11 search results - page 2 / 3 » Meeting State Recognition from Visual and Aural Labels |
MM
2009
ACM
13 years 11 months ago
2009
ACM
Human visual perception is able to recognize a wide range of targets under challenging conditions, but has limited throughput. Machine vision and automatic content analytics can p...
CVPR
2009
IEEE
14 years 12 months ago
2009
IEEE
Multi-instance multi-label learning (MIML) refers to the
learning problems where each example is represented by a
bag/collection of instances and is labeled by multiple labels.
...
ICASSP
2011
IEEE
12 years 8 months ago
2011
IEEE
Acoustic event detection (AED) aims to identify both timestamps and types of multiple events and has been found to be very challenging. The cues for these events often times exist...
PAA
2006
13 years 4 months ago
2006
We present our studies on the application of Coupled Hidden Markov Models(CHMMs) to sports highlights extraction from broadcast video using both audio and video information. First,...
ICCV
2007
IEEE
14 years 6 months ago
2007
IEEE
Invariant feature descriptors such as SIFT and GLOH have been demonstrated to be very robust for image matching and visual recognition. However, such descriptors are generally par...