As technologies such as digital TV, video libraries, and streaming video mature, retrieving video in large archives poses an ever increasing challenge.  Moving from images to video adds several orders of complexity to the retrieval problem due to indexing, analysis, and browsing over the inherently temporal aspect of video.  For example, the user can pose a similarity based query of "Find a video scene similar to this one."  Responding to such a query requires representations of the image and temporal aspects of the video scene.  Furthermore, higher level representations which reflect the structure of the constituent video shots or semantic temporal information such as gestures could also aid in retrieving the right video scene.

Several new paradigms have emerged along the themes of video understanding.  Examples include semantic video retrieval models, interactive retrieval paradigms, and intelligent video summaries.  The goal of this special issue is to cover the state-of-the-art in video retrieval and summarization. The topics include but are not limited to the following:

• Retrieval:
• similarity among video shots and scenes
• video indexing representations and structures
• construction of video signatures
• MPEG-7 video searching
• multi-modal techniques for video retrieval
• semantic video retrieval
• symbolic video retrieval
• interactive video retrieval
• relevance feedback
• video retrieval benchmarking

 
• Summarization:
• visualization of video results
• video skims
• video manga
• video posters
• salient stills
• mosaics
• learning personal video summarizations
• data mining for video libraries