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...
Tao Mei, Xian-Sheng Hua, Wei Lai, Linjun Yang, Zhe...
Local spatiotemporal features or interest points provide compact but descriptive representations for efficient video analysis and motion recognition. Current local feature extract...
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...
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...
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...