Sooyeon Kang  Minsoo Jeong  Jongho Nang

10.5626/JOK.2023.50.3.257

video video partial copy detection video near-duplicated copy detection Deep Learning

With the recent generalization of video-capturing devices and the development of various multimedia platforms, video content usage is increasing every year. However, as a side effect of this, copyright infringement crimes regarding video content are also increasing. In this paper, we propose a segment fingerprint generation method for robust video copy detection systems in various transforms to address these problems. We propose a method for generating a frame fingerprint with a hybrid vision transformer, weighting the generated frame fingerprint with a transformer encoder, and fusing it into Maxpooling to aggregate a segment fingerprint. We used the VCDB dataset and measured the F1 score, which was 0.772.