In this paper, the system developed by the University of Bremen for participation in the Trecvid 2006 high-level feature extraction task is presented. Six runs have been submitted, each of them incorporating a different combination of three classifiers based on image, sound, and text features. For the feature Corporate Leader, aboveaverage results could be achieved. Results are shown and differ...

Human Behavior Analysis in Uncontrolled Environments can be categorized in two main challenges: 1) Feature extraction and 2) Behavior analysis from a set of corporal language vocabulary. In this work, we present our achievements characterizing some simple behaviors from visual data on different real applications and discuss our plan for future work: low level vocabulary definition from bag-of-g...

We describe a high level feature extraction system for video. Video sequences are modeled using Gaussian Mixture Models. We have used those models in the past to segment video sequences into 2D+time objects. The segmentation result has been used with great success in a compression scheme. In the present work, the Gaussian components of the model are considered to completely model the correspond...

This work presents an approach on high-level semantic feature detection in video sequences. Keyframes are selected to represent the visual content of the shots. Then, low-level feature extraction is performed on the keyframes and a feature vector including color and texture features is formed. A region thesaurus that contains all the high-level features is constructed using a subtractive cluste...

In this paper, we propose a novel deep neural network framework embedded with low-level features (LCNN) for salient object detection in complex images. We utilise the advantage of convolutional neural networks to automatically learn the high-level features that capture the structured information and semantic context in the image. In order to better adapt a CNN model into the saliency task, we r...

With the development of digital cameras, the digital photographs were flooded in our life. How to classify images efficiently in huge image database becomes an important research topic. In recent years, the related researches of the image classification are based on semantics. The scene image classification has received much attention especially because it contains plenty semantics. It is a dif...