PinnedLoading

1. video_featuresvideo_featuresPublic

   Extract video features from raw videos using multiple GPUs. We support RAFT flow frames as well as S3D, I3D, R(2+1)D, VGGish, CLIP, and TIMM models.

   Python 624 102

2. SpecVQGANSpecVQGANPublic

   Source code for "Taming Visually Guided Sound Generation" (Oral at the BMVC 2021)

   Jupyter Notebook 367 39

3. BMTBMTPublic

   Source code for "Bi-modal Transformer for Dense Video Captioning" (BMVC 2020)

   Jupyter Notebook 228 56

4. MDVCMDVCPublic

   PyTorch implementation of Multi-modal Dense Video Captioning (CVPR 2020 Workshops)

   Python 143 20

5. SynchformerSynchformerPublic

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

   Python 94 9

6. SparseSyncSparseSyncPublic

   Source code for "Sparse in Space and Time: Audio-visual Synchronisation with Trainable Selectors." (Spotlight at the BMVC 2022)

   Python 53 10