Quoc-Bao Nguyen

Automatic Curation of Golf Highlights Using Multimodal Excitement Features

The production of sports highlight packages summarizing a game’s most exciting moments is an essential task for broadcast media. Yet, it requires labor-intensive video editing. We propose a novel approach for auto-curating sports highlights, and use it to create a real-world system for the editorial aid of golf highlight reels. Our method fuses information from the players’ reactions (action recognition such as high-fives and fist pumps), spectators (crowd cheering), and commentator (tone of the voice and word analysis) to determine the most interesting moments of a game. We accurately identify the start and end frames of key shot highlights with additional metadata, such as the player’s name and the hole number, allowing personalized content summarization and retrieval. In addition, we introduce new techniques for learning our classifiers with reduced manual training data annotation by exploiting the correlation of different modalities. Our work has been demonstrated at a major golf tournament, successfully extracting highlights from live video streams over four consecutive days.

Community Situational Awareness and Resilience through Mobile Applications

Access to social networks via portable devices promises to be especially valuable for public communities. Because smart phones increasingly accompany community members wherever they are, the social network extends into everyday interactions where location-specific, real time interactions are natural and resulting actions can be immediate. Governments and NGOs can leverage the self-organizing, collectively-intelligent community to improve situational awareness and improve the communitys resilience. At this time of limited public budgets, static but authoritative data can be combined with dynamic data provided by citizens. This paper reports our experience and challenges in building a mobile app named Yellow Button. We describe the architecture of Yellow Button and our experience in the initial applications to utilities, traffic and transportation.

A bid evaluation system for Internet contract negotiation

Competitive advantages in a fast-changing electronic procurement market are enabling buyers to explore many opportunities to purchase the best commodities, not only at the most favorable prices, but also to satisfy business objectives and organizational strategies. Some seasonal commodities and future contracts have to deal with uncontrollable factors such as the elasticity of the price and the constant variation of the demand. These trends present some new challenges in bid evaluations and business decisions. We have developed a system, which uses a hierarchical decision-criteria framework to handle complex constraint hierarchy with n-ary variables. In addition, the system provides the mechanism to analyze and forecast certain events based on the seasonal and historical data.