Action recognition is an important yet challenging task in computer vision. In this paper, we propose a novel deep-based framework for action recognition, which improves the recognition accuracy by: 1) deriving more precise features for representing actions, and 2) reducing the asynchrony between different information streams. We first introduce a coarse-to-fine network which extracts shared deep features at different action class granularities and progressively integrates them to obtain a more accurate feature representation for input actions. We further introduce an asynchronous fusion network. It fuses information from different streams by asynchronously integrating stream-wise features at different time points, hence better leveraging the complementary information in different streams. Experimental results on action recognition benchmarks demonstrate that our approach achieves the state-of-the-art performance.
In this paper, we present a novel community sensing paradigm -- Community Sensing Without Aggregation. CSWA is designed to obtain the environment information (e.g., air pollution or temperature) in each subarea of the target area, without aggregating sensor and location data collected by community members. CSWA operates on top of a secured peer-to-peer network over the community members and proposes a novel \emphDecentralized Spatial-Temporal Compressive Sensing framework based on \emphParallelized Stochastic Gradient Descent. Through learning the \emphlow-rank structure via distributed optimization, CSWA approximates the value of the sensor data in each subarea (both covered and uncovered) for each sensing cycle using the sensor data locally stored in each member's mobile device. Simulation experiments based on real-world datasets demonstrate that CSWA exhibits low approximation error (i.e., less than $0.2 ^\circ$C in city-wide temperature sensing task and $10$ units of PM2.5 index in urban air pollution sensing) and performs comparably to (sometimes better than) state-of-the-art algorithms based on the data aggregation and centralized computation.
Spatial item recommendation has become an important means to help people discover interesting locations, especially when people pay a visit to unfamiliar regions. Some current researches are focusing on modelling individual and collective geographical preferences for spatial item recommendation based on users' check-in records, but they fail to explore the phenomenon of user interest drift across geographical regions, i.e., users would show different interests when they travel to different regions. Besides, they ignore the influence of public comments for subsequent users' check-in behaviors. Specifically, it is intuitive that users would refuse to check in to a spatial item whose historical reviews seem negative overall, even though it might fit their interests. Therefore, it is necessary to recommend the right item to the right user at the right location. In this paper, we propose a latent probabilistic generative model called LSARS to mimic the decision-making process of users' check-in activities both in home-town and out-of-town scenarios by adapting to user interest drift and crowd sentiments, which can learn location-aware and sentiment-aware individual interests from the contents of spatial items and user reviews. Due to the sparsity of user activities in out-of-town regions, LSARS is further designed to incorporate the public preferences learned from local users' check-in behaviors. Finally, we deploy LSARS into two practical application scenes: spatial item recommendation and target user discovery. Extensive experiments on two large-scale location-based social networks (LBSNs) datasets show that LSARS achieves better performance than existing state-of-the-art methods.
May 30 2017 cs.CV
Part-based representation has been proven to be effective for a variety of visual applications. However, automatic discovery of discriminative parts without object/part-level annotations is challenging. This paper proposes a discriminative mid-level representation paradigm based on the responses of a collection of part detectors, which only requires the image-level labels. Towards this goal, we first develop a detector-based spectral clustering method to mine the representative and discriminative mid-level patterns for detector initialization. The advantage of the proposed pattern mining technology is that the distance metric based on detectors only focuses on discriminative details, and a set of such grouped detectors offer an effective way for consistent pattern mining. Relying on the discovered patterns, we further formulate the detector learning process as a confidence-loss sparse Multiple Instance Learning (cls-MIL) task, which considers the diversity of the positive samples, while avoid drifting away the well localized ones by assigning a confidence value to each positive sample. The responses of the learned detectors can form an effective mid-level image representation for both image classification and object localization. Experiments conducted on benchmark datasets demonstrate the superiority of our method over existing approaches.
