These two papers have nice overview of recent works. First one explain recent architectures and introduce a state of the art method for video recognition problem and the second one analyze datasets, algorithms and evaluation metrics in a different perspective.

Little is known about what causes anti-social behavior online. The paper at hand analyzes vandalism and damage in Wikipedia with regard to the time it is conducted and the country it originates from. First, we identify vandalism and damaging edits via ex post facto evidence by mining Wikipedia’s revert graph. Second, we geolocate the cohort of edits from anonymous Wikipedia editors using their associated IP addresses and edit times, showing the feasibility of reliable historic geolocation with respect to country and time zone, even under limited geolocation data. Third, we conduct the first spatio-temporal analysis of vandalism on Wikipedia. Our analysis reveals significant differences for vandalism activities during the day, and for different days of the week, seasons, countries of origin, as well as Wikipedia’s languages. For the analyzed countries, the ratio is typically highest at non-summer workday mornings, with additional peaks after break times. We hence assume that Wikipedia vandalism is linked to labor, perhaps serving as relief from stress or boredom, whereas cultural differences have a large effect. Our results open up avenues for new research on collaborative writing at scale, and advanced technologies to identify and handle antisocial behavior in online communities.

The Temporal Network with Uncertainty (TNU) modeling framework is used to represent temporal knowledge in presence of qualitative temporal uncertainty. Dynamic Controllability (DC) is the problem of deciding the existence of a strategy for scheduling the controllable time points of the network observing past happenings only. In this paper, we address the DC problem for a very general class of TNU, namely Disjunctive Temporal Network with Uncertainty. We make the following contributions. First, we define strategies in the form of an executable language; second, we propose the first decision procedure to check whether a given strategy is a solution for the DC problem; third we present an efficient algorithm for strategy synthesis based on techniques derived from Timed Games and Satisfiability Modulo Theory. The experimental evaluation shows that the approach is superior to the state-of-the-art.

We represent knowledge as integrity constraints in a formalization of probabilistic spatio-temporal knowledge bases. We start by defining the syntax and semantics of a formalization called PST knowledge bases. This definition generalizes an earlier version, called SPOT, which is a declarative framework for the representation and processing of probabilistic spatio-temporal data where probability is represented as an interval because the exact value is unknown. We augment the previous definition by adding a type of non-atomic formula that expresses integrity constraints. The result is a highly expressive formalism for knowledge representation dealing with probabilistic spatio-temporal data. We obtain complexity results both for checking the consistency of PST knowledge bases and for answering queries in PST knowledge bases, and also specify tractable cases. All the domains in the PST framework are finite, but we extend our results also to arbitrarily large finite domains.

Accurate and efficient analysis of multivariate spatio-temporal data is critical in climatology, geology, and sociology applications. Existing models usually assume simple inter-dependence among variables, space, and time, and are computationally expensive. We propose a unified low rank tensor learning framework for multivariate spatio-temporal analysis, which can conveniently incorporate different properties in spatio-temporal data, such as spatial clustering and shared structure among variables. We demonstrate how the general framework can be applied to cokriging and forecasting tasks, and develop an efficient greedy algorithm to solve the resulting optimization problem with convergence guarantee. We conduct experiments on both synthetic datasets and real application datasets to demonstrate that our method is not only significantly faster than existing methods but also achieves lower estimation error.

Solving challenging computational problems involving time has been a critical component in the development of artificial intelligence systems almost since the inception of the field. This book provides a concise introduction to the core computational elements of temporal reasoning for use in AI systems for planning and scheduling, as well as systems that extract temporal information from data. It presents a survey of temporal frameworks based on constraints, both qualitative and quantitative, as well as of major temporal consistency techniques. The book also introduces the reader to more recent extensions to the core model that allow AI systems to explicitly represent temporal preferences and temporal uncertainty. This book is intended for students and researchers interested in constraint-based temporal reasoning.

Although satisfiability checking is known to be an effective approach in classical planning, it has scarcely been investigated in the field of temporal planning. Most notably, the usage of E-step semantics for encoding the problem into a SAT formula, while being demonstrably quite efficient for decreasing the size of the encodings in classical planning, has not yet been employed to tackle temporal planning problems. In this paper, we define temporal versions of classical A-step and E-step plans. We show that when the casual and temporal reasoning phases of a SAT-based temporal planner are separated, these semantics can be used to translate a given temporal planning problem into a SAT formula. We introduce two different types of E-step encodings in temporal planning. The first encoding method is a temporal version of the classical E-step encoding. Like its classical counterpart, in the new encoding we suppose a few restrictive simplifying assumptions. On the other hand, by relaxing one of these assumptions, the second type of E-step encodings, which is often more compact than the first one, is introduced. However, if a temporal planning problem possesses the property that we call required causal simultaneity, neither of our proposed encodings will be expressive enough to represent a valid temporal plan. Nevertheless, we show that this property is rather rare and can be detected in polynomial time. Our experiments indicate that by embedding the proposed encodings into ITSAT, a SAT-based temporal planner based on the A-step encoding, a considerable improvement is achieved in terms of both speed and memory usage of the planner. The resulting planner significantly outperforms POPF, which is currently the state-of-the-art of temporally expressive planners.

The ability to predict the future in a given domain can be acquired by discovering empirically from experience certain temporal patterns that tend to repeat unerringly. Previous works in time series analysis allow one to make quantitative predictions on the likely values of certain linear variables. Since certain types of knowledge are better expressed in symbolic forms, making qualitative predictions based on symbolic representations require a different approach. A domain independent methodology called TIM (Time based Inductive Machine) for discovering potentially uncertain temporal patterns from real time observations using the technique of inductive inference is described here.

In this work, we investigated the social media streams to understand their characteristics and their temporal aspects. We assumed that each blogger has different temporal preference for posting. To investigate this hypothesis, we analyzed a massive dataset, nearly 700,000 blog articles, with the consideration of two factors which are day of the week and time of the day. The comparison was done in manifold ways: Blogosphere vs. Twitter, commercial blogs vs. non-commercial blogs, and their individuals. We hope that this work provides a hint to develop a personalized system which can be used for the reduction of the system resources for pull/fetch technology.

Location sharing services (LSS) like Foursquare, Gowalla, and Facebook Places support hundreds of millions of user-driven footprints (i.e., "checkins"). Those global-scale footprints provide a unique opportunity to study the social and temporal characteristics of how people use these services and to model patterns of human mobility, which are significant factors for the design of future mobile+location-based services, traffic forecasting, urban planning, as well as epidemiological models of disease spread. In this paper, we investigate 22 million checkins across 220,000 users and report a quantitative assessment of human mobility patterns by analyzing the spatial, temporal, social, and textual aspects associated with these footprints. We find that: (i) LSS users follow the “Levy Flight” mobility pattern and adopt periodic behaviors; (ii) While geographic and economic constraints affect mobility patterns, so does individual social status; and (iii) Content and sentiment-based analysis of posts associated with checkins can provide a rich source of context for better understanding how users engage with these services.