We present a novel method for the discovery and detection of visual object categories based on decompositions using topic models. The approach is capable of learning a compact and...
Many realistic visual recognition tasks are “open” in the sense that the number and nature of the categories to be learned are not initially known, and there is no closed set ...
One of the grand challenges of AI is to build systems that learn by reading. The ideal system would construct a rich knowledge base capable of automated reasoning. We have built a...
The paper presents an approach to using structural descriptions, obtained through a human-robot tutoring dialogue, as labels for the visual object models a robot learns. The paper...
Geert-Jan M. Kruijff, John D. Kelleher, Gregor Ber...
— Multi-target tracking becomes significantly more challenging when the targets are in close proximity or frequently interact with each other. This paper presents a promising tr...
Xuan Song, Huijing Zhao, Jinshi Cui, Xiaowei Shao,...