Linear Discriminant Analysis (LDA) is a well-known method for dimensionality reduction and classification. Previous studies have also extended the binary-class case into multi-classes. However, many applications, such as object detection and keyframe extraction cannot provide consistent instance-label pairs, while LDA requires labels on instance level for training. Thus it cannot be directly ap...

Motion capture is an increasingly popular animation technique; however data acquired by motion capture can become substantial. This makes it difficult to use motion capture data in a number of applications, such as motion editing, motion understanding, automatic motion summarization, motion thumbnail generation, or motion database search and retrieval. To overcome this limitation, we propose an...

ions," Proceedings of the CHI '98 Conference on Human Factors in Computing Systems (Los Angeles, CA, Apr. 1998), pp. 171-178 (1998). Christel et al. "Information Visualization within a Digital Video Library," Journal of Intelligent Information Systems 11 :235-257 (1998). Dellaert et al. "Recognizing emotion in speech," Proceedings ICSLP 96. Fourth International Conference on Spoken Language Pro...

Sign Language Recognition (SLR) targets interpreting the signs so as to facilitate communication between hearing or speaking disabled people and normal people. This makes signers effective seamless. The scarcely available key information regarding gestures is recognise signs. To implement continuous sign language gesture recognition, are identified from video using Deep Convolutional Neural Net...

Content based video indexing and retrieval has its foundations in the analyses of the prime video temporal structures. Consequently, technologies for video segmentation and key-frame extraction have become crucial for the development of advanced digital video systems. Conventional algorithms for video partitioning and keyframe extraction are mainly implemented autonomously. By focusing the anal...

For the high-level feature extraction task, we use visual features (visual words of keyframe images and motion features), and do not use any audio information. Maximum entropy models [1] are employed to model these visual features. Because there was a material mistake in our submission, the inferred Average Precisions of our runs was almost zero. Therefore, in this notebook, we also show the re...

The use of hidden Markov models (HMMs) for the high-level feature detection task of TRECVID 2005 is described. Highlevel features present in a keyframe are assumed to constitute the state-space of a Markov chain. The observed visual features of the keyframe, as well as the text accompanying the keyframe, are modeled as stochastic emissions from (unobserved) states of this Markov chain. Manual a...

In this paper, we present the methodology we use in the NIST TRECVID'2005 evaluation. We have participated in the High-level Feature Extraction task. Our approach is founded on Fuzzy Decision Trees through the Salammbô software. 1 Structured Abstract Summary Here we present the contribution of the University of Paris 6 at TRECVID 2005 [1]. It concerns only the High-Level Feature Extraction task...