khhuiyh's picture
Upload 3 files
17a3576
raw
history blame
522 Bytes
Model,Overall Acc.,Dynamic Perception,State Transitions Perception,Camera Movement Perception,Explanatory Reasoning,Counterfactual Reasoning,Predictive Reasoning,Comparison Reasoning,Reasoning with External Knowledge,Description
[Flan-T5](https://huggingface.co/google/flan-t5-xl),27.7,27.3,28.6,23,29,32.8,31.8,20.5,31.8,33
[BLIP-2](https://github.com/salesforce/LAVIS),46.4,49.7,36.7,59.1,53.9,49.2,42.3,43.2,36.7,55.7
[VideoChat](https://github.com/OpenGVLab/Ask-Anything),37.6,39,33.7,47.1,43.8,34.9,40,32.8,34.6,42.3