Image segmentation is conventionally formulated as a pixellabeling problem, in which “hard” decisions have to be made to partition pixels into regions. As image segmentation i...
Unsupervised learning can be used to extract image representations that are useful for various and diverse vision tasks. After noticing that most biological vision systems for int...
The bag-of-words representation has attracted a lot of attention recently in the field of object recognition. Based on the bag-of-words representation, topic models such as Probab...
Objects in scenes interact with each other in complex ways. A key observation is that these interactions manifest themselves as predictable visual patterns in the image. Discoveri...
Recent work in object categorization often uses local image descriptors such as SIFT to learn and detect object categories. Such descriptors explicitly code local appearance and h...