Paper ID: 2303.13193

VADER: Video Alignment Differencing and Retrieval

Alexander Black, Simon Jenni, Tu Bui, Md. Mehrab Tanjim, Stefano Petrangeli, Ritwik Sinha, Viswanathan Swaminathan, John Collomosse

We propose VADER, a spatio-temporal matching, alignment, and change summarization method to help fight misinformation spread via manipulated videos. VADER matches and coarsely aligns partial video fragments to candidate videos using a robust visual descriptor and scalable search over adaptively chunked video content. A transformer-based alignment module then refines the temporal localization of the query fragment within the matched video. A space-time comparator module identifies regions of manipulation between aligned content, invariant to any changes due to any residual temporal misalignments or artifacts arising from non-editorial changes of the content. Robustly matching video to a trusted source enables conclusions to be drawn on video provenance, enabling informed trust decisions on content encountered.

Submitted: Mar 23, 2023