tterns help narrow the gap between the abstract views of the data structures and their concrete implementations. The smaller the gap, the higher the level action. The more abstract...
Traditional browsing of large multimedia documents (e.g., video, audio) is primarily sequential. In the absence of an index structure browsing and searching for relevant informatio...
Abstract. In this paper, we present a logical representation for form documents to be used for identification and retrieval. A hierarchical structure is proposed to represent the s...
Most existing structure from motion (SFM) approaches for unordered images cannot handle multiple instances of the same structure in the scene. When image pairs containing differen...
Richard Roberts, Sudipta Sinha, Richard Szeliski, ...