In this paper, we propose a new local spatio-temporal descriptor for videos and we propose a new approach for action recognition in videos based on the introduced descriptor. The new descriptor is called the Video Covariance Matrix Logarithm (VCML). The VCML descriptor is based on a covariance matrix representation, and it models relationships between different low-level features, such as intensity and gradient. We apply the VCML descriptor to encode appearance information of local spatio-temporal video volumes, which are extracted by the Dense Trajectories. Then, we present an extensive evaluation of the proposed VCML descriptor with the Fisher vector encoding and the Support Vector Machines on four challenging action recognition datasets. We show that the VCML descriptor achieves better results than the state-of-the-art appearance descriptors. Moreover, we present that the VCML descriptor carries complementary information to the HOG descriptor and their fusion gives a significant improvement in action recognition accuracy. Finally, we show that the VCML descriptor improves action recognition accuracy in comparison to the state-of-the-art Dense Trajectories, and that the proposed approach achieves superior performance to the state-of-the-art methods.

Representation learning has shown its effectiveness in many tasks such as image classification and text mining. Network representation learning aims at learning distributed vector representation for each vertex in a network, which is also increasingly recognized as an important aspect for network analysis. Most network representation learning methods investigate network structures for learning. In reality, network vertices contain rich information (such as text), which cannot be well applied with algorithmic frameworks of typical representation learning methods. By proving that DeepWalk, a state-of-the-art network representation method, is actually equivalent to matrix factorization (MF), we propose text-associated DeepWalk (TADW). TADW incorporates text features of vertices into network representation learning under the framework of matrix factorization. We evaluate our method and various baseline methods by applying them to the task of multi-class classification of vertices. The experimental results show that, our method outperforms other baselines on all three datasets, especially when networks are noisy and training ratio is small.

Community detection on social media is a classic and challenging task. In this paper, we study the problem of detecting communities by combining social relations and user generated content in social networks. We propose a nonnegative matrix tri-factorization (NMTF) based clustering framework with three types of graph regularization. The NMTF based clustering framework can combine the relations and content seamlessly and the graph regularization can capture user similarity, message similarity and user interaction explicitly. In order to design regularization components, we further exploit user similarity and message similarity in social networks. A unified optimization problem is proposed by integrating the NMTF framework and the graph regularization. Then we derive an iterative learning algorithm for this optimization problem. Extensive experiments are conducted on three real-world data sets and the experimental results demonstrate the effectiveness of the proposed method.

The rapidly growing of Location-based Social Networks (LBSNs) provides a vast amount of check-in data, which enables many services, e.g., point-of-interest (POI) recommendation. In this paper, we study the next new POI recommendation problem in which new POIs with respect to users' current location are to be recommended. The challenge lies in the difficulty in precisely learning users' sequential information and personalizing the recommendation model. To this end, we resort to the Metric Embedding method for the recommendation, which avoids drawbacks of the Matrix Factorization technique. We propose a personalized ranking metric embedding method (PRME) to model personalized check-in sequences. We further develop a PRME-G model, which integrates sequential information, individual preference, and geographical influence, to improve the recommendation performance. Experiments on two real-world LBSN datasets demonstrate that our new algorithm outperforms the state-of-the-art next POI recommendation methods.

The triad is one of the most basic human groups in social networks. Understanding factors affecting the formation of triads will help reveal the underlying mechanisms that govern the emergence and evolution of complex social networks. In this paper, we study an interesting problem of decoding triadic closure in social networks. Specifically, for a given closed triad (a group of three people who are friends with each other), which link was created first, which followed, and which link closed. The problem is challenging, as we may not have any dynamic information. Moreover, the closure processes of different triads are correlated with each other. Our technical contribution lies in the proposal of a probabilistic factor graph model (DeTriad). The model is able to recover the dynamic information in the triadic closure process. It also naturally models the correlations among closed triads. We evaluate the proposed model on a large collaboration network, and the experimental results show that our method improves the accuracy of decoding triadic closure by up to 20% over that of several alternative methods.

