After more than 70 years of evolution,great achievements have been made in machine translation.Especially in recent years,translation quality has been greatly improved with the emergence of neural machine translation(...After more than 70 years of evolution,great achievements have been made in machine translation.Especially in recent years,translation quality has been greatly improved with the emergence of neural machine translation(NMT).In this article,we first review the history of machine translation from rule-based machine translation to example-based machine translation and statistical machine translation.We then introduce NMT in more detail,including the basic framework and the current dominant framework,Transformer,as well as multilingual translation models to deal with the data sparseness problem.In addition,we introduce cutting-edge simultaneous translation methods that achieve a balance between translation quality and latency.We then describe various products and applications of machine translation.At the end of this article,we briefly discuss challenges and future research directions in this field.展开更多
Background Gesture recognition has attracted significant attention because of its wide range of potential applications.Although multi-modal gesture recognition has made significant progress in recent years,a popular m...Background Gesture recognition has attracted significant attention because of its wide range of potential applications.Although multi-modal gesture recognition has made significant progress in recent years,a popular method still is simply fusing prediction scores at the end of each branch,which often ignores complementary features among different modalities in the early stage and does not fuse the complementary features into a more discriminative feature.Methods This paper proposes an Adaptive Cross-modal Weighting(ACmW)scheme to exploit complementarity features from RGB-D data in this study.The scheme learns relations among different modalities by combining the features of different data streams.The proposed ACmW module contains two key functions:(1)fusing complementary features from multiple streams through an adaptive one-dimensional convolution;and(2)modeling the correlation of multi-stream complementary features in the time dimension.Through the effective combination of these two functional modules,the proposed ACmW can automatically analyze the relationship between the complementary features from different streams,and can fuse them in the spatial and temporal dimensions.Results Extensive experiments validate the effectiveness of the proposed method,and show that our method outperforms state-of-the-art methods on IsoGD and NVGesture.展开更多
In this paper, we propose to detect a special group of microblog users： the ＂marionette＂ users, who are created or employed by backstage ＂puppeteers＂, either through programs or manually. Unlike normal users that...In this paper, we propose to detect a special group of microblog users： the ＂marionette＂ users, who are created or employed by backstage ＂puppeteers＂, either through programs or manually. Unlike normal users that access microblog for information sharing or social communication, the marionette users perform specific tasks to earn financial profits. For example, they follow certain users to increase their ＂statistical popularity＂, or retweet some tweets to amplify their ＂statistical impact＂. The fabricated follower or retweet counts not only mislead normal users to wrong information, but also seriously impair microblog-based applications, such as hot tweets selection and expert finding. In this paper, we study the important problem of detecting marionette users on microblog platforms. This problem is challenging because puppeteers are employing complicated strategies to generate marionette users that present similar behaviors as normal users. To tackle this challenge, we propose to take into account two types of discriminative information： 1） individual user tweeting behavior and 2） the social interactions among users. By integrating both information into a semi-supervised probabilistic model, we can effectively distinguish marionette users from normal ones. By applying the proposed model to one of the most popular microblog platforms （Sina Weibo） in China, we find that the model can detect marionette users with F-measure close to 0.9. In addition, we apply the proposed model to calculate the marionette ratio of the top 200 most followed microbloggers and the top 50 most retweeted posts in Sina Weibo. To accelerate the detecting speed and reduce feature generation cost, we further propose a light-weight model which utilizes fewer features to identify marionettes from retweeters.展开更多
Quantum error correction plays an important role in fault-tolerant quantum information processing.It is usually difficult to experimentally realize quantum error correction,as it requires multiple qubits and quantum g...Quantum error correction plays an important role in fault-tolerant quantum information processing.It is usually difficult to experimentally realize quantum error correction,as it requires multiple qubits and quantum gates with high fidelity.Here we propose a simple quantum error-correcting code for the detected amplitude damping channel.The code requires only two qubits.We implement the encoding,the channel,and the recovery on an optical platform,the IBM Q System,and a nuclear magnetic resonance system.For all of these systems,the error correction advantage appears when the damping rate exceeds some threshold.We compare the features of these quantum information processing systems used and demonstrate the advantage of quantum error correction on current quantum computing platforms.展开更多
