Channel-Wise Spatiotemporal Aggregation Technology for Face Video Forensics

Table 7

Binary classification accuracy (%) (higher is better) on video clips on the Celeb-DF dataset.

Model	1	3	6	9	12	15	18
CWSA net	93.97	95.86	96.27	96.17	97.12	96.91	95.28
CNN-LSTM	—	95.22	95.06	95.13	96.53	96.38	95.28