May 18 2017 cs.AI
Outlier detection is the identification of points in a dataset that do not conform to the norm. Outlier detection is highly sensitive to the choice of the detection algorithm and the feature subspace used by the algorithm. Extracting domain-relevant insights from outliers needs systematic exploration of these choices since diverse outlier sets could lead to complementary insights. This challenge is especially acute in an interactive setting, where the choices must be explored in a time-constrained manner. In this work, we present REMIX, the first system to address the problem of outlier detection in an interactive setting. REMIX uses a novel mixed integer programming (MIP) formulation for automatically selecting and executing a diverse set of outlier detectors within a time limit. This formulation incorporates multiple aspects such as (i) an upper limit on the total execution time of detectors (ii) diversity in the space of algorithms and features, and (iii) meta-learning for evaluating the cost and utility of detectors. REMIX provides two distinct ways for the analyst to consume its results: (i) a partitioning of the detectors explored by REMIX into perspectives through low-rank non-negative matrix factorization; each perspective can be easily visualized as an intuitive heatmap of experiments versus outliers, and (ii) an ensembled set of outliers which combines outlier scores from all detectors. We demonstrate the benefits of REMIX through extensive empirical validation on real-world data.
Apr 26 2017 cs.LG
Linear Discriminant Analysis (LDA) on Electronic Health Records (EHR) data is widely-used for early detection of diseases. Classical LDA for EHR data classification, however, suffers from two handicaps: the ill-posed estimation of LDA parameters (e.g., covariance matrix), and the "linear inseparability" of EHR data. To handle these two issues, in this paper, we propose a novel classifier FWDA -- Fast Wishart Discriminant Analysis, that makes predictions in an ensemble way. Specifically, FWDA first surrogates the distribution of inverse covariance matrices using a Wishart distribution estimated from the training data, then "weighted-averages" the classification results of multiple LDA classifiers parameterized by the sampled inverse covariance matrices via a Bayesian Voting scheme. The weights for voting are optimally updated to adapt each new input data, so as to enable the nonlinear classification. Theoretical analysis indicates that FWDA possesses a fast convergence rate and a robust performance on high dimensional data. Extensive experiments on large-scale EHR dataset show that our approach outperforms state-of-the-art algorithms by a large margin.
During the course of human language evolution, the semantic meanings of words keep evolving with time. The understanding of evolving semantics enables us to capture the true meaning of the words in different usage contexts, and thus is critical for various applications, such as machine translation. While it is naturally promising to study word semantics in a time-aware manner, traditional methods to learn word vector representation do not adequately capture the change over time. To this end, in this paper, we aim at learning time-aware vector representation of words through dynamic word embedding modeling. Specifically, we first propose a method that captures time-specific semantics and across-time alignment simultaneously in a way that is robust to data sparsity. Then, we solve the resulting optimization problem using a scalable coordinate descent method. Finally, we perform the empirical study on New York Times data to learn the temporal embeddings and develop multiple evaluations that illustrate the semantic evolution of words, discovered from news media. Moreover, our qualitative and quantitative tests indicate that the our method not only reliably captures the semantic evolution over time, but also onsistently outperforms state-of-the-art temporal embedding approaches on both semantic accuracy and alignment quality.
Nov 22 2016 cs.RO
Human ability of both versatile grasping of given objects and grasping of novel (as of yet unseen) objects is truly remarkable. This probably arises from the experience infants gather by actively playing around with diverse objects. Moreover, knowledge acquired during this process is reused during learning of how to grasp novel objects. We conjecture that this combined process of active and transfer learning boils down to a random search around an object, suitably biased by prior experience, to identify promising grasps. In this paper we present an active learning method for learning of grasps for given objects, and a transfer learning method for learning of grasps for novel objects. Our learning methods apply a kernel adaptive Metropolis-Hastings sampler that learns an approximation of the grasps' probability density of an object while drawing grasp proposals from it. The sampler employs simulated annealing to search for globally-optimal grasps. Our empirical results show promising applicability of our proposed learning schemes.
Oct 19 2016 cs.LG
To improve the performance of Linear Discriminant Analysis (LDA) for early detection of diseases using Electronic Health Records (EHR) data, we propose \TheName -- a novel framework for \emph\underlineEHR based \underlineEarly \underlineDetection of \underlineDiseases on top of \emphCovariance-Regularized LDA models. Specifically, \TheName employs a \emphnon-sparse inverse covariance matrix (or namely precision matrix) estimator derived from graphical lasso and incorporates the estimator into LDA classifiers to improve classification accuracy. Theoretical analysis on \TheName shows that it can bound the expected error rate of LDA classification, under certain assumptions. Finally, we conducted extensive experiments using a large-scale real-world EHR dataset -- CHSN. We compared our solution with other regularized LDA and downstream classifiers. The result shows \TheName outperforms all baselines and backups our theoretical analysis.
