Real-world videos often contain dynamic backgrounds and evolving people activities, especially for those web videos generated by users in unconstrained scenarios. This paper proposes a new visual representation, namely scene aligned pooling, for the task of event recognition in complex videos. Based on the observation that a video clip is often composed with shots of different scenes, the key i...

The present work is a part of research study aiming to develop an algorithm and a software system capable of quick identification of weapons and relations between human and a weapon in a scene. Bridging the semantic gap between the low level knowledge extracted from an image and the high level semantics needed to negotiate the weapon domain ontology is connected to the features extraction algor...

We describe the MusicMiner system for organizing large collections of music with databionic mining techniques. Low level audio features are extracted from the raw audio data on short time windows during which the sound is assumed to be stationary. Static and temporal statistics were consistently and systematically used for aggregation of low level features to form high level features. A supervi...

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...

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...

One difficulty in the HLF task this year was changing the applied domain from news video to foreign documentary videos. Classifiers trained in prior years performed poorly if naively applied, and classifiers trained on the 2007 data alone may suffer from too few positive training samples. This year we address this new fundamental problem how to efficiently and effectively adapt models learned f...

In this paper, we describe our approach and results for high-level feature extraction task (HLF) at TRECVID2008. This year, our focus is to develop a framework which fuses a number of features effectively. In our paper, color , face, motion, text, and local pattern features were extracted. After that, a simplymodified version of Adaboost algorithm was implemented as a late fusion to combine all...