Inverse optimal control (IOC) is a powerful approach for learning robotic controllers from demonstration that estimates a cost function which rationalizes demonstrated control trajectories. Unfortunately, its applicability is difficult in settings where optimal control can only be solved approximately. While local IOC approaches have been shown to successfully learn cost functions in such settings, they rely on the availability of good reference trajectories, which might not be available at test time. We address the problem of using IOC in these computationally challenging control tasks by using a graph-based discretization of the trajectory space. Our approach projects continuous demonstrations onto this discrete graph, where a cost function can be tractably learned via IOC. Discrete control trajectories from the graph are then projected back to the original space and locally optimized using the learned cost function. We demonstrate the effectiveness of the approach with experiments conducted on two 7-degree of freedom robotic arms.

We present Saul, a new probabilistic programming language designed to address some of the shortcomings of programming languages that aim at advancing and simplifying the development of AI systems. Such languages need to interact with messy, naturally occurring data, to allow a programmer to specify what needs to be done at an appropriate level of abstraction rather than at the data level, to be developed on a solid theory that supports moving to and reasoning at this level of abstraction and, finally, to support flexible integration of these learning and inference models within an application program. Saul is an object-functional programming language written in Scala that facilitates these by (1) allowing a programmer to learn, name and manipulate named abstractions over relational data; (2) supporting seamless incorporation of trainable (probabilistic or discriminative) components into the program, and (3) providing a level of inference over trainable models to support composition and make decisions that respect domain and application constraints. Saul is developed over a declaratively defined relational data model, can use piecewise learned factor graphs with declaratively specified learning and inference objectives, and it supports inference over probabilistic models augmented with declarative knowledge-based constraints.We describe the key constructs of Saul and exemplify its use in developing applications that require relational feature engineering and structured output prediction.

In this paper we focus on the greedy matrix completion problem. A simple atom selection strategy is proposed building upon an alternating minimization procedure. Based on this per-iteration strategy, we devise a greedy algorithm OAMC and establish an upper bound of the approximation error. To evaluate different weight refinement methods, several variants of OAMC are designed. We prove that OAMC and three of its variants have the property of linear convergence. Experiments of Recommendation and Image Recovery are conducted to make empirical evaluation. Results are promising. We report that our algorithm takes only 700 seconds to process Yahoo Music dataset in PC, yet achieves a root mean square error 24.5 on test set.

As compared to simple actions, activities are much more complex, but semantically consistent with a human's real life. Techniques for action recognition from sensor generated data are mature. However, there has been relatively little work on bridging the gap between actions and activities. To this end, this paper presents a novel approach for complex activity recognition comprising of two components. The first component is temporal pattern mining, which provides a mid-level feature representation for activities, encodes temporal relatedness among actions, and captures the intrinsic properties of activities. The second component is adaptive Multi-Task Learning, which captures relatedness among activities and selects discriminant features. Extensive experiments on a real-world dataset demonstrate the effectiveness of our work.

Sentiment classification aims to automatically predict sentiment polarity (e.g., positive or negative) of user generated sentiment data (e.g., reviews, blogs). In real applications, these user generated sentiment data can span so many different domains that it is difficult to manually label training data for all of them. Hence, this paper studies the problem of domain adaptation for sentiment classification where a systemtrained using labeled reviews from a source domain is deployed to classify sentimentsof reviews in a different target domain. In this paper, we propose to link heterogeneous input features with pivots via joint non-negative matrix factorization. This is achieved by learning the domain-specific information from different domains into unified topics, with the help of pivots across all domains. We conduct experiments on a benchmark composed of reviews of 4 types of Amazon products. Experimental results show that our proposed approach significantly outperforms the baseline method, and achieves an accuracy which is competitive with the state-of-the-art methods for sentiment classification adaptation.