Jul 26 2016 cs.LG
Matrix sketching is aimed at finding close approximations of a matrix by factors of much smaller dimensions, which has important applications in optimization and machine learning. Given a matrix A of size m by n, state-of-the-art randomized algorithms take O(m * n) time and space to obtain its low-rank decomposition. Although quite useful, the need to store or manipulate the entire matrix makes it a computational bottleneck for truly large and dense inputs. Can we sketch an m-by-n matrix in O(m + n) cost by accessing only a small fraction of its rows and columns, without knowing anything about the remaining data? In this paper, we propose the cascaded bilateral sampling (CABS) framework to solve this problem. We start from demonstrating how the approximation quality of bilateral matrix sketching depends on the encoding powers of sampling. In particular, the sampled rows and columns should correspond to the code-vectors in the ground truth decompositions. Motivated by this analysis, we propose to first generate a pilot-sketch using simple random sampling, and then pursue more advanced, "follow-up" sampling on the pilot-sketch factors seeking maximal encoding powers. In this cascading process, the rise of approximation quality is shown to be lower-bounded by the improvement of encoding powers in the follow-up sampling step, thus theoretically guarantees the algorithmic boosting property. Computationally, our framework only takes linear time and space, and at the same time its performance rivals the quality of state-of-the-art algorithms consuming a quadratic amount of resources. Empirical evaluations on benchmark data fully demonstrate the potential of our methods in large scale matrix sketching and related areas.
May 26 2016 cs.IR
Advances in smartphone technology have promoted the rapid development of mobile apps. However, the availability of a huge number of mobile apps in application stores has imposed the challenge of finding the right apps to meet the user needs. Indeed, there is a critical demand for personalized app recommendations. Along this line, there are opportunities and challenges posed by two unique characteristics of mobile apps. First, app markets have organized apps in a hierarchical taxonomy. Second, apps with similar functionalities are competing with each other. While there are a variety of approaches for mobile app recommendations, these approaches do not have a focus on dealing with these opportunities and challenges. To this end, in this paper, we provide a systematic study for addressing these challenges. Specifically, we develop a Structural User Choice Model (SUCM) to learn fine-grained user preferences by exploiting the hierarchical taxonomy of apps as well as the competitive relationships among apps. Moreover, we design an efficient learning algorithm to estimate the parameters for the SUCM model. Finally, we perform extensive experiments on a large app adoption data set collected from Google Play. The results show that SUCM consistently outperforms state-of-the-art top-N recommendation methods by a significant margin.
Mobile phone data have recently become an attractive source of information about mobility behavior. Since cell phone data can be captured in a passive way for a large user population, they can be harnessed to collect well-sampled mobility information. In this paper, we propose CT-Mapper, an unsupervised algorithm that enables the mapping of mobile phone traces over a multimodal transport network. One of the main strengths of CT-Mapper is its capability to map noisy sparse cellular multimodal trajectories over a multilayer transportation network where the layers have different physical properties and not only to map trajectories associated with a single layer. Such a network is modeled by a large multilayer graph in which the nodes correspond to metro/train stations or road intersections and edges correspond to connections between them. The mapping problem is modeled by an unsupervised HMM where the observations correspond to sparse user mobile trajectories and the hidden states to the multilayer graph nodes. The HMM is unsupervised as the transition and emission probabilities are inferred using respectively the physical transportation properties and the information on the spatial coverage of antenna base stations. To evaluate CT-Mapper we collected cellular traces with their corresponding GPS trajectories for a group of volunteer users in Paris and vicinity (France). We show that CT-Mapper is able to accurately retrieve the real cell phone user paths despite the sparsity of the observed trace trajectories. Furthermore our transition probability model is up to 20% more accurate than other naive models.
