A Similarity Alignment Model for Video Copy Segment Matching
This addresses video copy detection for social media platforms, representing an incremental advancement in a specific competition.
The paper tackles the problem of video copy segment matching, proposing a Similarity Alignment Model (SAM) that achieved first place in the CVPR 2023 Video Similarity Challenge, with absolute improvements of 0.108 and 0.144 over the second-place competitor in two phases.
With the development of multimedia technology, Video Copy Detection has been a crucial problem for social media platforms. Meta AI hold Video Similarity Challenge on CVPR 2023 to push the technology forward. In this report, we share our winner solutions on Matching Track. We propose a Similarity Alignment Model(SAM) for video copy segment matching. Our SAM exhibits superior performance compared to other competitors, with a 0.108 / 0.144 absolute improvement over the second-place competitor in Phase 1 / Phase 2. Code is available at https://github.com/FeipengMa6/VSC22-Submission/tree/main/VSC22-Matching-Track-1st.