argue that through this procedure, the reflectance images can be better modeled, and in the meantime, the shading images, though not supervised, can also achieve decent result. Extensive experiments show that our proposed network outperforms current state-of-the-art results by a large margin on the most challenging real-world IIW dataset. We also surprisingly find that on the densely labeled datasets (MIT and MPI-Sintel), our network can also achieve state-of-the-art results on both reflectance and shading images, when we only apply supervision on the reflectance images during training.

Social commerce, which is different from traditional e-commerce where people purchase products via initiative searching or recommendations from the platform, transforms a social community into an inclusive place to do business by enabling people to share products with their friends. A user (sharer), can share a link of a product to their social-connected friends (receiver). Once a receiver purchases the product, the sharer can earn commission provided by the platform. To promote sales, the platform can also assist sharers by providing product candidates which are more likely to be purchased during the social sharing. We define this task of generating sharing suggestions as item recommendation for word-of-mouth scenario, and to the best of our knowledge, this is a new task that has never been explored. In this article, we propose aTriM(short forTriad based word-of-Mouth recommendation) model that can capture both the sharer’s influence and the receiver’s interest at the same time, which are two significant factors that determine whether the receiver will buy the product or not. Furthermore, with joint learning on two parts of interaction data to address data sparsity issue, our proposed TriM-Joint further improves the recommendation performance. By conducting experiments, we show that our proposed models achieve the best results compared to state-of-the-art models with significant improvements by at least$7.4\% \sim 14.4\%$respectively.

Social recommendation, which utilizes social relations to enhance recommender systems, has been gaining increasing attention recently with the rapid development of online social networks. Existing social recommendation methods are based on the assumption, so-calledsocial-trust, that users’ preference or decision is influenced by their social-connected friends’ purchase behaviors. However, they assume that the influences of social relationships are always the same, which violates the fact that users are likely to share preference on different products with different friends. More precisely, friends’ behaviors do not necessarily affect a user’s preferences, and the influence is diverse among different items. In this paper, we contribute a new solution, CSR (short forCharacterizedSocialRegularization) model by designing a universal regularization term for modeling variable social influence. This regularization term captures the finely grained similarity of social-connected friends. We further introduce two variants of our model with different optimization manners. Our proposed model can be applied to both explicit and implicit interaction due to its high generality. Extensive experiments on three real-world datasets demonstrate that our CSR can outperform state-of-the-art social recommendation methods. Further experiments show that CSR can improve recommendation performance for those users with sparse social relations or behavioral interactions.

In this paper, we detailedly describe our solution for the IEEE BigData Cup 2021: RL-based RecSys (Track 1: Item Combination Prediction)1. We first conduct an exploratory data analysis on the dataset and then utilize the findings to design our framework. Specifically, we use a two-headed transformer-based network to predict user feedback and unlocked sessions, along with the proposed session-aware reweighted loss, multitasking with click behavior prediction, and randomness-in-session augmentation. In the final private leaderboard on Kaggle, our method ranked 2nd with a categorization accuracy of 0.39224.2

Today’s video streaming market is crowded with various content providers (CPs). For individual CPs, understanding user behavior, in particular how users migrate among different CPs, is crucial for improving users’ on-site experience and the CP’s chance of success. In this article, we take a data-driven approach to analyze and model user migration behavior in video streaming, i.e., users switching content provider during active sessions. Based on a large ISP dataset over two months (6 major content providers, 3.8 million users, and 315 million video requests), we study common migration patterns and reasons of migration. We find that migratory behavior is prevalent: 66% of users switch CPs with an average switching frequency of 13%. In addition, migration behaviors are highly diverse: regardless large or small CPs, they all have dedicated groups of users who like to switch to them for certain types of videos. Regarding reasons of migration, we find CP service quality rarely causes migration, while a few popular videos play a bigger role. Nearly 60% of cross-site migrations are landed to 0.14% top videos. Finally, we validate our findings by building an accurate regression model to predict user migration frequency as well as user survey, and discuss the implications of our results to CPs.

With the rapid growth of mobile networks and smart devices, a large number of people prefer to visiting video services via mobile devices. This generates massive data traffic, and thus increases the load of cellular networks. To deal with it, we need to investigate the usage patterns in the video consumption. In this article, we take a data-driven analysis of mobile video services by classifying them into three major types: traditional video portals, user-generated video services and personalized livestreaming. We collect a large dataset of 25,937,758 logs from 455 thousand users, and we find that 1) for the same kind of video services, users exhibit high loyalty; 2) in consecutive days, the traffic peaks have differences among different service types; 3) more video traffic is generated from personalized livestreaming services, and it keeps increasing after midnight at weekdays in the downtown; 4) traffic consumption of user-generated service exhibits great differences under different functional regions; 5) individual users are prone to click within the same service type but possible different time gaps during the consecutive views. Lastly, we utilize these findings to discuss the potential applications in the improvements of cellular networks and video services.