Session-based recommender systems are increasingly applied to next-item recommendations.However,existing approaches encode the session information of each user independently and do not consider the interrelationship b...Session-based recommender systems are increasingly applied to next-item recommendations.However,existing approaches encode the session information of each user independently and do not consider the interrelationship between users.This work is based on the intuition that dynamic groups of like-minded users exist over time.By considering the impact of latent user groups,we can learn a user’s preference in a better way.To this end,we propose a recommendation model based on learning user embeddings by modeling long and short-term dynamic latent user groups.Specifically,we utilize two network units to learn users’long and short-term sessions,respectively.Meanwhile,we employ two additional units to determine the affiliation of users with specific latent groups,followed by an aggregation of these latent group representations.Finally,user preference representations are shaped comprehensively by considering all these four aspects,based on an attention mechanism.Moreover,to avoid setting the number of groups manually,we further incorporate an adaptive learning unit to assess the necessity for creating a new group and learn the representation of emerging groups automatically.Extensive experiments prove our model outperforms multiple state-of-the-art methods in terms of Recall,mean average precision(mAP),and area under curve(AUC)metrics.展开更多
Background. During the COVID-19 pandemic, mobile sensing and data analytics techniques have demonstrated their capabilitiesin monitoring the trajectories of the pandemic, by collecting behavioral, physiological, and m...Background. During the COVID-19 pandemic, mobile sensing and data analytics techniques have demonstrated their capabilitiesin monitoring the trajectories of the pandemic, by collecting behavioral, physiological, and mobility data on individual,neighborhood, city, and national scales. Notably, mobile sensing has become a promising way to detect individuals’ infectiousstatus, track the change in long-term health, trace the epidemics in communities, and monitor the evolution of viruses andsubspecies. Methods. We followed the PRISMA practice and reviewed 60 eligible papers on mobile sensing for monitoringCOVID-19. We proposed a taxonomy system to summarize literature by the time duration and population scale under mobilesensing studies. Results. We found that existing literature can be naturally grouped in four clusters, including remote detection,long-term tracking, contact tracing, and epidemiological study. We summarized each group and analyzed representative workswith regard to the system design, health outcomes, and limitations on techniques and societal factors. We further discussed theimplications and future directions of mobile sensing in communicable diseases from the perspectives of technology andapplications. Conclusion. Mobile sensing techniques are effective, efficient, and flexible to surveil COVID-19 in scales of timeand populations. In the post-COVID era, technical and societal issues in mobile sensing are expected to be addressed toimprove healthcare and social outcomes.展开更多
This paper studies the dynamics of online purchase patterns, focusing on the impact of the channel used on conversion probability, as well as the transition of channel use over time. A novel data set from a major Chin...This paper studies the dynamics of online purchase patterns, focusing on the impact of the channel used on conversion probability, as well as the transition of channel use over time. A novel data set from a major Chinese online travel agency is used for analysis, consisting of four months of data with 24,337 store visits through three types of channels： direct visit, search advertising and referral. Results of a Bayesian multinomial logit model show that the search channel significantly affects consumers＇ conversion probability, and show a high degree of inertia in channel use. This finding contrasts sharply with suggestions of previous research that most future purchases will converge to the direct-visit channel.展开更多
In this paper, we propose NeuS-PIR, a novel approach for learning relightable neural surfaces using pre-integrated rendering from multi-view image observations. Unlike traditional methods based on NeRFs or discrete me...In this paper, we propose NeuS-PIR, a novel approach for learning relightable neural surfaces using pre-integrated rendering from multi-view image observations. Unlike traditional methods based on NeRFs or discrete mesh representations, our approach employs an implicit neural surface representation to reconstruct high-quality geometry. This representation enables the factorization of the radiance field into two components: a spatially varying material field and an all-frequency lighting model. By jointly optimizing this factorization with a differentiable pre-integrated rendering framework, and material encoding regularization, our method effectively addresses the ambiguity in geometry reconstruction, leading to improved disentanglement and refinement of scene properties. Furthermore, we introduce a technique to distill indirect illumination fields, capturing complex lighting effects such as inter-reflections. As a result, NeuS-PIR enables advanced applications like relighting, which can be seamlessly integrated into modern graphics engines. Extensive qualitative and quantitative experiments on both synthetic and real datasets demonstrate that NeuS-PIR outperforms existing methods across various tasks. Source code is available at https://github.com/Sheldonmao/NeuSPIR.展开更多
文摘After more than 70 years of evolution,great achievements have been made in machine translation.Especially in recent years,translation quality has been greatly improved with the emergence of neural machine translation(NMT).In this article,we first review the history of machine translation from rule-based machine translation to example-based machine translation and statistical machine translation.We then introduce NMT in more detail,including the basic framework and the current dominant framework,Transformer,as well as multilingual translation models to deal with the data sparseness problem.In addition,we introduce cutting-edge simultaneous translation methods that achieve a balance between translation quality and latency.We then describe various products and applications of machine translation.At the end of this article,we briefly discuss challenges and future research directions in this field.
