A large number of images with ground truth object bounding boxes are critical for learning object detectors, which is a fundamental task in compute vision. In this paper, we study strategies to crowd-source bounding box annotations. The core challenge of building such a system is to effectively control the data quality with minimal cost. Our key observation is that drawing a bounding box is significantly more difficult and time consuming than giving answers to multiple choice questions. Thus quality control through additional verification tasks is more cost effective than consensus based algorithms. In particular, we present a system that consists of three simple sub-tasks --- a drawing task, a quality verification task and a coverage verification task. Experimental results demonstrate that our system is scalable, accurate, and cost-effective.

To ensure quality results from crowdsourced tasks requesters often aggregate worker responses and use one of a plethora of strategies for the process of inferring the correct answer from the set of noisy responses. However, all current models assume prior knowledge of all possible outcomes of the task. While not an unreasonable assumption for tasks that can be posited as multiple-choice questions (e.g. n-ary classification), we observe that many tasks do not naturally fit this paradigm, but instead demand a free-response, generalized, formulation where the outcome space is of infinite size (e.g. audio transcription). We call these tasks open questions. We model open questions with a novel probabilistic graphical model, and design and implement LazySusan, a decision-theoretic controller that dynamically requests responses as necessary in order to infer answers to these tasks. Live experiments on Amazon Mechanical Turk demonstrate the superiority of LazySusan at solving SAT Math questions, eliminating 83.2% of the error and achieving greater net utility compared to the state-of-the-art strategy, majority voting.

Reaching for a target requires estimating the spatial position of the target and to convert such a position in a suitable arm-motor command. In the proposed framework, the location of the target is represented implicitly by the gaze direction of the robot and by the distance of the target. The NAO robot is provided with two cameras, one to look ahead and one to look down, which constitute two independent head-centered coordinate systems. These head-centered frames of reference are converted into reaching commands by two neural networks. The weights of networks are learned by moving the arm while gazing the hand, using an on-line learning algorithm that maintains the covariance matrix of weights. This work adapts a previously proposed model that worked on a full humanoid robot torso, to work with the NAO and is a step toward a more generic framework for the implicit representation of the peripersonal space in humanoid robots.

We introduce a laboratory text on environmental and societal sustainability applications that can be a supplemental resource for any undergraduate AI course. The lab text, entitled Artificial Intelligence for Computational Sustainability: A Lab Companion, is brand new and incomplete; freely available through Wikibooks; and open to community additions of projects, assignments, and explanatory material on AI for sustainability. The project adds to existing educational efforts of the computational sustainability community, encouraging the flow of knowledge from research to education and public outreach. Besides summarizing the laboratory book, this paper touches on its implications for integration of research and education, for communicating science to the public, and other broader impacts.

Experience using computational perception within the context of art and performance is reported. Four different types of pedagogical projects are presented: a new non-majors introductory computing course, an upper-level course covering computer vision and graphics inan integrated manner, an interactive dance piece, and a peer-led tele-workshop outreach series.

In an Artificial Intelligence course, a basic concept is Constraint Satisfaction (CS), which is acknowledged as a hard domain for teachers to teach and student to understand. In this paper, we present a game-based learning approach to assist students in learning CS algorithms, such as arc consistency and search algorithms, for problem solving in an easy, interactive and motivating way. Preliminary valuation has showed promising results.

The Model AI Assignments session seeks to gather and disseminate the best assignment designs of the Artificial Intelligence (AI) Education community. Recognizing that assignments form the core of student learning experience, we here present abstracts of three AI assignments from the 2012 session that are easily adoptable, playfully engaging, and flexible for a variety of instructor needs.

In recent years, major research advances have taken place in the intersection of computer science and economics, but this material has so far been taught primarily at the graduate level. This paper describes a novel semester-long undergraduate-level course in the intersection of computer science and economics at Duke University, titled “CPS 173: Computational Microeconomics.”

This paper suggests some teaching strategies for Algorithms and AI courses. These courses can have a common goal of teaching complex problem-solving techniques. Based on my experience teaching undergraduates in a small liberal-arts college, the paper offers concrete ideas for working toward this goal. These ideas are supported by relevant studies in cognitive science and education. Together, they provide a plan for structuring lessons and assignments to help student become better problem-solvers.

Real-time transcription provides deaf and hard of hearing people visual access to spoken content, such as classroom instruction, and other live events. Currently, the only reliable source of real-time transcriptions are expensive, highly-trained experts who are able to keep up with speaking rates. Automatic speech recognition is cheaper but produces too many errors in realistic settings. We introduce a new approach in which partial captions from multiple non-experts are combined to produce a high-quality transcription in real-time. We demonstrate the potential of this approach with data collected from 20 non-expert captionists.