Most existing detection pipelines treat object proposals independently and predict bounding box locations and classification scores over them separately. However, the important semantic and spatial ...

Whipping out “Who’s More Likely” questions with close friends brings some competitive advantages, like in-depth knowledge of the other players and a built-in trove of embarrassing personal anecdotes ...

Existing object tracking applications focus on finding the moving patterns of a single object or all objects. In contrast, we propose a distributed mining algorithm that identifies a group of objects ...