v-iashin

v-iashin/Synchformer

Source code for "Synchformer: Efficient Synchronization from Sparse Cues" (ICASSP 2024)

132 stars 11 forks 132 watchers Python MIT License
audio-visual contrastive-learning multi-modal synchronization video-understanding
View on GitHub Website
1 Open Issue Need Help Last updated: Aug 12, 2026

Open Issues Need Help

View All on GitHub
Inconsistent `acccuracy_1` results with `av>=9.1.1` about 2 hours ago
help wanted
v-iashin/Synchformer
132

Source code for "Synchformer: Efficient Synchronization from Sparse Cues" (ICASSP 2024)

Python
#audio-visual#contrastive-learning#multi-modal#synchronization#video-understanding