Story generators typically adopt a pipelined model of generation wherein fabula structure is decided independently and prior to discourse structure. In this paper, we propose a novel story generator, PlotShot, capable of reasoning over discourse materials during fabula generation such that these materials meaningfully constrain the development of a causally and intentionally coherent story. PlotShot incorporates user-supplied photographs as optional story states through an oversubscription planning paradigm. Further, to leverage existing work on planning-based models of generation, we present a technique to compile the photo story planning problem to classical narrative planning. Our system attempts to maximize quality of an illustrated story by analyzing the affinity between a photo and the action it is meant to depict. An evaluation of generated artifacts shows advantage over heuristic baseline techniques.

Researchers often summarize their work in the form of posters. Posters provide a coherent and efficient way to convey core ideas from scientific papers. Generating a good scientific poster, however, is a complex and time consuming cognitive task, since such posters need to be readable, informative, and visually aesthetic. In this paper, for the first time, we study the challenging problem of learning to generate posters from scientific papers. To this end, a data-driven framework, that utilizes graphical models, is proposed. Specifically, given content to display, the key elements of a good poster, including panel layout and attributes of each panel, are learned and inferred from data. Then, given inferred layout and attributes, composition of graphical elements within each panel is synthesized. To learn and validate our model, we collect and make public a Poster-Paper dataset, which consists of scientific papers and corresponding posters with exhaustively labelled panels and attributes. Qualitative and quantitative results indicate the effectiveness of our approach.

We propose a novel learning framework for object categorization with interactive semantic feedback. In this framework, a discriminative categorization model improves through human-guided iterative semantic feedbacks. Specifically, the model identifies the most helpful relational semantic queries to discriminatively refine the model. The user feedback on whether the relationship is semantically valid or not is incorporated back into the model, in the form of regularization, and the process iterates. We validate the proposed model in a few-shot multi-class classification scenario, where we measure classification performance on a set of ‘target’ classes, with few training instances, by leveraging and transferring knowledge from ‘anchor’ classes, that contain larger set of labeled instances.

Player metrics are an invaluable resource for game designers and QA analysts who wish to understand players, monitor and improve game play, and test design hypotheses. Usually such metrics are collected in a straightforward manner by passively recording players; however, such an approach has several potential drawbacks. First, passive recording might fail to record metrics which correspond to an infrequent player behavior. Secondly, passive recording can be a costly, laborious, and memory intensive process, even with the aid of tools. In this paper, we explore the potential for an active approach to player metric collection which strives to collect data more efficiently, and thus with less cost. We use an online, iterative approach which models the relationship between player metrics and in-game situations probabilistically using a Markov Decision Process (MDP) and solves it for the best game configurations to run. To analyze the benefits and limitations of this approach, we implemented a system, called GAMELAB, for recording player metrics in Second Life.

Real-world AI systems have been recently deployed which can automatically analyze the plan and tactics of tennis players. As the game-state is updated regularly at short intervals (i.e. point-level), a library of successful and unsuccessful plans of a player can be learnt over time. Given the relative strengths and weaknesses of a player’s plans, a set of proven plans or tactics from the library that characterize a player can be identified. For low-scoring, continuous team sports like soccer, such analysis for multi-agent teams does not exist as the game is not segmented into “discretized” plays (i.e. plans), making it difficult to obtain a library that characterizes a team’s behavior. Additionally, as player tracking data is costly and difficult to obtain, we only have partial team tracings in the form of ball actions which makes this problem even more difficult. In this paper, we propose a method to overcome these issues by representing team behavior via play-segments, which are spatio-temporal descriptions of ball movement over fixed windows of time. Using these representations we can characterize team behavior from entropy maps, which give a measure of predictability of team behaviors across the field. We show the efficacy and applicability of our method on the 2010-2011 English Premier League soccer data.