基金the Chinese National Natural Science Foundation Projects(61961160704,61876179)the Key Project of the General Logistics Department(ASW17C001)the Science and Technology Development Fund of Macao(0010/2019/AFJ,0025/2019/AKP).
文摘Background Gesture recognition has attracted significant attention because of its wide range of potential applications.Although multi-modal gesture recognition has made significant progress in recent years,a popular method still is simply fusing prediction scores at the end of each branch,which often ignores complementary features among different modalities in the early stage and does not fuse the complementary features into a more discriminative feature.Methods This paper proposes an Adaptive Cross-modal Weighting(ACmW)scheme to exploit complementarity features from RGB-D data in this study.The scheme learns relations among different modalities by combining the features of different data streams.The proposed ACmW module contains two key functions:(1)fusing complementary features from multiple streams through an adaptive one-dimensional convolution;and(2)modeling the correlation of multi-stream complementary features in the time dimension.Through the effective combination of these two functional modules,the proposed ACmW can automatically analyze the relationship between the complementary features from different streams,and can fuse them in the spatial and temporal dimensions.Results Extensive experiments validate the effectiveness of the proposed method,and show that our method outperforms state-of-the-art methods on IsoGD and NVGesture.
文摘In this paper, we propose to detect a special group of microblog users： the ＂marionette＂ users, who are created or employed by backstage ＂puppeteers＂, either through programs or manually. Unlike normal users that access microblog for information sharing or social communication, the marionette users perform specific tasks to earn financial profits. For example, they follow certain users to increase their ＂statistical popularity＂, or retweet some tweets to amplify their ＂statistical impact＂. The fabricated follower or retweet counts not only mislead normal users to wrong information, but also seriously impair microblog-based applications, such as hot tweets selection and expert finding. In this paper, we study the important problem of detecting marionette users on microblog platforms. This problem is challenging because puppeteers are employing complicated strategies to generate marionette users that present similar behaviors as normal users. To tackle this challenge, we propose to take into account two types of discriminative information： 1） individual user tweeting behavior and 2） the social interactions among users. By integrating both information into a semi-supervised probabilistic model, we can effectively distinguish marionette users from normal ones. By applying the proposed model to one of the most popular microblog platforms （Sina Weibo） in China, we find that the model can detect marionette users with F-measure close to 0.9. In addition, we apply the proposed model to calculate the marionette ratio of the top 200 most followed microbloggers and the top 50 most retweeted posts in Sina Weibo. To accelerate the detecting speed and reduce feature generation cost, we further propose a light-weight model which utilizes fewer features to identify marionettes from retweeters.
基金supported by the National Natural Science Foundation for the Youth of China (11804410)partial support by the Foundation for Polish Science (IRAP project, ICTQT, contract No. 2018/MAB/5, cofinanced by EU within the Smart Growth Operational Programme)+5 种基金supported by the National Natural Science Foundation of China (11574291, 11774334)supported by the National Natural Science Foundation of China (11975117, 11875159, 11905099, and U1801661)Guangdong Basic and Applied Basic Research Foundation (2019A1515011383)Guangdong Provincial Key Laboratory (2019B121203002)supported by National Natural Science Foundation of China (61771278)Beijing Institute of Technology Research Fund Program for Young Scholars
文摘Quantum error correction plays an important role in fault-tolerant quantum information processing.It is usually difficult to experimentally realize quantum error correction,as it requires multiple qubits and quantum gates with high fidelity.Here we propose a simple quantum error-correcting code for the detected amplitude damping channel.The code requires only two qubits.We implement the encoding,the channel,and the recovery on an optical platform,the IBM Q System,and a nuclear magnetic resonance system.For all of these systems,the error correction advantage appears when the damping rate exceeds some threshold.We compare the features of these quantum information processing systems used and demonstrate the advantage of quantum error correction on current quantum computing platforms.
