This paper describes our participation in the NIST TERCVID 2004 retrieval evaluation. In the first-year effort for the TERCVID project, we only tackle Person X detection of the high-level feature extraction task. We design an automatic Person X detector using frontal faces in videos solely. We illustrate the architecture of Person X detector and the evaluation results in this paper.

This report proposes and compares a number of tandem-like feature extraction schemes. The proposed schemes use relative phone posteriors as confidence measures estimated from the MLP outputs directly or using Gamma function. The analysis of variances shows that the proposed tandem-like features discriminate better between phone classes than the conventional tandem features. But these capabiliti...

We present in this paper a study on auditory feature spaces for speech-driven face animation. The goal is to provide solid analytic ground to underscore the description capability of some well-known features with relation to lipsync. A set of various audio features describing the temporal and spectral shape of speech signal has been computed on annotated audio extracts. The dimension of the inp...

We describe our fourth participation, that includes two high-level feature extraction runs, and one manual search run, to the TRECVID video retrieval evaluation. All of these runs have used a system trained on the common development collection. Only visual information, consisting of color, texture and edge-based low-level features, was used.

Automatic creation of image descriptions, i.e. captioning images, is an important topic in artificial intelligence (AI) that bridges the gap between computer vision (CV) and natural language processing (NLP). Currently, neural networks are becoming increasingly popular images researchers looking for more efficient models CV sequence-sequence systems. This study focuses on a new caption generati...

We present a mcthod to lcarn diverse group of object categories from an unordcrcd point set. propose our Pyramid Point network, which uses dense pyramid structure instead thc traditional ’U’ shape, typically seen in semantic segmentation networks. This gives second look, allowing network revisit different layers creating various leveis on the for feature propagation. introduce Foc...