A Multi-Model Framework for Video Information Systems

Srinivasan, Uma; Lindley, Craig A.; Simpson-Young, Bill

doi:10.1007/978-0-387-35561-0_7

Cited by 6 publications

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…15,41,42 The definition of Composite Visual Objects, 41 for example, is similar to the definition hierarchy of the VA framework, with the difference that classifiers in the Visual Apprentice are learned automatically. It is also useful to note the similarity between the definition hierarchy and structures used in MPEG-7.…”

Section: Related Workmentioning

confidence: 99%

Learning Structured Visual Detectors From User Input at Multiple Levels

Jaimes

Chang

2001

Int. J. Image Grap.

View full text Add to dashboard Cite

In this paper, we propose a new framework for the dynamic construction of structured visual object/scene detectors for content-based retrieval. In the Visual Apprentice, a user defines visual object/scene models via a multiple-level Definition Hierarchy: a scene consists of objects, which consist of object-parts, which consist of perceptual-areas, which consist of regions. The user trains the system by providing example images/videos and labeling components according to the hierarchy she defines (e.g., image of two people shaking hands contains two faces and a handshake). As the user trains the system, visual features (e.g., color, texture, motion, etc.) are extracted from each example provided, for each node of the hierarchy (defined by the user). Various machine learning algorithms are then applied to the training data, at each node, to learn classifiers. The best classifiers and features are then automatically selected for each node (using cross-validation on the training data). The process yields a Visual Object/Scene Detector (e.g., for a handshake), which consists of an hierarchy of classifiers as it was defined by the user. The Visual Detector classifies new images/videos by first automatically segmenting them, and applying the classifiers according to the hierarchy: regions are classified first, followed by the classification of perceptual-areas, object-parts and objects. We discuss how the concept of Recurrent Visual Semantics can be used to identify domains in which learning techniques such as the one presented can be applied. We then present experimental results using several hierarchies for classifying images and video shots (e.g., Baseball video, images that contain handshakes, skies, etc.). These results, which show good performance, demonstrate the feasibility and usefulness of dynamic approaches for constructing structured visual object/scene detectors from user input at multiple levels.

show abstract

Section: Related Workmentioning

confidence: 99%

Learning Structured Visual Detectors From User Input at Multiple Levels

Jaimes

Chang

2001

Int. J. Image Grap.

View full text Add to dashboard Cite

show abstract

“…The idea is to explore object and attribute level relationships at different granularity levels so that it is easy and comfortable for users to specify. This way, the user can incrementally develop the semantics at any level [7] of interpretation.…”

Section: Video Object Attributesmentioning

confidence: 99%

Modelling high level semantics for video data management

Srinivasan

Nepal²,

Reynolds³

Proceedings of 2001 International Symposium on Intelligent Multimedia, Video and Speech Processing. ISIMP 2001 (IEEE Cat. No.01

View full text Add to dashboard Cite

Phone: 61 2 9325 3148, Fax: 61 2 93253200 { Uma.Srinivasan, Surya.Nepa1, Graham.Reynolds} AbstractIn order to manage large collections of video content, we need appropriate video content models that can facilitate interaction with the content. The important issue for video applications is to accommodate different ways in which a video sequence can function semantically. In. this paper we propose and illustrate 'a metamodel framework that allows users to develop and specify their own semantics using automatically detected features and explicitly specifying objects, events and their relationships.

show abstract

Multi-modal Feature-Map: An Approach to Represent Digital Video Sequences

Srinivasan

Lindley²

1999

Visual Information and Information Systems

View full text Add to dashboard Cite

A Multi-Model Framework for Video Information Systems

Cited by 6 publications

References 14 publications

Learning Structured Visual Detectors From User Input at Multiple Levels

Learning Structured Visual Detectors From User Input at Multiple Levels

Modelling high level semantics for video data management

Multi-modal Feature-Map: An Approach to Represent Digital Video Sequences

Contact Info

Product

Resources

About