Affective content detection using HMMs
MULTIMEDIA '03 Proceedings of the eleventh ACM international conference on Multimedia
Semantic context detection using audio event fusion: camera-ready version
EURASIP Journal on Applied Signal Processing
ACII '07 Proceedings of the 2nd international conference on Affective Computing and Intelligent Interaction
Hi-index | 0.00 |
Analysis of audio-visual data and detection of semanticevents with spatio-temporal support is a challenging multimedia understanding problem. The difficulty lies in the gap that exists between low level media features and high levelsemantic concept. We introduce a duration dependent input output Marko model (DDIOMM)to detect events basedon multiple modalities. The DDIOMM combines the abilityto model non-exponential duration densities with the mapping of input sequences to output sequences. We test theDDIOMM by modeling the audio-visual event explosion.We compare the detection performance of the DDIOMMwith the IOMM as well as the HMM. Experiments revealthat modeling of duration improves detection performance.