Audio-visual talking face detection

Authors:
Mingkun Li;Dongge Li;N. Dimitrova;I. Sethi
Affiliations:
Intelligent Inf. Eng. Lab, Oakland Univ., Rochester, MI, USA;IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA;IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA;IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
Venue:
ICME '03 Proceedings of the 2003 International Conference on Multimedia and Expo - Volume 1
Year:
2003

Citing 0
Cited 7

Multimedia content processing through cross-modal association

MULTIMEDIA '03 Proceedings of the eleventh ACM international conference on Multimedia
Similarity-based clustering strategy for mobile ad hoc multimedia databases

Mobile Information Systems
Omnidirectional Audio-Visual Talker Localization Based on Dynamic Fusion of Audio-Visual Features Using Validity and Reliability Criteria

IEICE - Transactions on Information and Systems
Multimodal biometric human recognition for perceptual human-computer interaction

IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
Multimedia semantics integration using linguistic model

PAKDD'06 Proceedings of the 10th Pacific-Asia conference on Advances in Knowledge Discovery and Data Mining
Location-Aware Caching for Semantic-Based Image Queries in Mobile AD HOC Networks

International Journal of Multimedia Data Engineering & Management
Multimedia search and retrieval using multimodal annotation propagation and indexing techniques

Image Communication

Quantified Score

Hi-index	0.00

Visualization

Abstract

Talking face detection is important for videoconferencing. However, the detection of the talking face is difficult because of the low resolution of the capturing devices, the informal style of communication and the background sounds. In this paper, we present a novel method for finding the talking face using latent semantic indexing approach. We tested our method on a comprehensive set of home video conferencing sessions with a very high detection rate. Our experiments show that the LSI method accuracy degrades gracefully in a noisy environment as opposed to the correlation method which simply fails in presence of noise.