Mesoscale ocean eddies are a critical component of the Earth System as they dominate the ocean's kinetic energy and impact the global distribution of oceanic heat, salinity, momentum, and nutrients. Therefore, accurately representing these dynamic features is critical for our planet's sustainability. The majority of methods that identify eddies from satellite observations analyze the data in a frame-by-frame basis despite the fact that eddies are dynamic objects that propagate across space and time. We introduce the notion of spatio-temporal consistency to identify eddies in a continuous spatio-temporal field, to simultaneously ensure that the features detected are both spatially and temporally consistent. Our spatio-temporal consistency approach allows us to remove most of the expert criteria used in traditional methods to reduce false negatives. The removal of arbitrary heuristics enables us to render more complete eddy dynamics by identifying smaller and longer lived eddies compared to existing methods.

Extracting emotions from images has attracted much interest, in particular with the rapid development of social networks. The emotional impact is very important for understanding the intrinsic meanings of images. Despite many studies having been done, most existing methods focus on image content, but ignore the emotion of the user who published the image. One interesting question is: How does social effect correlate with the emotion expressed in an image? Specifically, can we leverage friends interactions (e.g., discussions) related to an image to help extract the emotions? In this paper, we formally formalize the problem and propose a novel emotion learning method by jointly modeling images posted by social users and comments added by their friends. One advantage of the model is that it can distinguish those comments that are closely related to the emotion expression for an image from the other irrelevant ones. Experiments on an open Flickr dataset show that the proposed model can significantly improve (+37.4% by F1) the accuracy for inferring user emotions. More interestingly, we found that half of the improvements are due to interactions between 1.0% of the closest friends.

Indeed, to the best of our knowledge, we lack forgotten over time (Wu and Humberman 2007). For example, a probabilistic framework to model and predict the popularity videos on YouTube or stories on Digg gain their popularity dynamics of individual items. The reason behind this is by striving for views or votes (Szabo and Huberman partly illustrated in Figure 1, suggesting that the dynamical 2010); papers increase their visibility by competing for citations processes governing individual items appear too noisy to be from new papers (Ren et al. 2010; Wang, Song, and amenable to quantification. Barabási 2013); tweets or Hashtags in Twitter become more In this paper, we model the stochastic popularity dynamics popular as being retweeted (Hong, Dan, and Davison 2011) using reinforced Poisson processes, capturing simultaneously and so do webpages as being attached by incoming hyperlinks three key ingredients: fitness of an item, characterizing (Ratkiewicz et al. 2010). An ability to predict the popularity its inherent competitiveness against other items; a general of individual items within a dynamically evolving system temporal relaxation function, corresponding to the aging not only probes our understanding of complex systems, in the ability to attract new attentions; and a reinforcement but also has important implications in a wide range of domains, mechanism, documenting the well-known "rich-get-richer" from marketing and traffic control to policy making phenomenon. The benefit of the proposed model is threefold: and risk management. Despite recent advances of empirical (1) It models the arrival process of individual attentions methods, we lack a general modeling framework to predict directly in contrast to relying on aggregated popularity the popularity of individual items within a complex evolving time series; (2) As a generative probabilistic model, it can be system.

This paper presents a semi-automated methodology for generating geometric proof problems of the kind found in a high-school curriculum. We formalize the notion of a geometry proof problem and describe an algorithm for generating such problems over a user-provided figure. Our experimental results indicate that our problem generation algorithm can effectively generate proof problems in elementary geometry. On a corpus of 110 figures taken from popular geometry textbooks, our system generated an average of about 443 problems per figure in an average time of 4.7 seconds per figure.

We study the problem of instance alignment between knowledge bases (KBs). Existing approaches, exploiting the “symmetry” of structure and information across KBs, suffer in the presence of asymmetry, which is frequent as KBs are independently built. Specifically, we observe three types of asymmetries (in concepts, in features, and in structures). Our goal is to identify key techniques to reduce accuracy loss caused by each type of asymmetry, then design Asymmetry-Resistant Instance Alignment framework (ARIA). ARIA uses two-phased blocking methods considering concept and feature asymmetries, with a novel similarity measure overcoming structure asymmetry. Compared to a state-of-the-art method, ARIA increased precision by 19% and recall by 2%, and decreased processing time by more than 80% in matching large-scale real-life KBs.

Although users' preference is semantically reflected in the free-form review texts, this wealth of information was not fully exploited for learning recommender models. Specifically, almost all existing recommendation algorithms only exploit rating scores in order to find users' preference, but ignore the review texts accompanied with rating information. In this paper, we propose a novel matrix factorization model (called TopicMF) which simultaneously considers the ratings and accompanied review texts. Experimental results on 22 real-world datasets show the superiority of our model over the state-of-the-art models, demonstrating its effectiveness for recommendation tasks.

In this work, we propose a novel node splitting method for regression trees and incorporate it into the regression forest framework. Unlike traditional binary splitting, where the splitting rule is selected from a predefined set of binary splitting rules via trial-and-error, the proposed node splitting method first finds clusters of the training data which at least locally minimize the empirical loss without considering the input space. Then splitting rules which preserve the found clusters as much as possible are determined by casting the problem into a classification problem. Consequently, our new node splitting method enjoys more freedom in choosing the splitting rules, resulting in more efficient tree structures. In addition to the Euclidean target space, we present a variant which can naturally deal with a circular target space by the proper use of circular statistics. We apply the regression forest employing our node splitting to head pose estimation (Euclidean target space) and car direction estimation (circular target space) and demonstrate that the proposed method significantly outperforms state-of-the-art methods (38.5% and 22.5% error reduction respectively).

The main focus of our work is the use of classical planning algorithms in service of more complex problems of planning under uncertainty. In particular, we are exploring compilation techniques that allow us to reduce some probabilistic planning problems into variants of classical planning, such as metric planning,resource-bounded planning, and cost-bounded suboptimal planning. Currently, our initial work focuses on \emph{conformant probabilistic planning}. We intend toimprove our current methods by improving our compilation methods, but also by improving the ability of current planners to handle the special features ofour compiled problems. Then, we hope to extend these techniques to handle more complex probabilistic settings, such as problems with stochastic actions andpartial observability.

In real world planning problems, it might not be possible for an automated agent to satisfy all the objectives assigned to it because available resources are limited. When objectives cannot all be satisfied, classical planning returns no plan. In partial satisfaction planning, it is possible to satisfy only a subset of the objectives. To solve this kind of problems, an agent could select the objectives subset and the plan that maximizes the net benefit, i.e. the sum of satisfied objectives utilities minus the sum of the cost of actions. This approach has been experimented for deterministic planning. This paper extends partial satisfaction planning for problems with uncertainty on time. For problems under uncertainty, the best subset of objectives may not be calculated at planning time. The effective duration of actions at execution time may dynamically influence the achievable subset of objectives. Our approach introduces special actions to explicitly abort objectives. This enables control on when an objective is aborted.

Consider a family whose home is equipped with several service robots. The actions planned for the robots must adhere to Interaction Constraints (ICs) relating them to human activities and preferences. These constraints must be sufficiently expressive to model both temporal and logical dependencies among robot actions and human behavior, and must accommodate incomplete information regarding human activities. In this paper we introduce an approach for automatically generating plans that are conformant wrt. given ICs and partially specified human activities. The approach allows to separate causal reasoning about actions from reasoning about ICs, and we illustrate the computational advantage this brings with experiments on a large-scale (semi-)realistic household domain with hundreds of human activities and several robots.