Social e-commerce, as a new concept of e-commerce, uses social media as a new prevalent platform for online shopping. Users are now able to view, add to cart, and buy products within a single social media app. In this paper, we address the problem of cross-platform recommendation for social e-commerce, i.e., recommending products to users when they are shopping through social media. To the best of our knowledge, this is a new and important problem for all e-commerce companies (e.g. Amazon, Alibaba), but has never been studied before.

Social recommendation, which utilizes social relations to enhance recommender systems, has been gaining increasing attention recently with the rapid development of online social network. Existing social recommendation methods are based on the fact that users preference or decision is influenced by their social friends' behaviors. However, they assume that the influences of social relation are always the same, which violates the fact that users are likely to share preference on diverse products with different friends. In this paper, we present a novel CSR (short for C haracterized S ocial R egularization) model by designing a universal regularization term for modeling variable social influence. Our proposed model can be applied to both explicit and implicit iteration. Extensive experiments on a real-world dataset demonstrate that CSR significantly outperforms state-of-the-art social recommendation methods.

Android GUI testing is an important research field to maintain software quality of Android apps. Although many GUI testing schemes have been investigated in the past, the discussion of exploration event scheduling has not been investigated comprehensively for the event replay process. Based on the component priority relationship, this study proposes a novel exploration event scheduling scheme called CPR to reduce the number of the testing events in the replay process. Compared with the breadth-first traversal scheme, the proposed CPR scheme can reduce up to 62% of testing events for achieving the same component coverage, and up to 69% of testing events for layout traversal. Compared with the depth-first traversal scheme, CPR can reduce up to 15% of testing events for achieving the same component coverage, and up to 42% of testing events for layout traversal. With respect to the testing time, CPR can achieve the best performance for most of the AUTs in the empirical study. The results of the empirical experiments show that the proposed CPR scheduling scheme can have the benefits in improving the testing performance.

Watching videos online has become prevalent in our daily activities. While there are extensive measurements studying about video on demand, IPTV, live streaming, etc., most of them focus their analysis on a single content provider (CP). Various user behaviors over multiple different CPs are yet to be explored. In this paper, we collect about ten million viewing records of the six most popular video CPs through a major Internet service provider (ISP) in Shanghai, China, and examine the user behaviors and access patterns with an emphasis on comparing them among different CPs in the same environments. Our analysis reveals the day-scale temporal patterns, the diversified device-wise preferences, and the city-scale geographical features of the different CPs, and identifies the high relevance between the user behaviors and the contents of the videos. Moreover, we find that user migration across multiple CPs is prevalent and highly influenced by different features of CPs. We believe that our observations and findings can provide valuable insights for CPs to enhance their user experience as well as ISPs to optimize the network architecture.

Today's video streaming market is crowded with various content providers (CPs). For individual CPs, understanding user behavior, in particular how users migrate among different CPs, is crucial for improving users' on-site experience and the CP's chance of success. In this paper, we take a data-driven approach to analyze and model user migration behavior in video streaming, i.e., users switching content provider during active sessions. Based on a large ISP dataset over two months (6 major content providers, 3.8 million users, and 315 million video requests), we study common migration patterns and reasons of migration. We find that migratory behavior is prevalent: 66% of users switch CPs with an average switching frequency of 13%. In addition, migration behaviors are highly diverse: regardless large or small CPs, they all have dedicated groups of users who like to switch to them for certain types of videos. Regarding reasons of migration, we find CP service quality rarely causes migration, while a few popular videos play a bigger role. Nearly 60% of cross-site migrations are landed to 0.14% top videos. Finally, we validate our findings by building an accurate regression model to predict user migration frequency, and discuss the implications of our results to CPs.

Due to the proliferation of mobile networks and services, accessing online video services via mobile devices becomes increasingly popular, which generates huge data traffic and increases the cellular network load. It is valuable to characterize the usage patterns of different video services for network optimization and user experience enhancement. In this paper, we adopt a data-driven approach to investigate the usage patterns of three newly popular and major kinds of mobile video services: personalized livestreaming, user- generated video service, and traditional video portals. Based on the empirical analysis of a large dataset including 0.45 million users and 25 million logs, we find that 1) users have high loyalty in the same type of video services; 2) difference on the traffic peaks in consecutive days exists among different kinds of services; 3) personalized livestreaming services contributes a larger portion of video traffic, which still increases after midnight at weekday in the downtown. Finally, based on these findings, we discuss their implications and insights for network optimization and video service enhancement.