[ACL 2024 🔥] Video-ChatGPT is a video conversation model capable of generating meaningful conversation about videos. It combines the capabilities of LLMs with a pretrained visual encoder adapted for spatiotemporal video representation. We also introduce a rigorous 'Quantitative Evaluation Benchmarking' for video-based conversational models.
With this piece of code, you'll be able to run this file to run your inference on a sample video and get the results of your VQA model on the same terminal.
The instructions on how to run the code are in the top comment of the single_video_inference.py code. Please replace the paths with the actual paths.
With this piece of code, you'll be able to run this file to run your inference on a sample video and get the results of your VQA model on the same terminal. The instructions on how to run the code are in the top comment of the single_video_inference.py code. Please replace the paths with the actual paths.