Sciweavers

149 search results - page 24 / 30
» Modeling Background and Segmenting Moving Objects from Compr...
Sort
View
CVPR
2011
IEEE
13 years 4 months ago
Learning to Recognize Objects in Egocentric Activities
This paper addresses the problem of learning object models from egocentric video of household activities, using extremely weak supervision. For each activity sequence, we know onl...
Alireza Fathi, Xiaofeng Ren, James Rehg
IJCV
2002
141views more  IJCV 2002»
13 years 7 months ago
Spatio-Temporal Stereo Using Multi-Resolution Subdivision Surfaces
We present a method to automatically extract spatio-temporal descriptions of moving objects from synchronized and calibrated multi-view sequences. The object is modeled by a time-...
Jan Neumann, Yiannis Aloimonos
ACCV
2006
Springer
13 years 11 months ago
Motion Detection in Driving Environment Using U-V-Disparity
Abstract. Motion detection in driving environment, which aims to detect REAL moving objects from continuously changing background, is vital for Adaptive Cruise Control (ACC) applic...
Jia Wang, Zhencheng Hu, Hanqing Lu, Keiichi Uchimu...
MM
2004
ACM
188views Multimedia» more  MM 2004»
14 years 1 months ago
A new method to segment playfield and its applications in match analysis in sports video
With the growing popularity of digitized sports video, automatic analysis of them need be processed to facilitate semantic summarization and retrieval. Playfield plays the fundame...
Shuqiang Jiang, Qixiang Ye, Wen Gao, Tiejun Huang
WAPCV
2007
Springer
14 years 1 months ago
Language Label Learning for Visual Concepts Discovered from Video Sequences
Computational models of grounded language learning have been based on the premise that words and concepts are learned simultaneously. Given the mounting cognitive evidence for conc...
Prithwijit Guha, Amitabha Mukerjee