Placeholder repository for ArXiv Preprint paper "DisCoVQA: Temporal Distortion-Content Transformers for Video Quality Assessment". Full code will be released later.
Since your brilliant work DiscoVQA has been accepted by IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, VOL. 33, NO. 9, SEPTEMBER 2023, is the complete code open now?
Thanks for the wonderful work, Haoning! There's one question about the Temporal Sampling on Features (TSF) in the paper, since the original token set has been sampled in this stage, how to get the Tpe whose shape is BNC (as far as I'm concerned, the dimension N should be reduced?).
Ps. It would be great if it was convenient for you to open source the codes.