The problem of software artifact retrieval has the goal to effectively locate software artifacts, such as a piece of source code, in a large code repository. This problem has been traditionally addressed through the textual query. In other words, information retrieval techniques will be exploited based on the textual similarity between queries and textual representation of software artifacts, which is generated by collecting words from comments, identifiers, and descriptions of programs. However, in addition to these semantic information, there are rich information embedded in source codes themselves. These source codes, if analyzed properly, can be a rich source for enhancing the efforts of software artifact retrieval. To this end, in this paper, we develop a feature extraction method on source codes. Specifically, this method can capture both the inherent information in the source codes and the semantic information hidden in the comments, descriptions, and identifiers of the source codes. Moreover, we design a heterogeneous metric learning approach, which allows to integrate code features and text features into the same latent semantic space. This, in turn, can help to measure the artifact similarity by exploiting the joint power of both code and text features. Finally, extensive experiments on real-world data show that the proposed method can help to improve the performances of software artifact retrieval with a significant margin.
In this note, we prove a conjecture proposed by Tao Zhang, Shuxing Li, Tao Feng and Gennian Ge, IEEE Transaction on Information Theory, vol. 60, no. 5, May 2014. This conjecture is about the cross correlation distribution of ternary $m$-sequences.
Sep 09 2013 cs.CR
In this paper, a new method is presented to compute the 2-adic complexity of pseudo-random sequences. With this method, the 2-adic complexities of all the known sequences with ideal 2-level autocorrelation are uniformly determined. Results show that their 2-adic complexities equal their periods. In other words, their 2-adic complexities attain the maximum. Moreover, 2-adic complexities of two classes of optimal autocorrelation sequences with period $N\equiv1\mod4$, namely Legendre sequences and Ding-Helleseth-Lam sequences, are investigated. Besides, this method also can be used to compute the linear complexity of binary sequences regarded as sequences over other finite fields.
The Internet of Things (IoT) aims at interconnecting everyday objects (including both things and users) and then using this connection information to provide customized user services. However, IoT does not work in its initial stages without adequate acquisition of user preferences. This is caused by cold-start problem that is a situation where only few users are interconnected. To this end, we propose CRUC scheme - Cold-start Recommendations Using Collaborative Filtering in IoT, involving formulation, filtering and prediction steps. Extensive experiments over real cases and simulation have been performed to evaluate the performance of CRUC scheme. Experimental results show that CRUC efficiently solves the cold-start problem in IoT.
Understanding the behaviors of information propagation is essential for the effective exploitation of social influence in social networks. However, few existing influence models are both tractable and efficient for describing the information propagation process and quantitatively measuring social influence. To this end, in this paper, we develop a linear social influence model, named Circuit due to its close relation to the circuit network. Based on the predefined four axioms of social influence, we first demonstrate that our model can efficiently measure the influence strength between any pair of nodes. Along this line, an upper bound of the node(s)' influence is identified for potential use, e.g., reducing the search space. Furthermore, we provide the physical implication of the Circuit model and also a deep analysis of its relationships with the existing methods, such as PageRank. Then, we propose that the Circuit model provides a natural solution to the problems of computing each single node's authority and finding a set of nodes for social influence maximization. At last, the effectiveness of the proposed model is evaluated on the real-world data. The extensive experimental results demonstrate that Circuit model consistently outperforms the state-of-the-art methods and can greatly alleviate the computation burden of the influence maximization problem.
Understanding the behaviors of information propagation is essential for the effective exploitation of social influence in social networks. However, few existing influence models are tractable and efficient for describing the information propagation process, especially when dealing with the difficulty of incorporating the effects of combined influences from multiple nodes. To this end, in this paper, we provide a social influence model that alleviates this obstacle based on electrical circuit theory. This model vastly improves the efficiency of measuring the influence strength between any pair of nodes, and can be used to interpret the real-world influence propagation process in a coherent way. In addition, this circuit theory model provides a natural solution to the social influence maximization problem. When applied to realworld data, the circuit theory model consistently outperforms the state-of-the-art methods and can greatly alleviate the computation burden of the influence maximization problem.
