Sciweavers

2200 search results - page 298 / 440
» Objective reduction using a feature selection technique
Sort
View
SIP
2001
15 years 5 months ago
Multiresolutional descriptions of digital video in terms of "relevance"
This paper introduces algorithms for determining the "relevance" of each frame (and objects within the frame) to the scenes present in a given video sequence. Specifical...
Onur G. Guleryuz, V. Ratnakar
136
Voted
ICIP
2003
IEEE
16 years 5 months ago
Fast indexing for image retrieval based on local appearance with re-ranking
This paper describes an approach to retrieve images containing specific objects, scenes or buildings. The image content is captured by a set of local features. More precisely, we ...
Hao Shao, Tomás Svoboda, Vittorio Ferrari, ...
129
Voted
AAAI
2006
15 years 5 months ago
Active Learning with Near Misses
Assume that we are trying to build a visual recognizer for a particular class of objects--chairs, for example--using existing induction methods. Assume the assistance of a human t...
Nela Gurevich, Shaul Markovitch, Ehud Rivlin
WWW
2004
ACM
16 years 4 months ago
Mining models of human activities from the web
The ability to determine what day-to-day activity (such as cooking pasta, taking a pill, or watching a video) a person is performing is of interest in many application domains. A ...
Mike Perkowitz, Matthai Philipose, Kenneth P. Fish...
VLSID
2004
IEEE
125views VLSI» more  VLSID 2004»
16 years 4 months ago
Energy-Optimizing Source Code Transformations for OS-driven Embedded Software
The increasing software content of battery-powered embedded systems has fueled much interest in techniques for developing energyefficient embedded software. Source code transforma...
Yunsi Fei, Srivaths Ravi, Anand Raghunathan, Niraj...