We address the problem of multiclass object detection. Our aims are to enable models for new categories to benefit from the detectors built previously for other categories, and fo...
Representation and measurement are two important issues for saliency models. Different with previous works that learnt sparse features from large scale natural statistics, we prop...
Xiaoshuai Sun, Hongxun Yao, Rongrong Ji, Pengfei X...
Abstract. Selective attention shift can help neural networks learn invariance. We describe a method that can produce a network with invariance to changes in visual input caused by ...
Topic models have recently emerged as powerful tools for modeling topical trends in documents. Often the resulting topics are broad and generic, associating large groups of people...
Vidit Jain, Erik G. Learned-Miller, Andrew McCallu...
Abstract. Humans can associate vision and language modalities and thus generate mental imagery, i.e. visual images, from linguistic input in an environment of unlimited inflowing i...