We investigate the problem of designing delay-aware joint flow control, routing, and scheduling algorithms in general multi-hop networks for maximizing network utilization. Since the end-to-end delay performance has a complex dependence on the high-order statistics of cross-layer algorithms, earlier optimization-based design methodologies that optimize the long term network utilization are not immediately well-suited for delay-aware design. This motivates us in this work to develop a novel design framework and alternative methods that take advantage of several unexploited design choices in the routing and the scheduling strategy spaces. In particular, we reveal and exploit a crucial characteristic of back pressure-type controllers that enables us to develop a novel link rate allocation strategy that not only optimizes long-term network utilization, but also yields loop free multi-path routes between each source-destination pair. Moreover, we propose a regulated scheduling strategy, based on a token-based service discipline, for shaping the per-hop delay distribution to obtain highly desirable end-to-end delay performance. We establish that our joint flow control, routing, and scheduling algorithm achieves loop-free routes and optimal network utilization. Our extensive numerical studies support our theoretical results, and further show that our joint design leads to substantial end-to-end delay performance improvements in multi-hop networks compared to earlier solutions.
A privacy-preserving English auction protocol with round efficiency based on a modified ring signature has been proposed in this paper. The proposed protocol has three appealing characteristic: First, it offers conditional privacy-preservation: on the one hand, the bidder is anonymous to the public, on the other hand, only the collaboration of auctioneer and registration manager can reveal the true identity of a malicious bidder. Second, it does not require to maintain a black list which records the evicted malicious bidders. Finally, it is efficient: it saves the communication round complexity comparing with previously proposed solutions.
Aug 31 2010 cs.CR
In this paper, we introduce an efficient and trustworthy conditional privacy-preserving communication protocol for VANETs based on proxy re-signature. The proposed protocol is characterized by the Trusted Authority (TA) designating the Roadside Units (RSUs) to translate signatures computed by the On-Board Units (OBUs) into one that are valid with respect to TA's public key. In addition, the proposed protocol offers both a priori and a posteriori countermeasures: it can not only provide fast anonymous authentication and privacy tracking, but guarantees message trustworthiness for vehicle-to-vehicle (V2V) communications. Furthermore, it reduces the communication overhead and offers fast message authentication and, low storage requirements. We use extensive analysis to demonstrate the merits of the proposed protocol and to contrast it with previously proposed solutions.
May 13 2010 cs.LG
In this paper, we formulate a novel problem for finding blackhole and volcano patterns in a large directed graph. Specifically, a blackhole pattern is a group which is made of a set of nodes in a way such that there are only inlinks to this group from the rest nodes in the graph. In contrast, a volcano pattern is a group which only has outlinks to the rest nodes in the graph. Both patterns can be observed in real world. For instance, in a trading network, a blackhole pattern may represent a group of traders who are manipulating the market. In the paper, we first prove that the blackhole mining problem is a dual problem of finding volcanoes. Therefore, we focus on finding the blackhole patterns. Along this line, we design two pruning schemes to guide the blackhole finding process. In the first pruning scheme, we strategically prune the search space based on a set of pattern-size-independent pruning rules and develop an iBlackhole algorithm. The second pruning scheme follows a divide-and-conquer strategy to further exploit the pruning results from the first pruning scheme. Indeed, a target directed graphs can be divided into several disconnected subgraphs by the first pruning scheme, and thus the blackhole finding can be conducted in each disconnected subgraph rather than in a large graph. Based on these two pruning schemes, we also develop an iBlackhole-DC algorithm. Finally, experimental results on real-world data show that the iBlackhole-DC algorithm can be several orders of magnitude faster than the iBlackhole algorithm, which has a huge computational advantage over a brute-force method.
This paper introduces an efficient and spontaneous privacy-preserving protocol for vehicular ad-hoc networks based on revocable ring signature. The proposed protocol has three appealing characteristics: First, it offers conditional privacy-preservation: while a receiver can verify that a message issuer is an authorized participant in the system only a trusted authority can reveal the true identity of a message sender. Second, it is spontaneous: safety messages can be authenticated locally, without support from the roadside units or contacting other vehicles. Third, it is efficient by offering fast message authentication and verification, cost-effective identity tracking in case of a dispute, and low storage requirements. We use extensive analysis to demonstrate the merits of the proposed protocol and to contrast it with previously proposed solutions.