This paper presents and investigates a set of local spacetime descriptors for representing and recognizing motion patterns in video. Following the idea of local features in the spatial domain, we use the notion of space-time interest points and represent video data in terms of local space-time events. To describe such events, we define several types of image descriptors over local spatio-tempor...

This paper proposes combining spatio-temporal appearance (STA) descriptors with optical flow for human action recognition. The STA descriptors are local histogram-based descriptors of space-time, suitable for building a partial representation of arbitrary spatio-temporal phenomena. Because of the possibility of iterative refinement, they are interesting in the context of online human action rec...

Trajectory-pooled Deep-learning Descriptors have been the state-of-the-art feature descriptors for human action recognition in video on many datasets. This paper improves their performance by applying the proposed eigen-evolution pooling to each trajectory, encoding the temporal evolution of deep learning features computed along the trajectory. This leads to Eigen-Evolution Trajectory (EET) des...

background: mesial temporal lobe epilepsy (tle) is a remediable epileptic syndrome. about 40% of patients continue to have seizures after standard temporal lobectomy. it has been suggested that some of these patients could actually suffer from a more complex epileptogenic network. because a few papers have been dedicated to this topic, we decided to write an article updating this theme. methods...

In this paper we address the automatic video genre classification with descriptors extracted from both, audio (blockbased features) and visual (color and temporal based) modalities. Tests performed on 26 genres from blip.tv media platform prove the potential of these descriptors to this task.

Human body movements and postures carry emotion-specific information. On the basis of this motivation, the objective of this study is to analyze this information in the spatial and temporal structure of the motion capture data and extract features that are indicative of certain emotions in terms of affective state descriptors. Our contribution comprises identifying the directly or indirectly re...

Recently Trajectory-pooled Deep-learning Descriptors were shown to achieve state-of-the-art human action recognition results on a number of datasets. This paper improves their performance by applying rank pooling to each trajectory, encoding the temporal evolution of deep learning features computed along the trajectory. This leads to Evolution-Preserving Trajectory (EPT) descriptors, a novel ty...

Recognizing actions is one of the important challenges in computer vision with respect to video data, with applications to surveillance, diagnostics of mental disorders, and video retrieval. Compared to other data modalities such as documents and images, processing video data demands orders of magnitude higher computational and storage resources. One way to alleviate this difficulty is to focus...