194 search results - page 6 / 39 » Video text recognition using feature compensation as categor... |
TRECVID
2007
13 years 9 months ago
2007
This paper describes the MSRA-USTC-SJTU experiments for TRECVID 2007. We performed the experiments in high-level feature extraction and automatic search tasks. For high-level feat...
ICCV
2007
IEEE
14 years 9 months ago
2007
IEEE
Local spatiotemporal features or interest points provide compact but descriptive representations for efficient video analysis and motion recognition. Current local feature extract...
AUSAI
2007
Springer
13 years 11 months ago
2007
Springer
Abstract. This paper describes and compares the use of methods based on Ngrams (specifically trigrams and pentagrams), together with five features, to recognise the syntactic and s...
ECCV
2010
Springer
14 years 1 months ago
2010
Springer
Abstract. We address the problem of learning good features for understanding video data. We introduce a model that learns latent representations of image sequences from pairs of su...
ICASSP
2010
IEEE
13 years 8 months ago
2010
IEEE
In this paper, we present a robust spectro-temporal feature extraction technique using autoregressive models (AR) of sub-band Hilbert envelopes. AR models of Hilbert envelopes are...