Location-based context is important for many applications. Previous systems offered only coarse room-level features or used manually specified room regions to determine fine-sca...
David Demirdjian, Konrad Tollmar, Kimberle Koile, ...
This paper presents a multimodal crisis management system (XISM). It employs processing of natural gesture and speech commands elicited by a user to efficiently manage complex dyn...
Nils Krahnstoever, Emilio Schapira, Sanshzar Kette...
This paper presents a novel theory for learning generic prior models from a set of observed natural images based on a minimax entropy theory that the authors studied in modeling t...
In this paper, we tackle the problem of characterizing the aesthetic appeal of consumer videos and automatically classifying them into high or low aesthetic appeal. First, we condu...
The paper proposes a new parallel connected-component-tree construction algorithm based on line independent building and progressive merging of partial 1-D trees. Two parallelizati...
P. Matas, Eva Dokladalova, Mohamed Akil, Thierry G...