This paper is interested with the performance evaluation of the partial video copy detection. Several public datasets exist designed from web videos. The detection problem is inherent to the continuous video broadcasting. The alternative is then to process with TV datasets offering a deeper scalability and a control of degradations for a fine performance evaluation. We propose in this paper a TV dataset called STVD. It is designed with a protocol ensuring a scalable capture and robust groundtruthing. STVD is the largest public dataset on the task with a near 83k videos having a total duration of 10, 660 hours. Performance evaluation results of representative methods on the dataset are reported in the paper for a baseline comparison.

A system for the real-time copy detection of live TV videos is presented. A TV workstation supports the real-time and multichannel processing. Real-time NCC features are used for matching. A key-frame selection method ensures the robustness, the response and processing time optimization. Experiments are reported for time processing and accuracy on a public dataset against competitive methods.

In this paper, we introduce a large-scale multimodal publicly available dataset 1 for the French political content analysis and factchecking. This dataset consists of more than 1, 200 fact-checked claims that have been scraped from a fact-checking service with associated metadata. For the video counterpart, the dataset contains nearly 6, 730 TV programs, having a total duration of 6, 540 hours, with metadata. These programs have been collected during the 2022 French presidential election with a dedicated workstation.