A large-scale audio and video fingerprints-generated database of TV repeated contents

Abstract

Using specifically-designed lightweight audio and video fingerprints, we were able to detect repeated contents over a quasi-uninterrupted recording of 10+ TV channels, over more than 4 years, starting January 2010 (380,000 hours); the detection independently uses audio and video fingerprints. The results are stored into a database that holds more than 20 million detected repeats. Detections range from a few seconds up to one hour. The database can be explored using a standard web browser. There are many potential applications, e.g. for structuring and documenting contents.

A Large-scale TV Dataset for Partial Video Copy Detection

“…This is explained by the groundtruthing approaches requiring a huge user interaction [9,8]. Several datasets are not public available due to the intellectual property [10,16,2].…”

A large-scale TV video and metadata database for French political content analysis and fact-checking

“…Since a large amount of TV candidates' videos has to be captured, a dedicated platform for the scalable capture of TV programs [25] is required. In our work, we have used the TV workstation depicted in [20].…”

“…For storage optimization, we have set the video resolution to 320 × 240 for the capture with a parameter of 560 Kbps. This resolution has been set similar to [22,25] and presented as the best trade-off between the memory cost and video degradation. Suitable for most of the computer vision tasks such as the face and human activity recognition [28,29], it also fits with the workstation storage capacity of 5 TB and the campaign requirements of 3.4 TB.…”

“…Since, thousands of TV programs could be scheduled every months and appear in the metadata, the user selection is a challenging task. However, a large amount of these TV programs are repeated every day and week [25]. These repeated programs can be detected and grouped automatically to support the selection.…”

“…One last problem remains, indeed TV suffers from latency [25] implying a shift in the time obtained in the metadata. To deal with this issue, we have used the approach of [22].…”