In this paper, we investigate the contribution of dynamic evolution of 3D faces to identity recognition. To this end, we adopt a subspace representation of the flow of curvature-maps computed on 3D facial frames of a sequence, after normalizing their pose. Such representation allows us to embody the shape as well as its temporal evolution within the same subspace representation. Dictionary lear...

The Knowledge Representation Package consist of a framework that implement several kinds of processing engines. The framework using a data structure based on the Blackboard pattern [2], is written in Java and has three main components: knowledge representation, knowledge repository and inference engine. It can be used for make reasoning in semantic networks, frames or rule based systems. In inf...

The recognition of objects that appear in a video sequence is an essential aspect of any video content analysis system. We present an approach which classifies a segmented video object based on its appearance (object views) in successive video frames. The classification is performed by matching curvature features of the contours of these object views to a database containing preprocessed views ...

We use principal component analysis (PCA) to reduce the dimensionality of features of video frames for the purpose of content description. This low-dimensional description makes practical the direct use of all the frames of a video sequence in later analysis. The PCA representation circumvents or eliminates several of the stumbling blocks in current analysis methods and makes new analyses feasi...

The recognition of objects that appear in a video sequence is an essential aspect of any video content analysis system. We present an approach which classifies a segmented video object based on its appearance (object views) in successive video frames. The classification is performed by matching curvature features of the contours of these object views to a database containing preprocessed views ...

As the demand of video summarization techniques increases nowadays, many methods are proposed for how to extract best representating key frames of a video. While most of them rely on hand-crafted image features, we resort to the feature learning power of deep convolutional networks. In this final project, we propose to learn a new image representation such that the similarity of frames are spec...

In this paper we propose a novel motion saliency estimation method for video sequences considering the motion between successive frames and their corresponding parametric camera motion representation. Background motion is compensated for every pair of frames, revealing areas that contain relative motion. Considering that these areas will likely attract the attention of the viewer and in line wi...

An elaboration on (Das et al., 2010), this report formalizes frame-semantic parsing as a structure prediction problem and describes an implemented parser that transforms an English sentence into a frame-semantic representation. SEMAFOR 1.0 finds words that evoke FrameNet frames, selects frames for them, and locates the arguments for each frame. The system uses two feature-based, discriminative ...

This paper describes a hierarchical approach towards the extraction of highly informative summarized information of humans from video sequences. Objects of interest, such as facial features, are detected through transformation-invariant clustering of the frames, iteratively from bigger to smaller regions, and then expressed with an informationrich representation obtained by super-resolution. To...

The recognition of objects that appear in a video sequence is an essential aspect of any video content analysis system. We present an approach which classifies a segmented video object based on its appearance (object views) in successive video frames. The classification is performed by matching curvature features of the contours of these object views to a database containing preprocessed views ...