基金supported by the National Natural Science Foundation of China(No.62202282)Shanghai Youth Science and Technology Talents Sailing Program(No.22YF1413700).
文摘Session-based recommender systems are increasingly applied to next-item recommendations.However,existing approaches encode the session information of each user independently and do not consider the interrelationship between users.This work is based on the intuition that dynamic groups of like-minded users exist over time.By considering the impact of latent user groups,we can learn a user’s preference in a better way.To this end,we propose a recommendation model based on learning user embeddings by modeling long and short-term dynamic latent user groups.Specifically,we utilize two network units to learn users’long and short-term sessions,respectively.Meanwhile,we employ two additional units to determine the affiliation of users with specific latent groups,followed by an aggregation of these latent group representations.Finally,user preference representations are shaped comprehensively by considering all these four aspects,based on an attention mechanism.Moreover,to avoid setting the number of groups manually,we further incorporate an adaptive learning unit to assess the necessity for creating a new group and learn the representation of emerging groups automatically.Extensive experiments prove our model outperforms multiple state-of-the-art methods in terms of Recall,mean average precision(mAP),and area under curve(AUC)metrics.
基金the National Cancer Institute of the National Institutes of Health under award numbers R01CA239246.
文摘Background. During the COVID-19 pandemic, mobile sensing and data analytics techniques have demonstrated their capabilitiesin monitoring the trajectories of the pandemic, by collecting behavioral, physiological, and mobility data on individual,neighborhood, city, and national scales. Notably, mobile sensing has become a promising way to detect individuals’ infectiousstatus, track the change in long-term health, trace the epidemics in communities, and monitor the evolution of viruses andsubspecies. Methods. We followed the PRISMA practice and reviewed 60 eligible papers on mobile sensing for monitoringCOVID-19. We proposed a taxonomy system to summarize literature by the time duration and population scale under mobilesensing studies. Results. We found that existing literature can be naturally grouped in four clusters, including remote detection,long-term tracking, contact tracing, and epidemiological study. We summarized each group and analyzed representative workswith regard to the system design, health outcomes, and limitations on techniques and societal factors. We further discussed theimplications and future directions of mobile sensing in communicable diseases from the perspectives of technology andapplications. Conclusion. Mobile sensing techniques are effective, efficient, and flexible to surveil COVID-19 in scales of timeand populations. In the post-COVID era, technical and societal issues in mobile sensing are expected to be addressed toimprove healthcare and social outcomes.
基金This research is supported by the National Natural Science Foundation of China （No. 71302172 and No. 71202145）.
文摘This paper studies the dynamics of online purchase patterns, focusing on the impact of the channel used on conversion probability, as well as the transition of channel use over time. A novel data set from a major Chinese online travel agency is used for analysis, consisting of four months of data with 24,337 store visits through three types of channels： direct visit, search advertising and referral. Results of a Bayesian multinomial logit model show that the search channel significantly affects consumers＇ conversion probability, and show a high degree of inertia in channel use. This finding contrasts sharply with suggestions of previous research that most future purchases will converge to the direct-visit channel.
基金supported by the National Natural Science Foundation of China(62472420).
文摘In this paper, we propose NeuS-PIR, a novel approach for learning relightable neural surfaces using pre-integrated rendering from multi-view image observations. Unlike traditional methods based on NeRFs or discrete mesh representations, our approach employs an implicit neural surface representation to reconstruct high-quality geometry. This representation enables the factorization of the radiance field into two components: a spatially varying material field and an all-frequency lighting model. By jointly optimizing this factorization with a differentiable pre-integrated rendering framework, and material encoding regularization, our method effectively addresses the ambiguity in geometry reconstruction, leading to improved disentanglement and refinement of scene properties. Furthermore, we introduce a technique to distill indirect illumination fields, capturing complex lighting effects such as inter-reflections. As a result, NeuS-PIR enables advanced applications like relighting, which can be seamlessly integrated into modern graphics engines. Extensive qualitative and quantitative experiments on both synthetic and real datasets demonstrate that NeuS-PIR outperforms existing methods across various tasks. Source code is available at https://github.com/Sheldonmao/NeuSPIR.
