This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.
July 2010
·
191 Reads
·
16 Citations
This paper presents the video retrieval engine VERGE, which combines indexing, analysis and retrieval techniques in various modalities (i.e. textual, visual and concept search). The functionalities of the search engine are demonstrated through the supported user interaction modes.
March 2010
·
126 Reads
·
8 Citations
This paper provides an overview of the tasks submitted to TRECVID 2009 by ITI-CERTH. ITI-CERTH participated in the high-level feature extraction task and the search task. In the high-level feature extraction task, techniques are developed that combine motion information with existing well-performing descriptors such as SIFT and Bag-of-Words for shot representation. In a separate run, the use of compressed video information to form a Bag-of-Words model for shot representation is studied. The search task is based on an interactive retrieval application combining retrieval functionalities in various modalities (i.e. textual, visual and concept search) with a user interface supporting interactive search over all queries submitted. Evaluation results on the submitted runs for this task provide interesting conclusions regarding the comparison of the involved retrieval functionalities as well as the strategies in interactive video search.
July 2009
·
133 Reads
·
8 Citations
In this paper, the MKLab interactive video retrieval system is described.
January 2008
·
121 Reads
·
5 Citations
Abstract In this paper, we give an overview of the four tasks submitted to TRECVID 2008 by COST292. The high-level feature extraction framework comprises four systems. The first system transforms a set of low-level descriptors into the semantic space using Latent Semantic Analysis and utilises neural networks for feature detection. The second system uses a multi-modal classifier based on SVMs and several descriptors. The third system uses three image classifiers based on ant colony optimisation, particle swarm,optimisation and a multi-objective learning algorithm. The fourth system uses a Gaussian model for singing detection and a person detection algorithm. The search task is based on an interactive retrieval application combining retrieval functionalities in various modalities with a user interface supporting automatic and interactive search over all queries submitted. The rushes task submission is based on a spectral clustering approach for removing similar scenes based on eigenvalues of frame similarity matrix and and a redundancy removal strategy which depends on semantic features extraction such as camera motion and faces. Finally, the submission to the copy detection task is conducted by two dierent,systems. The first system consists of a video module and an audio module. The second system is based on mid-level features that are related to the temporal structure of videos. Q. Zhang, K. Chandramouli, U. Damnjanovic, T. Piatrik and E. Izquierdo are with Dept. of Elec-
... Aiming to support content recommendation by estimating the relevance of media items to the thematic categories of the platform, we designed methods for image, video, and text semantic analysis. Concerning the image semantic analysis, we exploited three publicly available models pre-trained on the ImageNet [85], Places365 [86], and YouTube8M [87] datasets (1000, 365, 3886 semantic labels, respectively), as well as two new models that we trained on the TRECVID SIN [88] and the Kaggle Sports100 [89] datasets (300 and 100 semantic labels, respectively). These five models constitute model set I, which can annotate images with more than 5000 unique semantic labels. ...
March 2010
... Enriching the retrieval techniques with the past behavior of the users could potentially lead to more relevant results.In fact, in the literature, few works are interested in this aspect. Let us mention the approach mentioned by [54], which is the first to look for putting the user at the center of the retrieval process, and the work of [31], previously mentioned. The execution of a semi-automatic retrieval approach allowing us to improve the precision of the system by getting the user's feedback, along with offering the user a range of methods to express his query, such as navigation, by image example, or by text, and helping him formulate his textual query, is a very promising prospect. ...
July 2010
... In [Vrochidis 2008], the MKLab interactive retrieval system brings back in the spotlight the traditional MPEG-7 descriptors. The system takes advantage of the MPEG-7 visual descriptors capturing different aspects of human perception such as colour and texture in order to provide a content-based similarity search. ...
July 2009
... Typical supervised methods such as those used in TRECVID systems/submissions use Support Vector Machines (SVMs) to learn a pre-selected set of concepts and events (e.g. [7]). Other efforts on supervised annotation have focused on correlative tagging, which exploits annotation co-occurrences in the labeling process [8] and active learning [9]. ...
January 2008
