This paper presents our approaches and results of the four TRECVID 2008 tasks we participated in: high-level feature extraction, automatic video search, video copy detection, and ...
Head pose and gesture offer several key conversational grounding cues and are used extensively in face-to-face interaction among people. We investigate how dialog context from an ...
Louis-Philippe Morency, Candace L. Sidner, Christo...
: Present-day handheld devices, such as PDAs, are a useful blend of hardware and software oriented toward the mobile workforce. While they provide the capability to review document...
In the novelty task on sentence level, the amount of information used in similarity computation is the major challenging issue. A shallow NLP approach extracts noun and verb featu...
This paper introduced a human surveillance system which integrated the face understanding technologies to recognize personal identities in real time. We proposed a coarse-to-fine s...