Pinned Loading

1. TRIAD TRIAD Public

   Tri-modal Dense feature grounding between Text-Image-Audio for multimodal prompted localization of features and embedding in a shared space.

   Python

2. AV-Align AV-Align Public

   Unsupervised Audio-Visual feature alignment: Repository for audio and visual features embedding onto the same latent space for downstream tasks.

   Python

3. LetMeSee LetMeSee Public

   Learned Content aware patch truncation for ViTs for compute efficiency through soft masking during raining.

   Python

4. ICPR-RIP ICPR-RIP Public

   [ICPR 2024 Competition on Rider Intention Prediction] - [Top Submission] - State-Space Model based sequence modelling of rider's-view videos for intent prediction tasks.

   Jupyter Notebook