Developing effective content recognition methods for diverse imagery continues to challenge computer vision researchers. We present a new approach for document image content catego...
Guangyu Zhu, Xiaodong Yu, Yi Li, David S. Doermann
—As it is true for human perception that we gather information from different sources in natural and multi-modality forms, learning from multi-modalities has become an effective ...
In this work, we investigate how to propagate annotated labels for a given single image from the image-level to their corresponding semantic regions, namely Label-toRegion (L2R), ...
Site maps are frequently provided on Web sites as a navigation support for Web users. The automatic generation of site maps is a complex task since the structure of the data, sema...
Matching local features across images is often useful when comparing or recognizing objects or scenes, and efficient techniques for obtaining image-to-image correspondences have b...