We describe a baseline system for the VideoCLEF Vid2RSS task. The system uses an unaltered off-the-shelf Information Retrieval system. ASR content is indexed using
default stemming and stopping methods. The subject categories are populated by using the category label as a query on the collection, and assigning the retrieved items
to that particular category. We describe the results of the system and provide some high-level analysis of its performance.
Metadata
Item Type:
Conference or Workshop Item (Paper)
Event Type:
Workshop
Refereed:
Yes
Uncontrolled Keywords:
Classification; Information Retrieval; Automatic Speech Recognition