[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.
I am currently working with a dataset and have come across the QA_GT_caption_based_noisy tag. However, its role and purpose within the dataset are unclear to me. There are instances where this tag appears in the inference output. Could you please provide some insight into what this tag signifies? Is it something that we can safely remove or ignore during our processes?
Thank you for your assistance and time in addressing this query.
Thank you for your interest in our work. This might be related to the noise due to automatic annotations. It can be removed/filtered from the annotations. Thanks
Hello,
I am currently working with a dataset and have come across the QA_GT_caption_based_noisy tag. However, its role and purpose within the dataset are unclear to me. There are instances where this tag appears in the inference output. Could you please provide some insight into what this tag signifies? Is it something that we can safely remove or ignore during our processes?
Thank you for your assistance and time in addressing this query.