Overview of the MPEG-7 Standard and of Future Challenges for Visual Information Analysis

Salembier, Philippe

doi:10.1155/s1110865702000781

Cited by 29 publications

(15 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Low-level features include edge [21] histograms, color histograms [27], and bag-of-visual words using SURF [1] keypoint features. The edge direction histogram provides a compact and computational efficient representation of the video.…”

Section: Feature Spacementioning

confidence: 99%

Semi-Supervised Rank Learning for Multimedia Known-Item Search

Etter

Domeniconi

2014

Proceedings of International Conference on Multimedia Retrieval

View full text Add to dashboard Cite

Known Item Search (KIS) is a specialized task of the general multimedia search problem. It describes the scenario where a user has previously seen a video and wants to find it again in a large collection using a text description. While there exists only one correct answer to a query (or topic), the goal is to return a ranked list of videos most likely to satisfy the request. This search problem includes content from speech, visual, and meta-data, and it is not clear how the individual modalities should be combined in the final result. Reranking models have been shown to be effective in problems such as image search, but the single ground truth video for a topic presents a challenge for building a model. In this paper, we propose a semi-supervised rank learning approach to the multimedia problem. We use a large training set of topics and ground truth videos to learn a pairwise ranking model based on gradient boosted regression trees. We define a learning feature space that consists of features derived from topics, videos, and topic-video dependent results. To overcome the KIS class imbalance problem, a set of pseudo positive training examples are identified from each of the multimedia modalities. This semi-supervised approach uses a ground truth video to select similar videos in each of the individual modalities. We then model the similarities as a graph and use a K-Step Markov approach to estimate the importance of nodes in the graph relative to the truth root node.

show abstract

Section: Feature Spacementioning

confidence: 99%

Semi-Supervised Rank Learning for Multimedia Known-Item Search

Etter

Domeniconi

2014

Proceedings of International Conference on Multimedia Retrieval

View full text Add to dashboard Cite

show abstract

“…Within this context, various techniques have been developed for image similarity comparisons, video characterization, and abstraction via highlighting image sequences. In general we may distinguish two basic strategies: color information and motion-based parameters [19][20][21].…”

Section: Audio-visual Content Management Approachesmentioning

confidence: 99%

“…"1D motion signals" can be effectively deployed to facilitate motion-based video summarization and abstraction. It is important to mention that the motion intensity parameter described in (8) is completely different from the "MPEG-7 motion intensity parameter," which has been established via experimental procedures considering perceptual aspects of the human vision [19][20][21]. To avoid confusion, we will use the "motion equivalent surface" (m SE ) index instead, which is equal to the square root of m int .…”

Section: Dynamic Background-foreground Segmentation For Video Motion mentioning

confidence: 99%

“…In fact, the data structures with the semiautomated extracted information of the MEDSS approach are currently employed to train more sophisticated pattern recognition systems for content classification and characterization. In any case, we have decided to use different data structures and files to store the content description information, than to incorporate them to the original recordings, following the "bits about the bits" philosophy of the MPEG-7 protocol [1,[19][20][21]. A related work, where the multimodal content interaction and the MPEG-7 schemas, that are employed to hold content descriptions, are currently under preparation.…”

Section: Multimodal Event Detection Segmentation and Summarization mentioning

confidence: 99%

See 1 more Smart Citation

Joint Wavelet Video Denoising and Motion Activity Detection in Multimodal Human Activity Analysis: Application to Video-Assisted Bioacoustic/Psychophysiological Monitoring

Dimoulas

Avdelidis

Kalliris

et al. 2007

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

The current work focuses on the design and implementation of an indoor surveillance application for long-term automated analysis of human activity, in a video-assisted biomedical monitoring system. Video processing is necessary to overcome noise-related problems, caused by suboptimal video capturing conditions, due to poor lighting or even complete darkness during overnight recordings. Modified wavelet-domain spatiotemporal Wiener filtering and motion-detection algorithms are employed to facilitate video enhancement, motion-activity-based indexing and summarization. Structural aspects for validation of the motion detection results are also used. The proposed system has been already deployed in monitoring of long-term abdominal sounds, for surveillance automation, motion-artefacts detection and connection with other psychophysiological parameters. However, it can be used to any video-assisted biomedical monitoring or other surveillance application with similar demands.

show abstract

“…Moreover, XML has become the standard format for data representation. Standards for content annotation and description, such as MPEG-7 use XML [19]. Virtually every language and specification for semantics annotation and retrieval of digital items (multimedia content, 3D models, etc.)…”

Section: An Ontology For Interactive Virtual Environmentsmentioning

confidence: 99%

Semantic Virtual Environments with Adaptive Multimodal Interfaces

Gutiérrez

Thalmann

Vexo

11th International Multimedia Modelling Conference

View full text Add to dashboard Cite

We present a system for real-time configuration of multimodal interfaces to Virtual Environments (VE). The flexibility of our tool is supported by a semantics-based representation of VEs. Semantic descriptors are used to define interaction devices and virtual entities under control. We use portable (XML) descriptors to define the I/O channels of a variety of interaction devices. Semantic description of virtual objects turns them into reactive entities with whom the user can communicate in multiple ways. This article gives details on the semantics-based representation and presents some examples of multimodal interfaces created with our system, including gestures-based and PDA-based interfaces, amongst others.

show abstract

Overview of the MPEG-7 Standard and of Future Challenges for Visual Information Analysis

Cited by 29 publications

References 7 publications

Semi-Supervised Rank Learning for Multimedia Known-Item Search

Semi-Supervised Rank Learning for Multimedia Known-Item Search

Joint Wavelet Video Denoising and Motion Activity Detection in Multimodal Human Activity Analysis: Application to Video-Assisted Bioacoustic/Psychophysiological Monitoring

Semantic Virtual Environments with Adaptive Multimodal Interfaces

Contact Info

Product

Resources

About