Pinned Loading

1. seeAoT seeAoT Public

   Code and data release for the paper "Seeing the Arrow of Time in Large Multimodal Models"

   Python 12

2. ProgCaptioner ProgCaptioner Public

   Code release for the paper "Progress-Aware Video Frame Captioning" (CVPR 2025)

   Python 20 1

3. HOISwap HOISwap Public

   [NeurIPS 2024] HOI-Swap: Swapping Objects in Videos with Hand-Object Interaction Awareness

   Python 25

4. facebookresearch/VidOSC facebookresearch/VidOSC Public archive

   Code and data release for the paper "Learning Object State Changes in Videos: An Open-World Perspective" (CVPR 2024)

   Python 35 2

5. DynMM DynMM Public

   Code for the paper 'Dynamic Multimodal Fusion'

   Python 121 17

6. MFH MFH Public

   [ICLR 23 oral] The Modality Focusing Hypothesis: Towards Understanding Crossmodal Knowledge Distillation

   Python 46 4