Connectionists: A new dataset for evaluating performance of Partial Video Copy Detection

[Donatello Conte]

---------------------------------------

Apologies for multiple copies

---------------------------------------

 

The LIFAT laboratory (Tours city, France)  <https://lifat.univ-tours.fr/> https://lifat.univ-tours.fr/ has published a dataset, named STVD "large-Scale TV Dataset",  for the research community in the Computer Vision field. The STVD dataset is designed to aim at evaluating performance of partial video copy detection (PVCD) methods. The PVCD goal is to find one or more video segments of a reference video which have transformed copies. The STVD dataset is now public available (website link below) under an intellectual property agreement / terms of use.

 

 <https://dataset-stvd.univ-tours.fr/pvcd/> https://dataset-stvd.univ-tours.fr/pvcd/ 

 

STVD is the largest public dataset on the PVCD task. It was constituted with about 83 thousands of videos having in total of more than 10 thousands of hours duration and including more than 420 thousands of video copy pairs. It offers different test sets for a fine performance characterization (frame degradation, global transformation, video speeding, etc.) with a frame level annotation for the real-time detection and video alignment. Baseline comparisons were reported to show a room for improvement. 

 

More information about the STVD dataset can be found into the publications [1, 2]. 

 

[1] V.H. Le, M. Delalandre and D. Conte. A large-Scale TV Dataset for partial video copy detection. International Conference on Image Analysis and Processing (ICIAP), Lecture Notes in Computer Science (LNCS), vol 13233, pp. 388-399, 2022.  <https://hal.archives-ouvertes.fr/hal-03638514/document> https://hal.archives-ouvertes.fr/hal-03638514/document  

 

[2] V.H. Le, M. Delalandre and D. Conte. Une large base de données pour la détection de segments de vidéos TV. Journées Francophones des Jeunes Chercheurs en Vision par Ordinateur (ORASIS), 2021. https://hal.archives-ouvertes.fr/hal-03339724/document  

 

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20220926/bd46d2c5/attachment.html>